# Show HN: Have your agent consult other models > Source: > Published: 2026-06-14 07:34:40+00:00 [Quick start](#quick-start) · [Usage](#usage) · [Providers & Configuration](#providers--configuration) · [Skills](#skills) · [Logging](#logging) · [Monitor](#monitor) · [Changelog](/raine/consult-llm/blob/main/CHANGELOG.md) `consult-llm` is a tool for getting a second opinion from another AI model, right inside your existing agent workflow. Use it to plan architecture, review changes, debate approaches, or get unstuck on tricky bugs. It supports GPT-5.5, Gemini 3.1 Pro, Claude Opus 4.7, DeepSeek V4 Pro, MiniMax M2.7, and Grok 4.3, along with any `openrouter/*` model, with API and local CLI backends, multi-turn threads, git diff context, web-mode clipboard export, and a live monitor TUI. A model reviewing its own work isn't an independent check. Even in a fresh context, it shares the same training, priors, and many of the same failure modes. A different model was trained differently and makes different mistakes, so it's more likely to push back, challenge weak reasoning, or expose a blind spot. Model strengths are uneven and hard to predict per task. A quick cross-check is cheap, and sometimes the other model is the one that finds the path forward. - Install skills into your agent (Claude Code, Codex, OpenCode) - Trigger with a slash command: `/consult` ,`/debate` ,`/collab` - The skill pipes your prompt into `consult-llm` , which calls the backend and streams the response back inline For the more detailed flow, [continue below](#how-it-really-works). ``` > The hint unlocking is still broken after your fix. Ask gemini ⏺ Skill(consult-llm) ⎿ Successfully loaded skill · 1 tool allowed ⏺ Let me consult Gemini to understand this segmentation mismatch: ⏺ Bash(cat issue.md | consult-llm -m gemini -f HintsText.tsx -f hints.ts) ⎿ [model:gemini-3.1-pro-preview] The root cause is a race condition in `handleConfirmGenerateHints`. After `await generateHints()`, the component state updates in the background, but the function continues with a stale `activeSegment` variable, requesting a hint for "isn't" instead of "isn't it". ⏺ Gemini identified the real issue: a race condition with stale state after async operations. I was looking at the wrong thing entirely. ``` Note This project previously used MCP as its transport layer. If you were using that version, see the [migration guide](#migrating-from-mcp) below. **Get a second opinion from another model** from your agent with relevant file context (`/consult` )**Have models debate the best approach** and synthesize a consensus (`/debate` )**Use existing subscriptions** via CLI backends without API keys ([Gemini CLI](#gemini-cli),[Codex CLI](#codex-cli),[Cursor CLI](#cursor-cli),[Claude CLI](#profile-backend),[OpenCode](#opencode))**Continue conversations across requests** with`thread_id` **Copy prompts to clipboard** for browser-based LLMs (`--web` )in a real-time TUI[Monitor](#monitor)active and past runs - Install the binaries: ``` # Homebrew brew install raine/consult-llm/consult-llm # Shell script (macOS/Linux) curl -fsSL https://raw.githubusercontent.com/raine/consult-llm/main/scripts/install.sh | bash ``` - Configure a backend. CLI backends are the easiest if you have an existing subscription (no API key needed): ``` consult-llm config set gemini.backend gemini-cli # requires: gemini login consult-llm config set openai.backend codex-cli # requires: codex login ``` Or set API keys: ``` consult-llm config set openai.api_key your_openai_key consult-llm config set gemini.api_key your_gemini_key consult-llm config set grok.api_key your_xai_key # or via environment variables: OPENAI_API_KEY, GEMINI_API_KEY, XAI_API_KEY, etc. ``` - Verify your setup: ``` consult-llm models # see available models and resolved selectors echo "hello" | consult-llm -m gemini # quick smoke test ``` - Install the skills so your agent can call `consult-llm` for you: ``` consult-llm install-skills ``` Then invoke skills from inside your agent (see [Usage](#usage) right below). Some real-world examples. Click to expand. ## Explain the problem, and tell CC to consult a smarter LLM ``` Consult LLM for assistance, use gemini ⏺ I see the issue! The problem is that the frontend is trying to use the hint for "isn't" but the server generated a hint for "isn't it" (the full phrase). This is a mismatch between how the frontend segments text and how the server generates hints. Let me consult the LLM to get assistance on this segmentation mismatch issue. ⏺ Write(hint-segmentation-issue.md) ⎿ Wrote 53 lines to hint-segmentation-issue.md # Hint Segmentation Mismatch Issue ## Problem Description There's a mismatch between how the frontend segments text for clickable words and how the backend generates hints. This causes hint unlocking to fail when the segments don't match exactly. ## Example Case **Original Text**: "Hello! Nice weather, isn't it?" … +43 lines (ctrl+r to expand) ⏺ Bash(cat hint-segmentation-issue.md | consult-llm -m gemini -f hint-segmentation-issue.md -f web/src/components/HintsText.tsx -f web/src/utils/hints.ts -f server/src/routes/public/hints.ts -f server/src/llm/hints.ts) ⎿ [model:gemini-3.1-pro-preview] [thread_id:a3f7c...] An excellent analysis of the problem. The root cause has been correctly identified: a race condition within the `handleConfirmGenerateHints` function in `HintsText.tsx`. The component state updates in the background after `await generateHints()`, but the function continues executing with a stale `activeSegment` variable, causing it to request a hint for a smaller text segment ( e.g., "isn't") instead of the full, newly-available hint phrase (e.g., "isn't it"). … +607 lines (ctrl+r to expand) ⏺ Perfect! The LLM identified the core issue - there's a race condition in handleConfirmGenerateHints where the function uses stale state after async operations. The solution is to re-target the hint key after generation to find the correct matching hint. Let me implement this solution: ⏺ Update Todos ⎿ ☐ Fix hint segmentation mismatch by implementing smarter hint key targeting in handleConfirmGenerateHints ``` ## Using web mode to copy prompts to clipboard for browser-based LLMs ``` > I need help implementing a -b/--background flag for my Rust CLI. Use consult LLM with web mode ⏺ I'll use web mode to copy the formatted prompt to your clipboard so you can paste it into any browser-based LLM service. ⏺ Bash(cat <<'EOF' | consult-llm -m gemini --web -f src/cli.rs -f src/workflow.rs -f src/tmux.rs What is the best approach to implement a -b/--background flag for the "workmux add" command that creates a tmux window in the background without switching to it? The current implementation automatically switches to the newly created window via `tmux::select_window()` in the `setup_environment()` function. I need to make this behavior conditional based on a flag passed from the CLI. Consider: 1. Where should the background flag be threaded through the call chain? 2. Should I modify the existing SetupOptions struct or add a parameter? 3. What's the most maintainable approach given the codebase structure? 4. Are there any edge cases to consider (e.g., should select_pane also be conditional)? EOF) ⎿ ✓ Prompt copied to clipboard! Please paste it into your browser-based LLM service and share the response here before I proceed with any implementation. Note: File paths were included: - src/cli.rs - src/workflow.rs - src/tmux.rs > [User pastes the response from the external LLM] ⏺ Thank you! Based on the recommendations, I'll now implement the solution... ``` This is useful when: - You want to use a free browser-based LLM service instead of API credits - You prefer a specific LLM's web interface - You want to review the full prompt before submitting it ## Debugging Neovim plugin treesitter API breakage ``` ⏺ Fixed! Added nil checks for both node and child and updated the iter_matches call to handle the newer API properly. > Still not working: E5108: Error executing lua /Users/raine/code/testonly.nvim/lua/testonly.lua:92: attempt to call method 'child' (a nil value) stack traceback: /Users/raine/code/testonly.nvim/lua/testonly.lua:92: in function 'reset_all_exclusive' /Users/raine/code/testonly.nvim/lua/testonly.lua:110: in function 'reset_all_exclusive' [string ":lua"]:1: in main chunk Ask gemini ⏺ Let me consult with a more powerful AI to understand the current Neovim treesitter API changes: ⏺ Bash(cat <<'EOF' | consult-llm -m gemini -f lua/testonly.lua I'm debugging a Neovim plugin that's broken due to treesitter API changes. The error is "attempt to call method 'child' (a nil value)" on line 92. The code is trying to access child nodes from treesitter matches but the API seems to have changed in newer Neovim versions. Here's the problematic code: ``` lua for _, match, _ in parsed_query:iter_matches(root, bufnr, start_row, end_row) do for id, node in pairs(match) do local name = parsed_query.captures[id] if name == "call" and node then local child = node:child(0) -- ERROR HERE if child then local text = vim.treesitter.get_node_text(child, bufnr) -- ... rest of logic end end end end ``` What's the correct way to iterate over treesitter query matches and access child nodes in current Neovim versions? What API changes should I be aware of? EOF) ⎿ [model:gemini-3.1-pro-preview] [thread_id:b9e2a...] Problem ------- … +93 lines (ctrl+r to expand) ⏺ Perfect! The issue is that iter_matches() can return nil nodes in the match table. Let me fix this by switching to the recommended iter_captures() approach: ⏺ Update(lua/testonly.lua) ⎿ Updated lua/testonly.lua with 7 additions and 10 removals 85 local root = parser:parse()[1]:root() 86 local start_row, _, end_row, _ = root:range() 87 88 - for _, match, _ in parsed_query:iter_matches(root, bufnr, start_row, end_row) do 89 - for id, node in pairs(match) do 90 - local name = parsed_query.captures[id] 91 - if name == "call" and node then 92 - local child = node:child(0) 93 - if child then 94 - local text = vim.treesitter.get_node_text(child, bufnr) 88 + for id, node, _ in parsed_query:iter_captures(root, bufnr, start_row, end_row) do 89 + if parsed_query.captures[id] == "call" then 90 + local first_child = node:named_child(0) 91 + if first_child then 92 + local text = vim.treesitter.get_node_text(first_child, bufnr) 93 94 - if text == "it.only" or text == "describe.only" then 95 - toggle_test_exclusive(child) 96 - end 94 + if text == "it.only" or text == "describe.only" then 95 + toggle_test_exclusive(first_child) 96 end 97 end 98 end ``` ## Using slash command to consult multiple LLMs for comparison ``` > /consult The branch completions should dynamic. Git should be called only when using tab to autocomplete. Ask gemini and codex ⏺ I'll consult both Gemini and Codex about making the branch completions dynamic (only calling git when tab-completing). Let me gather the relevant context first. ⏺ Bash(cat <<'EOF' | consult-llm -m gemini -f src/cli.rs -f src/git.rs I have a Rust CLI tool using clap that needs dynamic shell completions. Currently, the branch completions are generated at completion script generation time via `possible_values()`. Instead, I need the git operations to only run when the user presses TAB to autocomplete. Current setup: 1. `WorktreeBranchParser` implements `TypedValueParser` with `possible_values()` that calls git 2. Shell completions are generated via clap_complete's `generate()` function 3. The completions are sourced at shell startup: `source <(workmux completions zsh)` The problem: Running `workmux completions zsh` takes ~210ms because it runs git operations during completion generation, not during actual tab completion. How can I implement truly dynamic completions where git is only called when the user presses TAB? What's the best approach with clap and clap_complete for zsh? EOF) ⎿ [model:gemini-3.1-pro-preview] [thread_id:c1d4e...] The root cause of the slow startup (~210ms) is that `clap_complete::generate()` executes your `possible_values()` logic (git operations) *while generating the script*. This bakes the *current* branches into the static script, which is both slow (happens every time you `source` it) and incorrect (branches become stale). … +116 lines (ctrl+o to expand) ⏺ Bash(cat <<'EOF' | consult-llm -m codex -f src/cli.rs -f src/git.rs I have a Rust CLI tool using clap that needs dynamic shell completions. Currently, the branch completions are generated at completion script generation time via `possible_values()`. Instead, I need the git operations to only run when the user presses TAB to autocomplete. Current setup: 1. `WorktreeBranchParser` implements `TypedValueParser` with `possible_values()` that calls git 2. Shell completions are generated via clap_complete's `generate()` function 3. The completions are sourced at shell startup: `source <(workmux completions zsh)` The problem: Running `workmux completions zsh` takes ~210ms because it runs git operations during completion generation, not during actual tab completion. How can I implement truly dynamic completions where git is only called when the user presses TAB? What's the best approach with clap and clap_complete for zsh? EOF) ⎿ [model:gpt-5.1-codex-max] [thread_id:d2f5b...] **Findings** - `WorktreeBranchParser::possible_values` (`cli.rs:41-72`) runs git during script generation, so `workmux completions zsh` always pays the git cost (~210ms) even though the result is only needed at tab time. … +77 lines (ctrl+o to expand) ⏺ Summary from Gemini and Codex Both agree on the same solution: Root Cause clap_complete::generate() calls possible_values() during script generation, not at tab-completion time. This means git runs every shell startup. ... ``` This example shows using the `/consult` slash command to ask multiple LLMs (Gemini and Codex) about the same problem **in parallel** and compare their responses. Both LLMs independently arrived at the same solution, providing confidence in the approach. The CLI is invoked by your agent via the installed skills; you don't call it directly. From inside Claude Code, OpenCode, or Codex: ``` /consult what's the best way to model this state machine? /consult --gemini review this design for edge cases /debate should this be a separate service or stay in the monolith? consult-llm models # list available models and resolved selectors consult-llm doctor # diagnose backend auth and config consult-llm config set # set a config value (user config by default) consult-llm init-config # scaffold ~/.config/consult-llm/config.yaml consult-llm init-prompt # scaffold ~/.config/consult-llm/SYSTEM_PROMPT.md consult-llm install-skills # install bundled skills to platform skill dirs consult-llm update # self-update the binary ``` `consult-llm models` shows which models are active based on the configuration loaded for the current directory and prints `Default models:` , the ordered list used when `-m` is omitted. The `Default -m args:` line is a convenience for same-prompt calls; `--run` workflows use the model list to build one `--run model=...` entry per prompt. `consult-llm doctor` checks that each provider's backend dependency (API key or CLI binary) is satisfied, shows which config files were loaded, and validates session storage. Pass `--verbose` to see all config keys including unset defaults. `consult-llm` separates **model families** from **backends**. A **model family** is what you ask for: `gemini` , `openai` , `deepseek` , `minimax` , `anthropic` , `grok` , or `openrouter` . A **backend** is how `consult-llm` reaches that model family: : direct HTTP calls using an API key`api` **CLI backends**: shell out to a local CLI tool already installed and logged in | Model family | `api` backend | CLI backends available | API key env var | |---|---|---|---| | Gemini | yes | `gemini-cli` , `cursor-cli` , `opencode` , `profile` | `GEMINI_API_KEY` | | OpenAI | yes | `codex-cli` , `cursor-cli` , `opencode` , `profile` | `OPENAI_API_KEY` | | DeepSeek | yes | `opencode` , `profile` | `DEEPSEEK_API_KEY` | | MiniMax | yes | `opencode` , `profile` | `MINIMAX_API_KEY` | | Anthropic | yes | `profile` , `claude-cli` , `cursor-cli` | `ANTHROPIC_API_KEY` | | Grok | yes | `cursor-cli` , `profile` | `XAI_API_KEY` | | OpenRouter | yes | `opencode` , `profile` | `OPENROUTER_API_KEY` | Direct HTTP calls to the provider. Requires an API key. Set it in your user config or as an environment variable: ``` # User config (recommended, persists across sessions) consult-llm config set openai.api_key your_openai_key consult-llm config set gemini.api_key your_gemini_key consult-llm config set grok.api_key your_xai_key # Or as environment variables export OPENAI_API_KEY=your_openai_key export GEMINI_API_KEY=your_gemini_key export XAI_API_KEY=your_xai_key ``` The `api` backend is the default. To set it explicitly: ``` consult-llm config set gemini.backend api consult-llm config set openai.backend api consult-llm config set grok.backend api ``` Shell out to an already-installed local CLI. No API keys needed in `consult-llm` ; authentication is handled by the CLI tool. A key advantage over the API backend: CLI agents can browse your codebase, run commands, and do their own research before responding. The API backend receives only the prompt and files you explicitly include. Requires the [Gemini CLI](https://github.com/google-gemini/gemini-cli) and `gemini login` : ``` consult-llm config set gemini.backend gemini-cli ``` Requires Codex CLI and `codex login` : ``` consult-llm config set openai.backend codex-cli consult-llm config set openai.reasoning_effort high # none | minimal | low | medium | high | xhigh # Optional: append extra args to every `codex exec` invocation. Shell-quoted. # Useful e.g. to skip the sandbox in environments that already isolate Codex: consult-llm config set openai.extra_args '--dangerously-bypass-approvals-and-sandbox' ``` The same `extra_args` field is supported on `gemini:` for the Gemini CLI backend. Routes through `cursor-agent` : ``` consult-llm config set openai.backend cursor-cli consult-llm config set gemini.backend cursor-cli ``` If your prompts need shell commands in Cursor CLI ask mode, allow them in `~/.cursor/cli-config.json` . Routes Anthropic models through the stock `claude` executable on `PATH` : ``` consult-llm config set anthropic.backend claude-cli ``` The native backend defaults to `claude` , stream-json output, stdin prompt delivery, and the non-interactive flags needed by consult-llm. Optional native settings: ``` consult-llm config set anthropic.reasoning_effort high # low | medium | high | xhigh | max consult-llm config set anthropic.extra_args '--permission-mode acceptEdits' ``` Use the `profile` backend instead when you need a custom Claude command, env, model env var, or wrapper. Routes any model family through a named CLI profile. This is useful when a Claude Code CLI process proxies another provider, for example routing Gemini models through a local [claude-code-proxy](https://github.com/raine/claude-code-proxy): ``` cli_profiles: claude-gemini-proxy: command: /Users/you/.local/bin/claude env: ANTHROPIC_BASE_URL: http://localhost:18765 ANTHROPIC_AUTH_TOKEN: anything ANTHROPIC_SMALL_FAST_MODEL: gemini-3.1-pro-preview model_env: ANTHROPIC_MODEL gemini: backend: profile cli_profile: claude-gemini-proxy ``` `model_env` sets the named environment variable to the requested model ID before launching the profile command. For Anthropic models, use `anthropic.backend: profile` when selecting a named CLI profile. Existing configs that combine `anthropic.backend: claude-cli` with `anthropic.cli_profile` are treated as profile-backed for backward compatibility, but new configs should use `profile` explicitly. Fields like `type: claude-cli` ,`command: claude` ,`interface: stream-json` ,`prompt: stdin` and flags like`-p` ,`--output-format stream-json` ,`--verbose` ,`--bare` are defaulted or auto-injected for`claude-cli` profiles. Only non-default choices need to be written. See[CLI backend profiles]below. The example passes literal environment values and arguments to the CLI process. Prefer a user or project-local config for profiles with `env` values; committed project config rejects `cli_profiles.*.env` so secrets and machine-local paths do not leak. Run `consult-llm doctor` after configuring it. The provider row should show `via profile` and the selected profile command, for example `profile 'claude-gemini-proxy' command claude (...)` . Routes through `opencode` to Copilot, OpenRouter, or other providers: ``` consult-llm config set openai.backend opencode consult-llm config set gemini.backend opencode consult-llm config set deepseek.backend opencode consult-llm config set minimax.backend opencode # Optional: configure OpenCode provider routing consult-llm config set opencode.default_provider copilot consult-llm config set openai.opencode_provider openai ``` Routes `openrouter/*` models through OpenCode: ``` consult-llm config set openrouter.backend opencode ``` No API key needed -- authentication is handled by your OpenCode installation. Any `openrouter/*` model ID available in OpenCode works automatically. Add it to your config: ``` openrouter: backend: opencode extra_models: - openrouter/xiaomi/mimo-v2.5-pro allowed_models: - gpt-5.5 - gemini-3.1-pro-preview - openrouter/xiaomi/mimo-v2.5-pro ``` The `extra_models` entry adds the model to the catalog; `allowed_models` must also list it since it acts as an allowlist. Any `openrouter/*` model ID from OpenCode works -- add them to both lists. The `openrouter` selector resolves to the first available enabled model (e.g. `openrouter/auto` when no specific model is configured directly). The `profile` backend selects a named entry from the top-level `cli_profiles` map. Each profile defines how consult-llm launches the CLI process: `type` : profile executor type (defaults to`claude-cli` , the only supported value today)`command` : executable name or path (defaults to`claude` )`args` : literal argv entries before the prompt`env` : literal environment variables passed to the CLI process`effort` : optional effort level (`low` ,`medium` ,`high` ,`xhigh` ,`max` ); passed as`--effort ` to the CLI`model_env` : optional env var name set to the requested model ID at launch time`interface` : output parsing strategy (`text` ,`json` , or`stream-json` ; defaults to`stream-json` )`prompt` : how the prompt is delivered (`stdin` or`argument` ; defaults to`stdin` ) For `claude-cli` profiles, the executor auto-injects `-p` , `--output-format ` , `--verbose` , `--bare` and the env vars `CLAUDE_CODE_DISABLE_AUTO_MEMORY=1` , `CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1` , `CLAUDE_CODE_DISABLE_UPDATE_CHECK=1` , and `NO_COLOR=1` . Provider blocks reference a profile by name. For example, `gemini.backend: profile` with `gemini.cli_profile: claude-gemini-proxy` uses the profile shown above. For Anthropic, prefer `anthropic.backend: claude-cli` for the stock native backend and `anthropic.backend: profile` when selecting a named profile. CLI backends support multi-turn conversations. The first response includes a `[thread_id:xxx]` prefix; pass that ID back with `--thread-id` to continue the conversation with full context from prior turns. ``` > Ask codex what's the best caching strategy for our read-heavy API ⏺ Bash(cat <<'EOF' | consult-llm -m codex What's the best caching strategy for a read-heavy API? EOF) ⎿ [model:gpt-5.5] [thread_id:thread_b1ff711...] Redis with TTL-based invalidation. Set short TTLs for volatile data ... ⏺ Codex recommends Redis with TTL-based invalidation, but our payment endpoints need strong consistency. Let me push back on that. ⏺ Bash(cat <<'EOF' | consult-llm -m codex --thread-id thread_b1ff711... What if we need strong consistency guarantees? Does that change your recommendation? EOF) ⎿ [model:gpt-5.5] [thread_id:thread_b1ff711...] Yes. With strong consistency, the TTL approach breaks down. Consider write-through caching or cache invalidation on writes instead ... ⏺ Codex revised its recommendation based on the consistency constraint. I'll use write-through caching for the payment endpoints. ``` This works with Gemini CLI, Codex CLI, Cursor CLI, OpenCode, and Claude CLI. See the [debate skills](#skills) for multi-LLM workflows that use thread IDs to maintain context across debate rounds. consult-llm reads layered YAML config files. Resolution order (highest to lowest precedence): - Environment variables - `.consult-llm.local.yaml` (project-local overrides, not committed to git) - `.consult-llm.yaml` (committed project config) - `~/.config/consult-llm/config.yaml` (user config)Supports `$XDG_CONFIG_HOME` . The legacy path`~/.consult-llm/config.yaml` is still read for backward compatibility. Project files are discovered by walking up from the current directory to the nearest `.git` root or `$HOME` . `.consult-llm.local.yaml` is useful for personal backend or model preferences that you don't want committed. Add it to your [global gitignore](https://docs.github.com/en/get-started/getting-started-with-git/ignoring-files#configuring-ignored-files-for-all-repositories-on-your-computer) so it's excluded from all projects: ``` echo '.consult-llm.local.yaml' >> ~/.gitignore_global ``` If you use [workmux](https://github.com/raine/workmux) worktrees, symlink it into new worktrees automatically by adding it to your `.workmux.yaml` : ``` files: symlink: - .consult-llm.local.yaml ``` Scaffold the user config and set values: ``` consult-llm init-config consult-llm config set default_model gemini consult-llm config set default_models '[gemini, openai, openai]' consult-llm config set gemini.backend gemini-cli # Write to project config instead of user config: consult-llm config set --project default_model openai # Write to local project overrides (not committed): consult-llm config set --local openai.backend codex-cli ``` Values are parsed as YAML, so booleans and lists work naturally: ``` consult-llm config set no_update_check true consult-llm config set allowed_models '[gemini, openai]' ``` Model selection has three layers: `allowed_models` is the allowlist: it restricts which exact model IDs are enabled and which selectors can resolve. It also validates`default_model` ,`default_models` , and explicit`--` skill flags.`default_model` controls single-response CLI calls where`-m` is omitted and`default_models` is empty or unset.`default_models` controls multi-model calls where`-m` is omitted; it preserves order and duplicates, so`[openai, openai]` intentionally samples OpenAI twice. When`default_models` is empty or unset, the CLI falls back to`default_model` , then the built-in fallback model. If `default_models` names a model excluded by `allowed_models` , config loading fails instead of silently using it. Example `~/.config/consult-llm/config.yaml` : ``` allowed_models: [gemini-3.1-pro-preview, gpt-5.5, grok-4.3] default_model: gpt-5.5 default_models: [gpt-5.5, gpt-5.5] gemini: backend: gemini-cli openai: backend: codex-cli reasoning_effort: high anthropic: backend: claude-cli reasoning_effort: high grok: api_key: your_xai_key opencode: default_provider: copilot ``` API keys can be set in your user config, a project-local config file, or as environment variables. Environment variables take highest precedence. **User config** (`~/.config/consult-llm/config.yaml` ), applies everywhere: ``` openai: api_key: your_openai_key gemini: api_key: your_gemini_key grok: api_key: your_xai_key ``` **Project-local config** (`.consult-llm.local.yaml` in the repo root, gitignored), overrides the user config for that project: ``` openai: api_key: your_project_specific_key ``` API keys are **not** allowed in `.consult-llm.yaml` (the committed project config). The tool will refuse to load it and tell you to move the key to `.consult-llm.local.yaml` . **Environment variables** (highest precedence, useful for CI): `OPENAI_API_KEY` `GEMINI_API_KEY` `ANTHROPIC_API_KEY` `DEEPSEEK_API_KEY` `MINIMAX_API_KEY` `XAI_API_KEY` ** direnv** is an alternative to `.consult-llm.local.yaml` for project-specific keys via environment variables. Add a `.envrc` in the repo root and `direnv allow` it, then put keys in a `.env` file (both gitignored): ``` # .envrc dotenv # .env OPENAI_API_KEY=your_project_specific_key ``` direnv loads the variables automatically when you enter the directory and unloads them when you leave. Cost estimates are displayed for known models. Any model name is accepted; cost estimates show as zero for models without pricing data. ## Pricing table | Model | Input | Output | |---|---|---| OpenAI models | || `gpt-5.5` | $5.00/M | $30.00/M | `gpt-5.4` | $2.50/M | $15.00/M | `gpt-5.3-codex` | $2.50/M | $10.00/M | `gpt-5.2` | $1.75/M | $14.00/M | `gpt-5.2-codex` | $1.75/M | $7.00/M | Google Gemini models | || `gemini-2.5-pro` | $1.25/M | $10.00/M | `gemini-3-pro-preview` | $2.00/M | $12.00/M | `gemini-3.1-pro-preview` | $2.00/M | $12.00/M | DeepSeek models | || `deepseek-v4-pro` | $0.55/M | $2.19/M | MiniMax models | || `MiniMax-M2.7` | $0.30/M | $1.20/M | Anthropic models | || `claude-opus-4-7` | $5.00/M | $25.00/M | Grok models | || `grok-4.3` | $1.25/M | $2.50/M | Pricing is per million tokens (M). Check the provider's current pricing page before relying on estimates for billing decisions. ``` consult-llm init-prompt # scaffold ~/.config/consult-llm/SYSTEM_PROMPT.md ``` Override the path in config: ``` system_prompt_path: /path/to/project/.consult-llm/SYSTEM_PROMPT.md ``` ## All environment variables Environment variables override config file values. | Variable | Description | Allowed values | Default | |---|---|---|---| `OPENAI_API_KEY` | OpenAI API key | || `GEMINI_API_KEY` | Gemini API key | || `ANTHROPIC_API_KEY` | Anthropic API key | || `DEEPSEEK_API_KEY` | DeepSeek API key | || `MINIMAX_API_KEY` | MiniMax API key | || `OPENROUTER_API_KEY` | OpenRouter API key | || `XAI_API_KEY` | xAI API key for Grok models | || `CONSULT_LLM_DEFAULT_MODEL` | Model or selector to use for single-response calls when `-m` is omitted | selector or exact model ID | first available | `CONSULT_LLM_DEFAULT_MODELS` | Comma-separated ordered multi-model defaults when `-m` is omitted; duplicates preserved | selectors or exact model IDs | empty (falls through to default_model then fallback) | `CONSULT_LLM_GEMINI_BACKEND` | Backend for Gemini models | `api` `gemini-cli` `cursor-cli` `opencode` `profile` | `api` | `CONSULT_LLM_OPENAI_BACKEND` | Backend for OpenAI models | `api` `codex-cli` `cursor-cli` `opencode` `profile` | `api` | `CONSULT_LLM_DEEPSEEK_BACKEND` | Backend for DeepSeek models | `api` `opencode` `profile` | `api` | `CONSULT_LLM_MINIMAX_BACKEND` | Backend for MiniMax models | `api` `opencode` `profile` | `api` | `CONSULT_LLM_ANTHROPIC_BACKEND` | Backend for Anthropic models | `api` `profile` `claude-cli` `cursor-cli` | `api` | `CONSULT_LLM_GROK_BACKEND` | Backend for Grok models | `api` `cursor-cli` `profile` | `api` | `CONSULT_LLM_OPENROUTER_BACKEND` | Backend for OpenRouter models | `api` `opencode` `profile` | `api` | `CONSULT_LLM_ALLOWED_MODELS` | Comma-separated allowlist; restricts which models are enabled | model IDs | all | `CONSULT_LLM_EXTRA_MODELS` | Comma-separated extra model IDs to add to the catalog | model IDs | | `CONSULT_LLM_CODEX_REASONING_EFFORT` | Reasoning effort for Codex CLI backend | `none` `minimal` `low` `medium` `high` `xhigh` | `high` | `CONSULT_LLM_CODEX_EXTRA_ARGS` | Extra CLI args appended to `codex exec` (shell-quoted) | e.g. `--dangerously-bypass-approvals-and-sandbox` | | `CONSULT_LLM_GEMINI_EXTRA_ARGS` | Extra CLI args appended to `gemini` (shell-quoted) | shell-quoted args | | `CONSULT_LLM_CLAUDE_REASONING_EFFORT` | Reasoning effort for native Claude CLI backend | `low` `medium` `high` `xhigh` `max` | unset | `CONSULT_LLM_CLAUDE_EXTRA_ARGS` | Extra CLI args appended to `claude` (shell-quoted) | shell-quoted args | | `CONSULT_LLM_OPENCODE_PROVIDER` | Default OpenCode provider prefix for all models | provider name | per-model default | `CONSULT_LLM_ANTHROPIC_CLI_PROFILE` | CLI profile name when `anthropic.backend` is `profile` | profile name | | `CONSULT_LLM_GEMINI_CLI_PROFILE` | CLI profile name when `gemini.backend` is `profile` | profile name | | `CONSULT_LLM_OPENAI_CLI_PROFILE` | CLI profile name when `openai.backend` is `profile` | profile name | | `CONSULT_LLM_DEEPSEEK_CLI_PROFILE` | CLI profile name when `deepseek.backend` is `profile` | profile name | | `CONSULT_LLM_MINIMAX_CLI_PROFILE` | CLI profile name when `minimax.backend` is `profile` | profile name | | `CONSULT_LLM_GROK_CLI_PROFILE` | CLI profile name when `grok.backend` is `profile` | profile name | | `CONSULT_LLM_OPENROUTER_CLI_PROFILE` | CLI profile name when `openrouter.backend` is `profile` | profile name | | `CONSULT_LLM_OPENCODE_OPENAI_PROVIDER` | OpenCode provider for OpenAI models | provider name | `openai` | `CONSULT_LLM_OPENCODE_GEMINI_PROVIDER` | OpenCode provider for Gemini models | provider name | `google` | `CONSULT_LLM_OPENCODE_DEEPSEEK_PROVIDER` | OpenCode provider for DeepSeek models | provider name | `deepseek` | `CONSULT_LLM_OPENCODE_MINIMAX_PROVIDER` | OpenCode provider for MiniMax models | provider name | `minimax` | `CONSULT_LLM_OPENCODE_OPENROUTER_PROVIDER` | OpenCode provider for OpenRouter models | provider name | `openrouter` | `CONSULT_LLM_SYSTEM_PROMPT_PATH` | Path to a custom system prompt file | file path | `~/.config/consult-llm/SYSTEM_PROMPT.md` | `CONSULT_LLM_NO_UPDATE_CHECK` | Disable background update checks | `1` `true` `yes` | All prompts and responses are logged to: ``` $XDG_STATE_HOME/consult-llm/consult-llm.log ``` Default: `~/.local/state/consult-llm/consult-llm.log` Each entry includes tool call arguments, the full prompt, the full response, and token usage with cost estimates. ## Example log entry ``` [2025-06-22T20:16:04.675Z] PROMPT (model: deepseek-v4-pro): ## Relevant Files ### File: src/main.ts ... Please provide specific suggestions for refactoring with example code structure where helpful. ================================================================================ [2025-06-22T20:19:20.632Z] RESPONSE (model: deepseek-v4-pro): Based on the analysis, here are the key refactoring suggestions to improve separation of concerns and maintainability: ... This refactoring maintains all existing functionality while significantly improving maintainability and separation of concerns. Tokens: 3440 input, 5880 output | Cost: $0.014769 (input: $0.001892, output: $0.012877) ================================================================================ ``` `consult-llm-monitor` is a real-time TUI for active runs and history. ``` consult-llm-monitor ``` It reads the per-run spool written by `consult-llm` , including active snapshots, run metadata, event streams, and shared history. `consult-llm` keeps orchestration in the host agent and uses the CLI as a small transport boundary. Instead of manually copying context into a browser LLM or juggling another agent TUI, your current agent can hand off a focused prompt, stream the answer back inline, and continue the conversation from there. That boundary also lets the host agent and external model talk to each other in multi-turn workflows. `/consult` can ask for a second opinion, `/debate` can have models critique each other, and threaded CLI backends can continue the same conversation without leaving the agent session. The installed skills are reusable workflow definitions; the backend is just configuration. You can use Codex CLI for personal projects, Cursor CLI at work, direct APIs in CI, or different default model lists per repo while keeping the same `/consult` , `/debate` , and `/review-panel` habits. At runtime, the installed skill decides what context to include, formats the prompt, and invokes `consult-llm` with stdin plus `-f` file attachments. API backends receive only that explicit prompt and file context. CLI-agent backends such as Gemini CLI, Codex CLI etc. can also inspect the working tree themselves, depending on their own tools and permissions. The CLI resolves layered configuration, selects the requested backend, streams the model response to stdout, and records run metadata for logging and monitoring. If you like sequence diagrams, here's one for you: ``` sequenceDiagram participant User participant Agent as Host agent
(Claude Code, Codex, OpenCode) participant Skill as Workflow skill
(/consult, /debate, /collab) participant CLI as consult-llm CLI participant Config as Config resolver participant Backend as Backend adapter
(API or local CLI) participant Model as External model participant Logs as Logs / monitor spool User->>Agent: Ask for a second opinion Agent->>Skill: Load matching workflow skill Skill->>Skill: Gather prompt and file context Skill->>CLI: Pipe prompt via stdin
pass files with -f CLI->>Config: Resolve layered config and model selectors Config-->>CLI: Backend, model, prompt settings CLI->>Backend: Dispatch normalized request Backend->>Model: API request or local CLI invocation Model-->>Backend: Streaming response Backend-->>CLI: Normalized stream and metadata CLI-->>Logs: Write prompt, response, usage, run state CLI-->>Agent: Stream response on stdout Agent-->>User: Summarize and apply next steps ``` The skill system has two layers: ** consult-llm (base CLI)** handles the mechanics: reading stdin, attaching file context, calling the right backend, streaming the response, and managing thread IDs for multi-turn conversations. A dedicated `consult-llm` reference skill documents this contract and is loaded by other skills before they invoke the CLI.**Workflow skills** compose on top. They gather context from the codebase, decide which models to call and how, and synthesize the results for you. When you run `/consult` or `/debate` , the agent reads a skill file that tells it how to orchestrate one or more `consult-llm` calls and what to do with the responses. When a workflow skill runs, the agent pipes the prompt via stdin and passes file context with `-f` : ``` cat <<'__CONSULT_LLM_END__' | consult-llm -m gemini -f src/main.rs -f src/config.rs Your question here. __CONSULT_LLM_END__ ``` The response streams back to stdout and the agent sees it inline. If the response exceeds the shell tool's output limit (30k chars in Claude Code by default), the full output is saved to a file and the agent is notified where to find it; it can use `Read` to retrieve the rest. In practice this is rare; the large majority of responses are well under that limit. ``` consult-llm install-skills ``` Installs to all detected platforms. Target a specific one with `--platform` : ``` consult-llm install-skills --platform claude consult-llm install-skills --platform opencode consult-llm install-skills --platform codex ``` Platforms supported: - Claude Code: `~/.claude/skills/` - OpenCode: `~/.config/opencode/skills/` - Codex: `~/.codex/skills/` All workflow skills accept `--` flags matching the selectors reported by `consult-llm models` (e.g. `--gemini` , `--openai` , `--deepseek` ). With no selector flag, multi-model skills use the ordered `Default models` list printed by `consult-llm models` , which comes from `default_models` ; duplicate entries are intentional and preserved. : ask one or more external LLMs; any number of`consult` `--` flags, plus`--browser` for clipboard/web mode: multiple LLMs brainstorm together, building on each other's ideas`collab` : the agent brainstorms with one partner LLM (`collab-vs` `--` required) in alternating turns: multiple LLMs propose and critique competing approaches`debate` : the agent debates one opponent LLM (`debate-vs` `--` required), then synthesizes the best answer: role-asymmetric advisory panel; each model speaks from one expert lens, agent synthesizes a trade-off resolution. The agent picks roles to fit the task (with a`panel` `--roles` override). Modes:`--mode design` (default) or`--mode review` for diff critique: standalone multi-model code review of a diff with identical prompts; agent dedupes findings by severity/confidence. Read-only by default;`review-panel` `--fix` opt-in for localized must-fix items: autonomous spec → plan → review → implement → red-team workflow. Evidence-gated reviewers, written feedback ledger, triggered debug loop, opt-in commits. Rigor knob:`implement` `--rigor lite|standard|deep` : coordinator that breaks a large task into a DAG of phases, each running`phased-implement` `/implement` in its own[workmux](https://github.com/raine/workmux)worktree. Supports sequential, parallel, and mixed dependencies; per-phase merge with`/merge --keep` and ancestry verification; failure halts dependents. Requires`workmux` : interactive design session - agent clarifies the idea with the user, fans out to multiple LLMs in parallel for divergent approach generation, user picks one, then co-design with optional multi-LLM critique. Saves a design doc; hand it to`workshop` `/implement` to build See `skills/*/SKILL.md` for the exact prompts and invocation patterns. ``` consult-llm update ``` This downloads the latest GitHub release, verifies its SHA-256 checksum, updates `consult-llm` , and updates `consult-llm-monitor` if it lives alongside it. If you previously used the MCP server version (`consult-llm-mcp` npm package): - **Install the CLI binary**(see[Quick Start](#quick-start)). - **Install skills** so your agent can call`consult-llm` for you: ``` consult-llm install-skills ``` - **Migrate your config.** Any env vars you set in the MCP`"env"` block can move to`~/.config/consult-llm/config.yaml` , including API keys.For example, this MCP config in `~/.claude.json` : ``` "mcpServers": { "consult-llm": { "command": "npx", "args": ["-y", "consult-llm-mcp"], "env": { "CONSULT_LLM_GEMINI_BACKEND": "api", "CONSULT_LLM_OPENAI_BACKEND": "codex-cli", "CONSULT_LLM_CODEX_REASONING_EFFORT": "xhigh", "CONSULT_LLM_ALLOWED_MODELS": "gpt-5.4,gemini-3.1-pro-preview,MiniMax-M2.7", "CONSULT_LLM_MINIMAX_BACKEND": "opencode", "CONSULT_LLM_OPENCODE_MINIMAX_PROVIDER": "minimax" } } } ``` becomes: ``` allowed_models: [gpt-5.4, gemini-3.1-pro-preview, MiniMax-M2.7] gemini: backend: api openai: backend: codex-cli reasoning_effort: xhigh minimax: backend: opencode opencode_provider: minimax ``` Put this in `~/.config/consult-llm/config.yaml` for user-wide settings, or in`.consult-llm.yaml` at the project root if the settings were specific to that project. - **Remove the MCP server registration** from your Claude Code config (`~/.claude.json` ): ``` "mcpServers": { // remove this entry: "consult-llm": { ... } } ``` - **Uninstall the npm package** if you installed it globally: ``` npm uninstall -g consult-llm-mcp git clone https://github.com/raine/consult-llm.git cd consult-llm just check ``` `just check` runs the standard local validation, including build and tests. Use `cargo build` or `cargo test` directly only when iterating on one step. Try the local binary directly: ``` cat <<'EOF' | cargo run -- -m gemini Sanity-check the local build and explain what this CLI does well. EOF ``` See [RELEASE.md](/raine/consult-llm/blob/main/RELEASE.md).