{"slug": "your-coding-standards-are-becoming-agent-skills", "title": "Your Coding Standards Are Becoming Agent Skills", "summary": "Tikal's ADLC repository, a 28-skill framework for encoding an entire software development lifecycle as agent skills, has drawn criticism on Hacker News for being overbuilt, yet it highlights the growing adoption of the Agent Skills format, which originated as an Anthropic feature in Claude and Claude Code and has since been adopted by OpenAI's Codex, GitHub Copilot, Cursor, Gemini CLI, and others. The format allows teams to store coding standards in version control as portable skills that work across vendors, with progressive disclosure limiting context usage to about 8,000 characters for metadata.", "body_md": "[AI](https://sourcefeed.dev/c/ai)Article\n\n# Your Coding Standards Are Becoming Agent Skills\n\nTikal's 28-skill ADLC framework shows where team standards are headed — and how easy it is to overbuild.\n\n[Rachel Goldstein](https://sourcefeed.dev/u/rachel_goldstein)\n\nA consultancy just tried to encode an entire software development lifecycle as agent skills — 28 of them, covering everything from team constitutions to eval pipelines — and the Hacker News response was a collective wince. Both halves of that sentence matter. [Tikal](https://github.com/tikalk/adlc-team-skills)'s ADLC (\"Agentic SDLC\") repo is an early, overbuilt attempt at something that is genuinely coming: your team's coding standards living in version control as portable skills, loaded by whatever agent your teammates happen to run.\n\n## The format won before the frameworks did\n\nThe load-bearing fact here isn't Tikal's repo. It's that a skill is now a commodity artifact. [Agent Skills](https://agentskills.io/) — a folder with a `SKILL.md`\n\nfile carrying `name`\n\nand `description`\n\nfrontmatter, instructions, and optional scripts and reference files — started as an Anthropic feature in Claude and [Claude Code](https://code.claude.com/docs/en/skills) last October. Anthropic then released the format as an open standard, and the adopter list has since become absurd: [OpenAI's Codex](https://developers.openai.com/codex/skills/), GitHub Copilot and VS Code, Cursor, Gemini CLI, Goose, OpenCode, Amp, JetBrains' Junie, and dozens more.\n\nCodex's implementation is instructive because OpenAI didn't invent a rival format — it adopted its competitor's. Codex discovers skills from `.agents/skills`\n\nin your repo, `~/.agents/skills`\n\nfor personal ones, and `/etc/codex/skills`\n\nfor fleet-wide defaults; you invoke one explicitly with `$skill-name`\n\nor let the model pick it up from its description. Claude Code does the same dance with `.claude/skills`\n\nand `/slash-command`\n\ninvocation. Same folder, same frontmatter, both ends of the duopoly. That's the actual news environment Tikal's repo landed in: for the first time, a team can write its standards once and have them travel across vendors — something none of the earlier config dialects (`CLAUDE.md`\n\n, `.cursorrules`\n\n, `AGENTS.md`\n\n) managed.\n\nThe mechanism that makes this viable at team scale is progressive disclosure. At session start, an agent loads only each skill's name and description — Codex budgets roughly 8,000 characters for the whole metadata index — and reads the full `SKILL.md`\n\nonly when a task matches. A team can keep fifty skills on the shelf and pay context for two.\n\n## What Tikal actually shipped\n\nThe ADLC repo is a maximalist bet on that mechanism. Its 28-plus skills are organized into lifecycle families — `team-*`\n\nfor session boot and \"team constitution\" setup, `product-*`\n\nand `architect-*`\n\nfor spec-driven feature work, `evals-*`\n\nfor verification with PromptFoo or DeepEval, plus a `mission-brief`\n\norchestrator that routes across skill repos from other authors. Skills write structured decision records (ADRs, PDRs, and Tikal's own \"CDRs\") into a `.adlc/`\n\ndirectory, the idea being that standards, architecture decisions, and extracted patterns become reviewable git artifacts rather than folklore in someone's prompt stash. Installation is one command via the community skills CLI (`npx skills add tikalk/adlc-team-skills -a claude -g`\n\n), with a wrapper CLI that also wires up slash commands and session-start hooks for nine different agents.\n\nSome of the repo's slogans are genuinely good engineering instincts. \"Separate the maker from the checker\" — never let the agent that wrote the code verify it — is advice most solo Claude Code users would benefit from. \"Build to delete,\" pruning rules as models improve, is the correct posture toward any prompt artifact. And the core diagnosis is right: individual developers hoarding private prompt tricks produces inconsistent codebases and unreviewable AI-generated PRs.\n\n## The objection that's half right\n\nHN's pushback clustered on two points, and they deserve to be separated. The first — one commenter likened the framework to \"dumping the Clean Code book into context,\" predicting 100K tokens of rules the agent will ignore — is half wrong on cost. Progressive disclosure exists precisely so that 28 skills don't ride along on every request; only the metadata does. If Tikal's descriptions are tight, the standing tax is small.\n\nBut it's half right on the deeper issue: skills are suggestions, not enforcement. A `SKILL.md`\n\nis prose a probabilistic model may or may not follow, and adherence degrades as instruction volume grows — several commenters noted that stuffed context makes agents *forget* guidelines, not follow them. Another called the result \"more of a vibe guideline.\" That's the honest framing. Nothing in the skills mechanism verifies that the agent applied your naming conventions or ran your checklist. If a standard matters, its enforcement still belongs in deterministic tooling — linters, CI gates, pre-commit hooks, PR checks — and the skill's job is to get the agent to write code that passes those gates on the first try instead of the third. Skills reduce iteration count; they don't replace verification. Tikal's own \"maker vs. checker\" pillar concedes this, which makes the framework's sheer surface area — a Twelve-Factor methodology, four pillars, three bespoke record formats — feel like process arriving before evidence.\n\n## What to actually do with this\n\nIf you lead a team using Claude Code or Codex, the move is smaller than Tikal's and worth making this quarter. Pick the three standards that cause the most PR churn — say, your migration conventions, your error-handling policy, your test structure — and write each as one narrow skill: a folder, a `SKILL.md`\n\nwith a precise trigger description, maybe a script or a reference file. Commit them to the repo (`.claude/skills/`\n\nand `.agents/skills/`\n\ncan coexist, or symlink one to the other), and let discovery do the rest. You'll know within a week whether agents pick them up at the right moments; a skill that never triggers has a bad description, not a bad idea.\n\nSkip the governance superstructure until you've felt the need. The record-keeping instinct — decisions as reviewed git artifacts — is sound, but plain ADRs in a `docs/`\n\nfolder that a skill knows how to read gets you most of it without adopting anyone's methodology wholesale.\n\nThe direction, though, is settled. Team standards are leaving wikis and lint-adjacent prose and becoming executable-ish artifacts in a format every major agent reads. Tikal got the destination right and the vehicle overweight. The teams that win this transition will be the ones shipping five boring, tightly-scoped skills — not twenty-eight ambitious ones.\n\n## Sources & further reading\n\n-\n[ADLC Team Skills](https://github.com/tikalk/adlc-team-skills)— github.com -\n[Agent skills that bring team coding standards to Claude Code and Codex](https://news.ycombinator.com/item?id=49169640)— news.ycombinator.com -\n[Agent Skills — an open format for extending AI agents](https://agentskills.io/)— agentskills.io -\n[Skills in Codex](https://developers.openai.com/codex/skills/)— developers.openai.com\n\n[Rachel Goldstein](https://sourcefeed.dev/u/rachel_goldstein)· Dev Tools Editor\n\nRachel has been embedded in the developer tooling ecosystem for nearly eight years, covering everything from IDE wars and package-manager drama to the quiet rise of AI-assisted coding. She has a soft spot for open-source maintainers and an unhealthy number of terminal emulators installed on a single laptop.\n\n## Discussion 0\n\nNo comments yet\n\nBe the first to weigh in.", "url": "https://wpnews.pro/news/your-coding-standards-are-becoming-agent-skills", "canonical_source": "https://sourcefeed.dev/a/your-coding-standards-are-becoming-agent-skills", "published_at": "2026-08-04 16:09:15+00:00", "updated_at": "2026-08-04 16:29:30.218453+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "ai-products"], "entities": ["Tikal", "Anthropic", "Claude", "Claude Code", "OpenAI", "Codex", "GitHub Copilot", "Cursor"], "alternates": {"html": "https://wpnews.pro/news/your-coding-standards-are-becoming-agent-skills", "markdown": "https://wpnews.pro/news/your-coding-standards-are-becoming-agent-skills.md", "text": "https://wpnews.pro/news/your-coding-standards-are-becoming-agent-skills.txt", "jsonld": "https://wpnews.pro/news/your-coding-standards-are-becoming-agent-skills.jsonld"}}