TokenEconomizer: Cut coding-agent token costs 18-31%

A UC Berkeley and Microsoft Research team released TokenEconomizer, a plugin for Claude Code, Codex, the GitHub Copilot CLI and Pi that cut mean coding-agent cost by 18.4–30.9% across five agent–model combinations on 277 SWE-Bench tasks from six repositories, with lower cost in all 30 repository × combination cells and Pass@1 improving in 4 of 5. The plugin learns repository-specific facts ("micro-skills"), prunes unused tool definitions, and intervenes when a turn loops, with savings of 5–40% within each repository and combination, 16–21% on Web-Bench and 6–20% on two security-auditing benchmarks. TokenEconomizer's model calls run through the user's own agent plan and their cost is included in its reports, and learned data stays on the user's machine in ~/.tokeneconomizer.

Aaron J. Li<sup 1</sup , Weijia Xu<sup 2</sup , Chandan Singh<sup 2</sup , Zixiao Chen<sup 3</sup , Jeevana Priya Inala<sup 2</sup , Charlotte Siska<sup 3</sup , Acar Tamersoy<sup 3</sup , Bin Yu<sup 1</sup , Ion Stoica<sup 1</sup , Michel Galley<sup 2</sup , Jianfeng Gao<sup 2</sup <sup 1</sup UC Berkeley <sup 2</sup Microsoft Research <sup 3</sup Microsoft Security Our measurement on SWE-Bench tasks: 18.4–30.9% lower mean cost across five agent–model combinations, cheaper in all 30 repository × combination cells, and Pass@1 up in 4 of 5 . Results results TokenEconomizer makes coding agents cheaper to run in the repositories you work in often, without changing the agent itself. It learns from the sessions an agent has already run in a repository, and uses that experience to cut waste in the sessions that follow. It has three mechanisms: - Micro-skills: remember how the repository works. Sessions keep rediscovering the same facts: a build step that must run first, the spelling of a command that works here python -m pytest where pytest is missing, npx tsc where tsc is , an environment variable a command needs, where generated files live. Micro-skills learns such facts, in any language, from two sources: failures that repeat across sessions, and a model that reviews the recent sessions every k sessions k = 3 and proposes facts. A fact is stated at the start of each session once three sessions have confirmed it, and dropped when later sessions contradict it. - Tool pruning: stop loading tools that go unused. Every loaded tool's definition is sent with every request. A tool that goes unused over p prompts spread across at least m sessions, or over s sessions of any length p = 10, m = 2, s = 5 , is left out of the next sessions through the agent's own settings. One command brings it back. - Failure-loop intervention the loop guard : step in when a turn is stuck. When a turn the agent's work on one prompt keeps hitting the same failures, a judge model checks whether it is stuck. If the judge is at least c sure c = 0.7 , the agent gets a redirect a short note, added to its context, to try another approach , at most r times per turn r = 1 . If the turn is still stuck after that, TokenEconomizer tells you how to stop it; it never stops a turn itself. TokenEconomizer is a plugin for Claude Code , Codex , the GitHub Copilot CLI and Pi , with experimental support for opencode , Cursor Agent and Hermes Agent . Each italic letter above is a setting, shown with its default Settings settings , and each mechanism can be turned on or off. The plugin announces each action in one line, and if any part of it fails, your session carries on as if it were not installed. Its model calls the fact proposer, and the judge with the redirect it writes run through your own agent, on the same plan or login, and their cost is included in its reports. What it learns stays on your machine, in ~/.tokeneconomizer . The paper ran five agent–model combinations on the same 277 SWE-Bench tasks from six repositories. Each task ran as its own session, and each repository's tasks ran in order, starting with nothing learned. Costs include every model call TokenEconomizer made. Within each repository and combination, cost fell by 5–40%. The savings held on Web-Bench 16–21% lower and on two security-auditing benchmarks where every task is in a new repository 6–20% lower . The project page https://tokeneconomizer.github.io has interactive charts, per-repository numbers and nine annotated runs, and experiments/ https://github.com/microsoft/TokenEconomizer/blob/main/experiments/README.md reruns the SWE-Bench and Web-Bench experiments. Coding agents are built to finish tasks, not to keep them cheap. Every turn pays again for the agent's instructions, every loaded tool, and the conversation so far. Developers use the same agent on the same repository again and again, so much of that cost repeats: the same facts rediscovered, the same unused tools sent, the same kinds of failing loops. TokenEconomizer leaves the agent's model, weights and code alone and learns across a repository's sessions instead of treating each one on its own, so whatever the plugin spends is paid back over the sessions that follow. Four principles guide the mechanisms: - Work through what the agent already reads. Facts enter the context at session start, and tools are removed through the agent's own settings, so nothing depends on the agent learning a new tool. - Count cost as it is billed. Most tokens in a session are cached re-reads, so cost is computed with cache pricing, and it includes the plugin's own model calls. - Protect task success. Facts form only from repeated evidence, tools are removed only after going unused, and the loop guard leaves alone a turn that is still making progress. - Keep every action reversible. A fact that later sessions contradict is dropped, removed tools can be given back, and the loop guard only redirects and tells you: stopping a turn is your call. You need one of these agents, signed in any way it supports, and Python 3.10 or newer on PATH . The plugin needs no API key of its own and never handles credentials, so any plan or login works. Run these commands in the folder where you want to keep the clone. Claude Code, Codex, the Copilot CLI and opencode run the plugin from the clone, so leave it in place. Then start the agent in one of your repositories. Claude Code git clone https://github.com/microsoft/TokenEconomizer.git claude plugin marketplace add "$PWD/TokenEconomizer" claude plugin install tokeneconomizer@tokeneconomizer Start claude , trust the folder Yes, I trust this folder , and run /tokeneconomizer:status , allowing its script if asked. Once per machine, and again after Claude Code updates, run /tokeneconomizer:toolprune refresh-catalog . Codex git clone https://github.com/microsoft/TokenEconomizer.git codex plugin marketplace add "$PWD/TokenEconomizer" codex plugin add tokeneconomizer@tokeneconomizer Start codex , choose Trust and continue for the folder, then at Hooks need review choose Trust all and continue . The hooks take effect from your next Codex session, so quit /exit , start codex again, and check with $tokeneconomizer:status . Copilot CLI git clone https://github.com/microsoft/TokenEconomizer.git copilot plugin marketplace add "$PWD/TokenEconomizer" copilot plugin install tokeneconomizer@tokeneconomizer Start copilot , choose Yes, and remember this folder for future sessions , and run /tokeneconomizer:status , choosing Yes to run its script. Once per machine, and again after Copilot updates, run /tokeneconomizer:toolprune refresh-catalog . Pi pi install git:github.com/microsoft/TokenEconomizer Start pi and run /te status . Cursor Agent experimental python scripts/build plugin.py --out ~/.cursor/plugins/local/ Reload Cursor, confirm tokeneconomizer appears in Customize, then send a prompt in a repository. Check its state from a terminal with ~/.tokeneconomizer/bin/te --host cursor status . Cursor's published hooks provide session, prompt, tool-result and completion events. Its transcript format and per-session token usage are not a supported public interface, so the adapter records needed hook events locally and reports session cost as unavailable. Cursor support is macOS and Linux only: on Windows, Cursor runs hook commands through PowerShell, and this plugin's launcher is a POSIX shell script. opencode experimental git clone https://github.com/microsoft/TokenEconomizer.git mkdir -p ~/.config/opencode/plugins ln -s "$PWD/TokenEconomizer/plugin/opencode/tokeneconomizer.ts" ~/.config/opencode/plugins/ Start opencode and send a prompt, then check in the repository with ~/.tokeneconomizer/bin/te --host opencode status . opencode has no plugin commands, so the plugin's commands run from a terminal. Hermes Agent experimental; micro-skills and the loop guard, on the classic CLI and one-shot runs git clone https://github.com/microsoft/TokenEconomizer.git ln -s "$PWD/TokenEconomizer/plugin/hermes" ~/.hermes/plugins/tokeneconomizer hermes plugins enable tokeneconomizer hermes gateway restart Link it rather than running hermes plugins install , which leaves the launchers behind when given this directory and refuses the whole repository at its security scan. Send a prompt, then check in the repository with ~/.tokeneconomizer/bin/te --host hermes status . If the install worked, the status command prints a short status block. refresh-catalog records every tool a session loads without a model call , so that tool pruning can consider all of them. Keep the marketplace path absolute, as above: the Copilot CLI reads a relative path such as ./TokenEconomizer as the name of a GitHub repository. To update: | Agent | Update | |---|---| | Claude Code, Copilot CLI, opencode | git pull in the clone | | Hermes Agent | git pull in the clone, then hermes gateway restart | | Codex | git pull in the clone, then the codex plugin add line again | | Pi | pi update --extensions | plugin/README.md https://github.com/microsoft/TokenEconomizer/blob/main/plugin/README.md walks through each agent in more detail, including uninstalling, using Copilot with your own model key, and troubleshooting. | Agent | Supported | Older versions | |---|---|---| | Claude Code | 2.1.300 to 2.1.310 | not supported | | Codex | 0.153.1 to 0.164.0 | not supported | | Copilot CLI | 1.0.83 to 1.0.102 | not supported | | Pi | 1.2.0 to 1.3.0 | 0.99.x: load the extension by path below | | Cursor Agent experimental | 3.24.9, macOS and Linux below | not tested | | opencode experimental | 1.19.5 and 2.2.0 | not tested | | Hermes Agent experimental | 0.22.5 | not tested | The commands above were tested on the oldest and newest version in each range; newer versions have not been tested yet. - Codex before 0.141.0 does not run plugin hooks at all. - Pi 0.99.x : instead of pi install , clone the repository and start each session with pi --extension /path/to/TokenEconomizer/plugin/pi/tokeneconomizer.ts , using your clone's full path; git pull in the clone updates it. - opencode support is experimental: it was tested on 1.19.5 and 2.2.0 only, and not in the 2.x terminal UI. - Cursor Agent support is experimental. Cursor 3.24.9 loaded the local plugin, but hook delivery from a live Agent session has not yet been verified. - Hermes Agent support is experimental: it was tested on 0.22.5 only, with a scripted local model and one free real model, on the classic CLI and one-shot runs only. Micro-skills and a redirect reaching a real model are verified there; the still-stuck notice reaching a person is not. Its other surfaces the Ink TUI, the Desktop app, messaging platforms, cron and subagents are ignored, and tool pruning is not available. See its limits https://github.com/microsoft/TokenEconomizer/blob/main/plugin/README.md hermes-agent . Work as usual; the plugin needs nothing from you. To see or change what it does, use its commands. They have the same names on every agent; only the way you type them differs: | Agent | Type a command as | |---|---| | Claude Code, Copilot CLI | /tokeneconomizer:<command | | Codex | $tokeneconomizer:<command | | Pi | /te <command | | opencode | from a terminal: ~/.tokeneconomizer/bin/te --host opencode <command | | Cursor Agent | from a terminal: ~/.tokeneconomizer/bin/te --host cursor <command | | Hermes Agent | from a terminal: ~/.tokeneconomizer/bin/te --host hermes <command | | a terminal, in the repository | ~/.tokeneconomizer/bin/te <command | | Command | What it does | |---|---| | status | what it learned and did here, and what your sessions cost | | microskills | the facts it injects, and those still forming | | toolprune | the tools it left out, and the evidence not on Pi, opencode or Hermes Agent | | toolprune restore | give them back; they will not be removed again | | config | every setting in effect | | config set microskills=on | turn a mechanism on or =off in this repository; add --global for every repository | Inside an agent, a command costs one model turn; from a terminal it is free. The other commands repos , doctor , config unset , ... and each agent's permission prompts are listed under Commands https://github.com/microsoft/TokenEconomizer/blob/main/plugin/README.md commands . Tool pruning and the loop guard are on by default; with these defaults, the plugin calls a model only when a turn shows signs of looping: the judge, and the redirect it writes if it finds the turn stuck. Micro-skills is off by default, because its proposer adds model calls and how much it saves depends on the repository and the work you do there. Each mechanism has its own switch microskills , toolprune , loopguard that takes on or off , and the italic letters above are these settings: | | Setting | Default | What it sets | |---|---|---|---| | k | microskills propose every | 3 | sessions between runs of micro-skills' fact proposer | | p | toolprune evidence | 10 | prompts a tool must go unused before it is left out | | m | toolprune min sessions | 2 | sessions those prompts must span | | s | toolprune sessions | 5 | or this many sessions, of any length | | q | toolprune quiet minutes | 60 | minutes your sessions here must be idle before a deny list is written | | e | loopguard.envelope min samples | 5 | turns here that ended well no failing check after the last edit before the loop guard acts | | c | loopguard.judge confidence | 0.7 | how sure the judge must be that a turn is stuck | | r | loopguard nudges | 1 | redirects per turn before the guard only tells you | | b | loopguard.backstop mult | 2.5 | how many times its usual length a churning turn may run before it is redirected without the judge | Change them with config set , shown here in Claude Code's form other agents type it as in Everyday commands everyday-commands : /tokeneconomizer:config set microskills=on turn micro-skills on /tokeneconomizer:config set microskills propose every=5 k = 5: propose facts less often /tokeneconomizer:config set toolprune evidence=20 p = 20: wait for twenty unused prompts /tokeneconomizer:config set loopguard nudges=2 r = 2: redirect twice before telling you Tool pruning counts prompts so that long sessions weigh more, and requires m sessions so that a single session never decides alone. It writes the deny list only once your sessions in the repository have been idle for q minutes or, at the latest, a day after the list formed : a conversation resumed after its tools change must write its whole history to the prompt cache again instead of reading it, and after an idle hour that cache has expired anyway. On Claude Code, the plugin can also learn from a repository's earlier sessions, read from Claude Code's own logs oldest first and without any model call. This is off by default, and a repository's history is read only before the plugin has learned from any session there, so turn it on right after installing: with config set history import=on --global , the first session in each repository reads that repository's earlier sessions in the background see Earlier sessions https://github.com/microsoft/TokenEconomizer/blob/main/plugin/README.md earlier-sessions . A deny list that rests on those earlier sessions waits for toolprune apply , even under auto . Besides on and off , two modes are useful: toolprune=propose only proposes the deny list, and nothing changes until you run toolprune apply ; microskills=envfacts learns facts only from repeated failures, with no model calls. To change a single session, set an environment variable when you start the agent: TE DISABLE=1 claude turns the whole plugin off, and TE LOOPGUARD=off codex turns off one mechanism likewise TE MICROSKILLS and TE TOOLPRUNE . Every setting and its default are listed under Settings https://github.com/microsoft/TokenEconomizer/blob/main/plugin/README.md settings ; each one's environment variable is TE plus its name in capitals. Micro-skills and the loop guard work the same way on every agent. Each agent learns on its own: facts, tool evidence and the loop guard's sense of a usual turn are kept per agent and repository, while settings are shared. Tool pruning acts through each agent's own settings, so what it can leave out differs: | Agent | Tool pruning leaves out | Written to | |---|---|---| | Claude Code | single tools | .claude/settings.local.json | | Codex | capability packages | .codex/config.toml | | Copilot CLI | whole MCP servers | .github/copilot/settings.local.json | | Pi | nothing Pi loads only four tools | — | | Cursor Agent | nothing yet | — | | opencode | nothing yet | — | | Hermes Agent | nothing yet | — | Tool pruning adds only its own entries and never touches deny rules you wrote; a settings file it creates is kept out of git .git/info/exclude . On Claude Code, the session-start line that says what it left out shows only in the detailed transcript Ctrl+O , so check with /tokeneconomizer:toolprune . toolprune restore removes the plugin's entries and nothing else, and tools you give back are not removed again. If the plugin cannot edit a file safely a .codex/config.toml your repository commits, a settings file that is not valid JSON, a symlink that leads out of the repository , the list stays a proposal and the session start says why; toolprune apply tries again. docs/PLUGIN.md https://github.com/microsoft/TokenEconomizer/blob/main/docs/PLUGIN.md records how each agent's hooks and settings were verified to behave, and docs/ARCHITECTURE.md https://github.com/microsoft/TokenEconomizer/blob/main/docs/ARCHITECTURE.md how the package fits together. The loop guard first learns how long a turn in this repository usually runs: it waits until e turns here have ended well, on their own and with no failing check after the last edit. After that, a turn that shows signs of looping the same failures repeating, or errors piling up goes to the judge. One case is redirected without the judge: a turn that runs past b times the usual length while churning the same edits through the same failures. If a turn is still stuck after its redirects, you see one line that ends with how to stop it: TokenEconomizer: this turn still looks stuck after a redirect judge-stuck@0.82, 46 tool calls . Press Esc to interrupt it. Where that line appears, and how to stop the turn, in the terminal UI and in a headless run claude -p , codex exec , copilot -p , pi -p , opencode run , hermes -z : | Agent | Interactive: where it shows | How to stop | Headless: where it shows | How to stop | |---|---|---|---|---| | Claude Code | in Claude's reply | Esc | in the final reply | Ctrl+C | | Codex | in the conversation | Esc, then /stop | not shown | Ctrl+C | | Copilot CLI | in the conversation | Esc twice | on stdout | Ctrl+C | | Pi | as a notification | Esc | on stderr | Ctrl+C | | opencode | as a notification | Esc | on stderr | Ctrl+C | | Hermes Agent | in the model's reply | Ctrl+C | in the final reply | Ctrl+C | - Claude Code shows a plugin's own lines only in its detailed transcript Ctrl+O , so the plugin asks Claude to repeat this one in its reply; the model may word it differently or leave it out. - Codex : Esc interrupts the turn, but a command it started keeps running until /stop . codex exec prints no hook messages. - Pi : Ctrl+C ends a headless run, but a command it started runs on until it finishes. - opencode 2.x prints the line to the opencode server's error output, not in its terminal UI. - Hermes Agent : the plugin asks the model to repeat the line, since no hook was found to reach the person's view; a model may word it differently or leave it out. In a headless run nobody may be watching, so a flagged turn runs until it ends or reaches the agent's own limits; afterwards, te status counts the redirects and "still stuck" notices. | tokeneconomizer/microskills https://github.com/microsoft/TokenEconomizer/blob/main/tokeneconomizer/microskills | Micro-skill synthesis and injection: facts learned from finished sessions | | tokeneconomizer/toolprune https://github.com/microsoft/TokenEconomizer/blob/main/tokeneconomizer/toolprune | Tool pruning: unused tools and Codex capability packages | | tokeneconomizer/loopguard https://github.com/microsoft/TokenEconomizer/blob/main/tokeneconomizer/loopguard | Failure-loop intervention: the per-call guard and its per-repository envelope | | tokeneconomizer/trace https://github.com/microsoft/TokenEconomizer/blob/main/tokeneconomizer/trace | Each agent's session log, read into one shape | | tokeneconomizer/plugin https://github.com/microsoft/TokenEconomizer/blob/main/tokeneconomizer/plugin | The runtime the hooks and the te command run | | plugin https://github.com/microsoft/TokenEconomizer/blob/main/plugin | The installable plugin: manifests, hook files, launchers, slash commands, the Pi extension, the opencode and Hermes plugins | | experiments https://github.com/microsoft/TokenEconomizer/blob/main/experiments | The harness, launchers and task sets behind the paper's results | | docs https://github.com/microsoft/TokenEconomizer/blob/main/docs | PLUGIN.md design, verified agent behavior and ARCHITECTURE.md how the package fits together | | tests https://github.com/microsoft/TokenEconomizer/blob/main/tests | Offline tests for the package and the plugin | The package is standard-library only. Run the tests with python -m pytest tests add experiments/tests for the benchmark side , and build a self-contained plugin bundle with python3 scripts/build plugin.py --out dist/marketplace . The code behind the paper's results -- a harness that runs Claude Code, Codex and the Copilot CLI on SWE-Bench and Web-Bench, the launchers, and the evaluated task sets -- is in experiments/ https://github.com/microsoft/TokenEconomizer/blob/main/experiments/README.md , whose README gives the setup and one command per result. It is not part of the installed plugin; the two share only tokeneconomizer/ . @misc{li2026tokeneconomizer, title = {{TokenEconomizer}: Experience-Driven Black-Box Cost Control for Coding Agents}, author = {Li, Aaron J. and Xu, Weijia and Singh, Chandan and Chen, Zixiao and Inala, Jeevana Priya and Siska, Charlotte and Tamersoy, Acar and Yu, Bin and Stoica, Ion and Galley, Michel and Gao, Jianfeng}, year = {2026}, eprint = {2610.22732}, archivePrefix = {arXiv}, primaryClass = {cs.CL}, url = {https://arxiv.org/abs/2610.22732} } Apache 2.0; see LICENSE https://github.com/microsoft/TokenEconomizer/blob/main/LICENSE .