A plugin for Claude Code, Codex, the Copilot CLI and Pi (experimentally opencode, Cursor, Grok Build, Hermes Agent, the Antigravity CLI and Factory Droid) that reads finished sessions and changes what later sessions in the same repository pay for: micro-skills, tool pruning, and a loop guard. See README.md for the overview and the method, docs/PLUGIN.md for the design and the verified agent behavior, and docs/ARCHITECTURE.md for how the package fits together.
6.2k6d agoReviewMountCreate a free account to mount
Show or change TokenEconomizer's settings: turn micro-skills, tool pruning or the loop guard on or off, or tune them, for this repository or (with --global) every repository. Use when the user asks to configure, enable or disable TokenEconomizer or one of its mechanisms.
Steady34 mentions in 2 weeks
24 projects use a version of this
6.2k6d agoReviewMountCreate a free account to mount
Show the repository facts (micro-skills) TokenEconomizer learned and injects at the start of each session here, and the ones still forming. Use when the user asks what TokenEconomizer learned or injects, or about its facts or micro-skills.
Steady34 mentions in 2 weeks
No other project uses it yet
6.2k6d agoReviewMountCreate a free account to mount
List every repository TokenEconomizer keeps state for (how each was identified, its agents and sessions, the checkouts seen), or merge one repository's state into another. Use when the user asks which repositories TokenEconomizer tracks, why state looks split or missing, or asks to merge or migrate it.
Steady34 mentions in 2 weeks
4 projects use a version of this
6.2k6d agoReviewMountCreate a free account to mount
Show what TokenEconomizer has learned for this repository, what it has done, and what this repository's sessions cost. Use when the user asks about TokenEconomizer, its status, its savings or overhead, or what it learned here.
Steady34 mentions in 2 weeks
177 projects use a version of this
6.2k6d agoReviewMountCreate a free account to mount
Review, undo or apply TokenEconomizer's deny list of Codex capabilities this repository never uses (written to the project's .codex/config.toml). Use when the user asks about TokenEconomizer's tool pruning or deny list, or asks to restore or apply it.
Steady34 mentions in 2 weeks
1 project uses a version of this
6.2k6d agoReviewMountCreate a free account to mount
This file is for AI coding assistants (GitHub Copilot, Claude Code, Cursor, OpenAI Codex, Gemini CLI, Aider, etc.). It captures project-specific knowledge that isn't obvious from a fresh git clone and which routinely trips up agents. See CONTRIBUTING.md for coding standards (StyleCop rules, error handling, exception logging) — do not duplicate those here. The build scripts (scripts\Build.bat and friends) put build outputs one level up from the git working tree. The Readme documents the recommended clone-into-src\ convention, which matches the…
6.1k52d agoReviewMountCreate a free account to mount
Use Python 3.12 for desktop work. Install with: Keep the browser and desktop runtimes separate: Do not introduce a universal agent/model/environment abstraction or duplicate the browser runtime under another package. Preserve webwright compatibility aliases. Keep provider-specific private integrations outside this repository. Never save credentials or custom endpoint URLs in run artifacts, examples, or diagnostics. Before changing desktop prompts, read src/cuawright/desktop/config/prompts.py in full. Plain final text never completes a desktop task; the Actor must execute the standalone command python /opt/cuawright-tools/submit.py. Official…
1 project uses a version of this
6.1k41d agoReviewMountCreate a free account to mount
Alloy is a code generation framework using JSX components. Before working with Alloy code, read the relevant docs from installed packages. Your training data may be outdated — these docs match your installed version.
No other project uses it yet
5.9k4mo agoReviewMountCreate a free account to mount
ALWAYS follow these instructions first and only fall back to additional search and context gathering if the information here is incomplete or found to be in error. TypeSpec is a language for defining cloud service APIs and shapes. This monorepo contains the TypeSpec compiler, standard library packages, tools, documentation, and various language client emitters. [!IMPORTANT] These instructions do NOT apply to the language emitter packages (http-client-csharp, http-client-java, http-client-python). Those packages are excluded from the pnpm workspace and do not require…
No other project uses it yet
5.9k4mo agoReviewMountCreate a free account to mount
Review TypeSpec pull requests against the project's own rules: the Tier 0-3 breaking change policy, `.chronus` changelog requirements, compiler API usage, test framework conventions, and emitter output stability. Use when reviewing a diff or pull request in this repository.
Prepare language emitter changes for PR: validate (build, format, lint), add a changeset, and push. This skill is specifically for the language emitter packages (http-client-python, http-client-csharp, http-client-java) - NOT for core TypeSpec packages like compiler, http, openapi3, etc. Use when the user wants to finalize emitter changes, says things like "prep for pr", "prepare for PR", "validate and push", "add changeset", or "finalize changes".
No other project uses it yet
5.9k4mo agoReviewMountCreate a free account to mount
Writes TypeSpec http-client-python generator mock API tests (azure/unbranded/shared) from a Spector case. Use when given a Spector case link or a PR link that modifies Spector cases under http-specs/azure-http-specs.
No other project uses it yet
5.9k4mo agoReviewMountCreate a free account to mount
Scope: These instructions apply only to the packages/http-client-js sub-project in this monorepo. Use them whenever Copilot generates code, tests, commit messages, or pull request descriptions for the emitter. If Copilot is used in other sub-projects, these rules do not apply unless stated otherwise. - Project Purpose We are building a TypeSpec Emitter that generates JavaScript (TypeScript) HTTP clients.
No other project uses it yet
5.9k4mo agoReviewMountCreate a free account to mount
Generate Python SDK code from a TypeSpec specification using the local emitter. Use this skill when the user wants to generate/regenerate a Python client from a TypeSpec spec, provides a GitHub URL or local path to a TypeSpec project, or says things like "generate from this spec", "emit Python from this tsp", "regenerate the SDK", or "compile this TypeSpec for Python".
No other project uses it yet
5.9k4mo agoReviewMountCreate a free account to mount
Build and test the @typespec/http-client-python emitter. Use this skill whenever the user wants to test their local changes to the emitter, run the generator test suite, check if their http-client-python changes are passing, or validate a fix. Triggers on phrases like "test the emitter", "run tests", "check if my changes pass", "run test:generator", "run CI", or any mention of testing/validating changes in the emitter package.
No other project uses it yet
5.9k4mo agoReviewMountCreate a free account to mount
Ongoing work in this repository lands on the current release branch, not main. Release branches are named release/<semver> — currently release/0.3.0, the highest-versioned release/* branch on origin. main trails the release branch and only advances when a version is cut and merged (see RELEASING.md). Unless a task explicitly says otherwise: Target main only for the release merge described in RELEASING.md.
No other project uses it yet
5.8k4mo agoReviewMountCreate a free account to mount
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
MicrosoftCLAUDE.md