agents-md-protocol
Create or review an AGENTS.md file so coding agents get stable repo-local instructions: environment setup, testing, style, security boundaries, PR policy, and handoff rules. Use when a repo lacks durable agent guidance or when a custom harness needs a predictable context file.
- License 许可
- MIT
- 所属仓库
- stevesolun/ctx
- 最近更新
- 2026-10-15
- Stars
- ★ 593
- Forks
- 69
01 前言 Front Matter
- name
- agents-md-protocol
- description
- Create or review an AGENTS.md file so coding agents get stable repo-local instructions: environment setup, testing, style, security boundaries, PR policy, and handoff rules. Use when a repo lacks durable agent guidance or when a custom harness needs a predictable context file.
03 SKILL.md 正文
AGENTS.md Protocol
Purpose
Create or tighten a repository-level AGENTS.md contract for coding agents.
Treat it as durable operating context, not a chat prompt.
When to Use
- Repo has no
AGENTS.md,CLAUDE.md, or equivalent agent instructions. - Existing instructions are stale, vague, or missing test commands.
- A custom/API/local harness needs stable context it can load every run.
- A multi-agent workflow needs explicit handoff and review rules.
Procedure
- Inspect repo layout, package managers, CI files, and test commands.
- Capture only durable facts and team rules.
- Keep commands exact and runnable from the documented directory.
- Add security and destructive-operation boundaries.
- Add PR/review expectations and required verification.
- Keep the file short enough to load every session.
Recommended Sections
Dev environment tipsTesting instructionsBuild and lintCode styleSecurity boundariesPR instructionsAgent handoff notes
Quality Bar
- Every command has a working directory or clear scope.
- No secrets, tokens, or private URLs.
- No vague rules such as "be careful" without a concrete check.
- No roadmap or marketing text.
- Instructions match current CI and package metadata.
Harness Attachment
For non-Claude-Code harnesses, load AGENTS.md as outer-loop project context.
The harness should also keep explicit task state outside conversation history.
04 同仓库更多 Skills
toolbox
Pre/post dev toolbox — named bundles of skills/agents loaded before development work and councils of experts invoked after. Run /toolbox or the toolbox.py CLI to list, activate, initialize, export, import, and validate toolboxes. Invoke at the start or end of a dev session, when setting up a new repo, or when sharing toolboxes with a team.
skill-router
Alive skill router — reads the current project's stack and loads/unloads skills dynamically. Invoke at session start or when project context changes.
repo-stats-autoupdate
Keeps README badge + inline counts in sync with the real number of skills, agents, graph nodes/edges, communities, converted pipelines, and test inventory. Runs automatically on every commit via a git pre-commit hook. Use when the README drifts from reality or before publishing a release.
find-skills
Discover installable agent skills from ctx's shipped Skills.sh catalog, the Skills.sh search API, and the npx skills CLI. Use when a user asks whether a skill exists, wants to add/update a skill, or needs a repeatable procedure for finding candidate skills safely.
no-mistakes
Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.
zoom-out
Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.