agentleFS
dongshuyandongshuyan/compass-skills/AGENTS.md

compass-skills

AGENTS.md764 starsChanged 3 months agoMITView on GitHub

This repository contains agent-agnostic SKILL.md skills and an optional Codex session-title plugin. Use this file when your agent does not have native skills support, or when it needs explicit rules for discovering and applying the skills in skills/. The plugin has a separate installation contract in docs/session-titles.md. When a skill applies:

The file

Show its rules and text

We split this AGENTS.md into the rules it gives an agent

16 rules. About 4 are common, 7 are distinctive, and 5 are very specific to this project.

  • ≈4

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read each skill's YAML frontmatter name and description to decide whether it applies.

    line 8
  2. Very specific:

    Prefer explicit user invocation such as $task-clarifier, $task-forest, $pause-and-resume, $session-handoff-prompt, $user-profile-keeper, …

    line 9
  3. Distinctive:

    If no skill clearly applies, continue normally.

    line 10
  4. Distinctive:

    When a skill applies:

    line 15
  5. Very specific:

    Read the full SKILL.md before acting.

    line 17
  6. Very specific:

    Read referenced files under references/ only when the skill tells you to or when the current task needs them.

    line 19
  7. Very specific:

    Run scripts from the skill's own scripts/ directory instead of retyping large logic.

    line 20
  8. Distinctive:

    Keep generated runtime data out of the repository unless the user explicitly asks to commit it.

    line 21
  9. Common:

    Do not upload profile data, task data, credentials, cookies, browser sessions, or private local logs.

    line 53
  10. Common:

    Do not read password managers, keychains, SSH keys, browser cookies, API keys, tokens, or verification codes.

    line 54
  11. Common:

    Do not save secrets in user profiles or task graphs.

    line 55
  12. Distinctive:

    Treat resumes and candidate reports as confidential local records.

    line 56
  13. Distinctive:

    Do not use candidate age, birthplace, hometown, marital status, or other protected or sensitive traits for fit scoring, ranking, hiring, or …

    line 57
  14. Common:

    Before destructive actions, publishing, remote writes, global configuration changes, credential use, or external side effects, ask for …

    line 58
  15. Distinctive:

    Treat HTML exports as static offline views.

    line 59
  16. Distinctive:

    If your agent has no automatic skill router, use this AGENTS.md as the router policy.

    line 65

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

COMPASS Agent Adapter

This repository contains agent-agnostic SKILL.md skills and an optional Codex session-title plugin. Use this file when your agent does not have native skills support, or when it needs explicit rules for discovering and applying the skills in skills/. The plugin has a separate installation contract in docs/session-titles.md.

Discovery

  • Available skills live under skills/<skill-name>/SKILL.md.
  • Read each skill's YAML frontmatter name and description to decide whether it applies.
  • Prefer explicit user invocation such as $task-clarifier, $task-forest, $pause-and-resume, $session-handoff-prompt, $user-profile-keeper, $run-history-skill-builder, $run-history-skill-upgrader, $clear-communication, or $assess-interview-candidate.
  • If no skill clearly applies, continue normally; do not force a skill.
  • plugins/clarity-session-titles/skills/manage-title/ belongs to the full Codex plugin. Do not copy it into a portable skill root or enable the plugin merely because this repository was opened. Use scripts/title_plugin.py only when the user requests installation in a specific scope; hook trust is a separate Codex review step.

Loading Protocol

When a skill applies:

  1. Read the full SKILL.md before acting.
  2. Resolve relative paths from the directory that contains that SKILL.md.
  3. Read referenced files under references/ only when the skill tells you to or when the current task needs them.
  4. Run scripts from the skill's own scripts/ directory instead of retyping large logic.
  5. Keep generated runtime data out of the repository unless the user explicitly asks to commit it.

Invocation Examples

Use $task-clarifier to align this task before implementation.
Use $task-forest to update the task graph for this workspace.
Use $pause-and-resume to pause this unfinished task in the current conversation; later, continue it from the checkpoint.
Use $session-handoff-prompt to create a continuation prompt for a fresh session.
Use $user-profile-keeper to initialize or update my local profile.
Use $run-history-skill-builder to turn this completed workflow into a new skill package.
Use $run-history-skill-upgrader to plan a safe upgrade for this existing skill from recent run evidence.
Use $clear-communication to explain the supplied material for the current reader while preserving facts, conditions, uncertainty, and verification state.
Use $assess-interview-candidate to turn an authorized resume and job description into an auditable local interview report.

Local Paths

  • task-forest writes task data under the current workspace: .agent-workbench/task-forest/.
  • pause-and-resume keeps its checkpoint in the current conversation and creates no files solely for pausing.
  • session-handoff-prompt is read-only by default. It may validate local handoffs with real workspace paths or redact shareable handoffs.
  • user-profile-keeper writes profile data under the local user home: .compass-skills/user-profiles/v1/.
  • run-history-skill-builder writes new skill packages only to a user-approved local directory.
  • run-history-skill-upgrader is plan-only by default and edits existing skills only after explicit approval.
  • clear-communication provides writing instructions and references; it has no runtime script or fixed output directory. Follow the current task's authorization when reading material or writing a document.
  • The optional title plugin stores installation and title-protection records under the selected project's .local/ or the selected Codex home's agent-clarity/. Portable mode binds a shared state root inside the deployed package; never commit that generated binding or copy account credentials.
  • assess-interview-candidate writes case data and reports only below a user-approved local case root; generated candidate records stay outside this repository.
  • Set COMPASS_USER_PROFILE_HOME to override the profile directory.
  • Set COMPASS_AGENT_NAME to label task-forest changes by agent, for example codex, claude-code, opencode, or openclaw.

Safety Rules

  • Do not upload profile data, task data, credentials, cookies, browser sessions, or private local logs.
  • Do not read password managers, keychains, SSH keys, browser cookies, API keys, tokens, or verification codes.
  • Do not save secrets in user profiles or task graphs.
  • Treat resumes and candidate reports as confidential local records. Do not upload them or search for private background information without explicit authorization.
  • Do not use candidate age, birthplace, hometown, marital status, or other protected or sensitive traits for fit scoring, ranking, hiring, or rejection decisions.
  • Before destructive actions, publishing, remote writes, global configuration changes, credential use, or external side effects, ask for explicit user confirmation.
  • Treat HTML exports as static offline views; they do not authorize modifying the task graph.

Cross-Agent Notes

  • Codex, Claude Code, OpenClaw, OpenCode, and similar local agents may expose different skill directories and invocation syntax.
  • The portable contract is the file layout: SKILL.md plus optional references/, scripts/, assets/, and agents/.
  • If your agent has no automatic skill router, use this AGENTS.md as the router policy.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.