map-framework
AGENTS.md155 starsChanged 59 days agoMITView on GitHub
This project uses the MAP (Monitor-Actor-Predictor) Framework for structured development. Important: You must trust this project in Codex settings for project-scoped configuration to take effect. Without trust, .codex/ config, hooks, and agent files are ignored. Codex skills are installed under .agents/skills. MAP uses a workflow gate hook that restricts file-modifying commands during research and review phases. This prevents accidental edits while exploring. Note: Hooks require hooks = true in config.toml and are not supported on Windows. For write-capable MAP skills…
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository48 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- map-architectureSkill
- map-autoSkill
- map-checkSkill
- map-debugSkill
- map-efficientSkill
- map-explainSkill
- map-fastSkill
- map-learnSkill
- map-memory-nowSkill
- map-planSkill
- map-prd-reviewSkill
- map-releaseSkill
- map-resumeSkill
- map-reviewSkill
- map-skill-evalSkill
- map-so-searchSkill
- map-stateSkill
- map-taskSkill
- map-tddSkill
- map-tokenreportSkill
- map-understandSkill
- map-upgradeSkill
- map-wayfindSkill
- map-architectureSkill
- map-autoSkill
- map-checkSkill
- map-debugSkill
- map-efficientSkill
- map-explainSkill
- map-fastSkill
- map-learnSkill
- map-memory-nowSkill
- map-planSkill
- map-prd-reviewSkill
- map-releaseSkill
- map-resumeSkill
- map-reviewSkill
- map-skill-evalSkill
- map-so-searchSkill
- map-stateSkill
- map-taskSkill
- map-tddSkill
- map-tokenreportSkill
- map-understandSkill
- map-upgradeSkill
- map-wayfindSkill
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 42
Do not edit unrelated files, even if they are nearby or easy to clean up.
- Distinctive: line 43
Do not add, remove, or upgrade dependencies unless the current task or subtask explicitly names that dependency change.
- Distinctive: line 44
Do not refactor neighboring code unless the acceptance criteria cannot pass without that exact refactor.
- Distinctive: line 45
If a dependency change, broad refactor, or scope expansion seems necessary, report it as a blocker/tradeoff instead of doing it silently.
≈ “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.
Files
MAP Framework Agents
This project uses the MAP (Monitor-Actor-Predictor) Framework for structured development.
Prerequisites
Important: You must trust this project in Codex settings for project-scoped
configuration to take effect. Without trust, .codex/ config, hooks, and
agent files are ignored. Codex skills are installed under .agents/skills.
Available Agents
| Agent | Role | Invoked By |
| researcher | Codebase exploration and context gathering | $map-plan Step 0 |
| decomposer | Task decomposition into atomic subtasks | $map-plan Step 4 |
| monitor | Code review and validation | $map-plan SPEC_REVIEW, $map-efficient |
Available Skills
| Skill | Purpose |
| $map-plan | Plan and decompose complex tasks |
| $map-efficient | Execute approved MAP plans end to end |
| $map-fast | Quick implementation for small changes |
| $map-check | Quality gates and verification |
| $map-review | Pre-landing code review (normal, adversarial, cross-AI) |
| $map-prd-review | Review PRD readiness, strengths, risks, and uncovered edge cases |
Hooks
MAP uses a workflow gate hook that restricts file-modifying commands during research and review phases. This prevents accidental edits while exploring.
Note: Hooks require hooks = true in config.toml and are not
supported on Windows.
Mutation Boundary Constraints
For write-capable MAP skills and agents:
- Do not edit unrelated files, even if they are nearby or easy to clean up.
- Do not add, remove, or upgrade dependencies unless the current task or subtask explicitly names that dependency change.
- Do not refactor neighboring code unless the acceptance criteria cannot pass without that exact refactor.
- If a dependency change, broad refactor, or scope expansion seems necessary, report it as a blocker/tradeoff instead of doing it silently.
Getting Started
- Trust this project in Codex settings
- Type
$map-plan <your task>to start planning - Type
$map-efficientto execute an approved plan
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
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.