handoff
AGENTS.md0 starsChanged 4 months agoMITView on GitHub
This repository contains a Codex plugin that provides the handoff-handon skill.
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 repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- handoff-handonSkill
- handoffSkill
- handonSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
Keep the skill concise; move long templates or examples into references/.
- Very specific: line 23
Do not store secrets, private machine details, or full chat transcripts in generated handoff content.
≈ “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
Handoff Plugin Development
This repository contains a Codex plugin that provides the handoff-handon skill.
Project Shape
.codex-plugin/plugin.json: Codex plugin manifest..claude-plugin/plugin.json: Claude Code plugin metadata..cursor-plugin/plugin.json: Cursor-compatible plugin metadata..kimi-plugin/plugin.json: Kimi Code plugin metadata..opencode/INSTALL.md: OpenCode installation entry point.CLAUDE.mdandGEMINI.md: agent-specific instruction entry points.docs/README.*.md: platform-specific installation notes.skills/handoff/SKILL.md: dedicated handoff entry point.skills/handon/SKILL.md: dedicated handon entry point.skills/handoff-handon/SKILL.md: combined compatibility skill instructions.skills/handoff-handon/references/templates.md: reusable handoff and handon templates.skills/handoff-handon/agents/openai.yaml: Codex UI metadata for the skill.
Development Rules
- Keep the skill concise; move long templates or examples into
references/. - Do not store secrets, private machine details, or full chat transcripts in generated handoff content.
- Preserve
/handonas a read-and-summarize workflow until the user explicitly confirms implementation should continue. - Validate both the plugin manifest and the skill before calling the work complete.
Validation
python /path/to/plugin-creator/scripts/validate_plugin.py .
python /path/to/skill-creator/scripts/quick_validate.py skills/handoff-handonDoes 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.

