Tree-Ring-Memory / plugins
AGENTS.md18 starsChanged 3 months agoMITView on GitHub
Canonical native plugin distribution material. tree-ring-memory contains Codex/Claude manifests, commands, skills, hooks, legal text and public ZIP builder. Root marketplaces point here. The public OpenAI upload renders skill front matter without legacy metadata, preserves the skill body, and includes supported interface fields in skills/<skill>/agents/openai.yaml. Keep the public listing shortDescription within 30 characters. Native/shared skill source remains separate. Ship all four native lifecycle hooks. Codex skills-only means no MCP dependency; retain hooks and executable ZIP permissions. Effective host-owned project hooks cause…
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 31,774 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 repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- crates/AGENTS.mdAGENTS.md
- docs/AGENTS.mdAGENTS.md
- fixtures/AGENTS.mdAGENTS.md
- marketing/AGENTS.mdAGENTS.md
- scripts/AGENTS.mdAGENTS.md
- docs/llms.txtllms.txt
- tree-ring-memorySkill
The file
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 17
Keep shared skill instructions aligned with the CLI and preserve canonical hook bytes when syncing standalone marketplaces.
≈ “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
plugins
Purpose
Canonical native plugin distribution material.
Ownership
tree-ring-memory contains Codex/Claude manifests, commands, skills, hooks, legal text and public ZIP builder. Root marketplaces point here.
Local Contracts
The public OpenAI upload renders skill front matter without legacy metadata, preserves the skill body, and includes supported interface fields in skills/<skill>/agents/openai.yaml. Keep the public listing shortDescription within 30 characters. Native/shared skill source remains separate. Ship all four native lifecycle hooks. Codex skills-only means no MCP dependency; retain hooks and executable ZIP permissions. Effective host-owned project hooks cause plugin hooks to stand down; Codex linked-worktree root layers use the proven primary hook source, while Claude keeps local ownership checks. A genuinely absent project-local .tree-ring is a quiet skip; an existing entry, including a dangling symlink, must retain runtime diagnostics. Never redirect worktree memory to the primary checkout's store.
Work Guidance
Keep shared skill instructions aligned with the CLI and preserve canonical hook bytes when syncing standalone marketplaces. Do not put stores or user paths in archives.
Verification
python3 scripts/validate-plugin-packages.py; inspect deterministic archives and run unpacked hook probes.
Child DOX Index
None. This document owns the full subtree.
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.

