opencode-caveman
AGENTS.md2 starsChanged 56 days agoMITView on GitHub
OpenCode plugin packaging of the Caveman rules (upstream: JuliusBrussee/caveman, MIT).
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 repository7 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- caveman-commitSkill
- caveman-helpSkill
- caveman-reviewSkill
- cavemanSkill
- megacaveSkill
- ultracaveSkill
The file
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 7
Test: npm test (node --test, no runtime dependencies).
≈ “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
opencode-caveman — agent notes
OpenCode plugin packaging of the Caveman rules (upstream: JuliusBrussee/caveman, MIT).
Commands
- Test:
npm test(node--test, no runtime dependencies). - Format:
npm run format/npm run format:check(Prettier;skills/,agents/,NOTICE.md,LICENSEare excluded and must stay byte-identical). - Pre-commit hook: wired automatically by
npm install(preparescript); manual fallback isgit config core.hooksPath .githooks. It runsnpm test. - Local use: opening OpenCode in this repo loads
.opencode/plugins/caveman/index.mjs(V2 auto-discovery, plus the rootopencode.jsonpluginsentry).
Rules
skills/andagents/are vendored from upstream, not authored here. Do not edit them locally. Re-vendor from the pinned upstream commit in NOTICE.md and update the SHA there when syncing.- Runtime code is
hooks/*.cjsplus.opencode/plugins/caveman/index.mjs. The.mjsbridges to CommonJS withcreateRequireso it loads with no build step. - The default export is dual-shape: V2 validates
idplussetup(ctx), V1 (1.18.29+) callsserver()for the legacy hooks. Keep exactly one plugin-shaped export; OpenCode's legacy loader calls every named export of a plugin module as a plugin, so helpers live incaveman-frontmatter.cjs. - The injected ruleset is the active mode's vendored skill, loaded whole with frontmatter stripped, under a
CAVEMAN MODE ACTIVE — mode: <mode>banner;offinjects nothing. Modes are caveman (default), ultracave, megacave; legacy level names (lite/full/ultra/wenyan*) resolve inhooks/caveman-config.cjs. - State file is
~/.config/opencode/.caveman-active(XDG/OPENCODE_CONFIG_DIRaware). Never write state during tests outside a temp dir.
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.

