Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
@AGENTS.md
## Claude Code notes
- Project skills: `/contribute` (idea → spec → code → gates → PR, for anyone,
engineer or not) and `/spec-idea` (turn an idea into a filed issue, no
code). Both live in `.claude/skills/`.
- The `skills/` directory and `plugins/inite-brain/` are the product (skills
for agents that _use_ Brain as memory), not instructions for working on
this repo.
- `.claude/settings.local.json`, `.claude/worktrees/` and `.claude/*.lock`
are per-machine and gitignored; never commit them.
- The e2e suites start Docker containers (testcontainers). Ask before running
them on someone's laptop; unit + socket tests are always safe.
The line at the top of this page pins the label git:20261018.e75e011, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_6xailky6qxsb5hhj
GET https://markdownregistry.com/api/v1/resolve?ref=inite-ai/inite-brain-service/CLAUDE.md
GET https://markdownregistry.com/api/v1/blob/def32a8b9982d3591c54e4ce07877c02aa5f4b28a4a9c9f34a9a0fd773343781
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
inite-ai/inite-brain-service · .claude/skills/contribute/SKILL.md · Take an idea for INITE Brain from plain words to a green pull request. Use when someone says "I have an idea", "I want…
inite-ai/inite-brain-service · .claude/skills/spec-idea/SKILL.md · Turn an idea for INITE Brain into a well-formed GitHub issue — no code. Use when someone wants to propose, suggest or…
inite-ai/inite-brain-service · plugins/inite-brain/skills/brain-bitemporal/SKILL.md · How to query the INITE Brain knowledge graph across time — the asOf parameter, validFrom/validUntil semantics, reading…
inite-ai/inite-brain-service · plugins/inite-brain/skills/brain-conflict/SKILL.md · How to detect and resolve conflicting beliefs in the INITE Brain knowledge graph — the COMPETING fact status…
inite-ai/inite-brain-service · plugins/inite-brain/skills/brain-recall/SKILL.md · Recall everything brain knows about one specific entity — current profile, full bitemporal timeline, graph neighbours…
inite-ai/inite-brain-service · plugins/inite-brain/skills/brain-search/SKILL.md · Semantic search over the INITE Brain knowledge graph via the search_knowledge MCP tool. Use when the user wants to find…
inite-ai/inite-brain-service · plugins/inite-brain/skills/brain-write/SKILL.md · How to write to the INITE Brain knowledge graph from an agent loop — record_fact (with the conversationId / evidence[]…
inite-ai/inite-brain-service · skills/brain-bitemporal/SKILL.md · How to query the INITE Brain knowledge graph across time — the asOf parameter, validFrom/validUntil semantics, reading…
inite-ai/inite-brain-service · skills/brain-conflict/SKILL.md · How to detect and resolve conflicting beliefs in the INITE Brain knowledge graph — the COMPETING fact status…
