agenda-intelligence-md
CLAUDE.md8 starsChanged 6 months agoMITView on GitHub
AGENTS.md is the canonical project contract — apply it, do not restate it. It points to the detail files, loaded when the task needs them: Runtime skill contracts: skills/agenda-intelligence/SKILL.md and skills/source-ingest/SKILL.md. Sufficient for most changes — lint, typecheck, full test suite. Everything else, including which step failed and why, is in docs/local-checks.md. Do not keep a second copy of that list here. Two traps worth naming up front: black --check runs first in CI and fails the whole pipeline on…
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- llms.txtllms.txt
- agenda-intelligenceSkill
- source-ingestSkill
The file
We split this CLAUDE.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 25
Follow existing schema, CLI, and MCP patterns instead of inventing new ones.
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
@AGENTS.md
Claude Code working rules
AGENTS.md is the canonical project contract — apply it, do not restate it. It points to the detail files, loaded when the task needs them:
- docs/vertical-workers.md — shipped workers, the artifact ladder, hard requirements for a new one.
- docs/geography-routing.md — routing term sets; one of the two canon mirrors the routing guard checks.
- docs/local-checks.md — what to run before push, in what order, plus the dual-copy invariant.
Runtime skill contracts: skills/agenda-intelligence/SKILL.md and skills/source-ingest/SKILL.md.
Before push
make ciSufficient for most changes — lint, typecheck, full test suite. Everything else, including which step failed and why, is in docs/local-checks.md. Do not keep a second copy of that list here.
Two traps worth naming up front: black --check runs first in CI and fails the whole pipeline on formatting drift, and the dual-copy paths under src/agenda_intelligence/data/ must change in the same commit as their top-level twins.
Working style in this repo
Follow existing schema, CLI, and MCP patterns instead of inventing new ones. Additive changes are allowed without prior approval under the change-discipline rules in AGENTS.md — behind a stable contract, with a contract test and a CHANGELOG entry.
Breaking v1 schema changes, removing MCP tools, and renaming public HTTP endpoints or A2A profiles need an ADR and a version bump. The v1.0.x contract freeze (ADR 0003) is still in force.
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.