spliceailookup-link
CLAUDE.md0 starsChanged 4 months agoMITView on GitHub
Claude Code entrypoint only: - Use AGENTS.md for shared repository instructions. - Keep Claude-specific additions here short and tool-specific. - Prefer make ci-local before final handoff. It runs lint-loc, which enforces the 600-LOC per-file budget. - When planning an edit that would push a spliceailookup_link/ module past about 500 lines, propose a cohesive split first rather than growing the file. - Remember: the upstream scoring API reports errors as HTTP 200 + an error field, and calls can take 30s+.…
We split this CLAUDE.md into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Distinctive: line 7
Use AGENTS.md for shared repository instructions.
- Distinctive: line 8
Keep Claude-specific additions here short and tool-specific.
- Very specific: line 9
Prefer make ci-local before final handoff.
- Very specific: line 11
When planning an edit that would push a spliceailookup_link/ module past about 500 lines, propose a cohesive split first rather than …
≈ “Common” is an estimate: at least 1 in 5 of the 25,680 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
CLAUDE.md
@AGENTS.md
Claude Code entrypoint only:
- Use
AGENTS.mdfor shared repository instructions. - Keep Claude-specific additions here short and tool-specific.
- Prefer
make ci-localbefore final handoff. It runslint-loc, which enforces the 600-LOC per-file budget. - When planning an edit that would push a
spliceailookup_link/module past about 500 lines, propose a cohesive split first rather than growing the file. - Remember: the upstream scoring API reports errors as HTTP 200 + an
errorfield, and calls can take 30s+. Do not "fix" a slow/empty response by shortening timeouts or treating HTTP 200 as unconditional success.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ci-failure-triageSkill
- code-quality-reviewSkill
- dependency-cve-sweepSkill
- fastapi-route-changeSkill
- fleet-standard-adoptionSkill
- mcp-tool-changeSkill
- release-readinessSkill
- security-reviewSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

