Claude-Pipeline
AGENTS.md44 starsChanged 4 months agoMITView on GitHub
This file accumulates patterns and learnings across pipeline sessions. Auto-updated after each pipeline run. After each successful pipeline run, the following learnings are automatically extracted and appended: The extraction happens in the post-run phase of auto-pipeline.md. This file is read by Phase 0 (Pre-Check) to provide historical context about: - Patterns that have worked well in this project - Common mistakes to avoid - Security considerations specific to this codebase - Project conventions learned from previous runs Last updated: Never…
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 32,671 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 repository6 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- new-migrationSkill
- scaffold-apiSkill
- new-migrationSkill
- scaffold-apiSkill
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 22
After each successful pipeline run, the following learnings are automatically extracted and appended:
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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
AGENTS.md - Pipeline Learning Memory
This file accumulates patterns and learnings across pipeline sessions. Auto-updated after each pipeline run.
Patterns Discovered
<!-- Format: - YYYY-MM-DD: Pattern description (session: {id}) -->Common Failures & Fixes
<!-- Format: - Error pattern → Fix applied -->Project-Specific Rules Learned
<!-- Conventions discovered from codebase analysis -->Security Patterns
<!-- Recurring security issues and mitigations -->How This File Is Updated
After each successful pipeline run, the following learnings are automatically extracted and appended:
- Phase 3 (Adversarial Review): Issues that were raised and resolved during design revision
- Phase 6 (Build): Build failures that were encountered and fixed
- Phase 11 (Security): Security findings and their mitigations
The extraction happens in the post-run phase of auto-pipeline.md.
Usage
This file is read by Phase 0 (Pre-Check) to provide historical context about:
- Patterns that have worked well in this project
- Common mistakes to avoid
- Security considerations specific to this codebase
- Project conventions learned from previous runs
Last updated: Never (no pipeline runs yet)
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.

