ai-native-sdlc-playbook / templates
CLAUDE.md0 starsChanged 2 months agoMITView on GitHub
Run it before reporting any task complete, and paste the output. If a test fails, fix the code, not the test.
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- intent-templateSkill
- secure-api-reviewSkill
The file
We split this CLAUDE.md into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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 4
Run /init to draft the first three sections from your code, then cut them down to day-one knowledge.
- Distinctive: line 10
Test: <command> (all green)
- Distinctive: line 25
Test: <command> (all pass.
- Distinctive: line 27
Run it before reporting any task complete, and paste the output.
- Distinctive: line 28
If a test fails, fix the code, not the test.
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 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
<project name>
<!-- One page at most; Claude reads all of it at session start (article Play 3d).
Run /init to draft the first three sections from your code, then cut them
down to day-one knowledge. Add a line under "Things Claude gets wrong"
the second time a mistake happens. -->Commands
- Build:
<command>(must finish with "<healthy last line>") - Test:
<command>(all green) - Lint:
<command>(zero warnings)
Conventions
<!-- The rules that matter: language and framework versions, what never to use,
what every change must include. -->Architecture
<!-- Where things live and what talks to what. Name generated or frozen paths. -->Things Claude gets wrong
<!-- Corrections that earned their place by happening twice. -->Verifying your work
- Test:
<command>(all pass; never skip or delete a failing test)
Run it before reporting any task complete, and paste the output. If a test fails, fix the code, not the test.
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.

