neogents / templates
CLAUDE.md1 starsChanged 11 days agoMITView on GitHub
The file
We split this CLAUDE.md into the rules it gives an agent
6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Very specific: line 10
After completing meaningful work, save context: run /neo:save or ask NEO to update the brain.
- Very specific: line 11
When you correct a repeated mistake, add the rule here or ask neo-shadow to record it in .neo/brain/LESSONS.md.
- Distinctive: line 26
Never commit unless explicitly asked.
- Distinctive: line 27
Run the test command before declaring any change complete.
- Distinctive: line 33
Always preserve: the current focus, open todos, and any unverified or uncommitted changes.
- Very specific: line 35
If work was done that the brain does not yet reflect, note explicitly that a /neo:save is pending.
≈ “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
Project conventions
<!-- Starter CLAUDE.md written by /neo:init. Keep under ~100 lines — bloat causes rule-skipping.
Prune test: "would removing this line cause a mistake?" If no, remove it.
Long-term project knowledge lives in .neo/brain/, not here. -->Memory
- Long-term project memory lives in
.neo/brain/(loaded automatically at session start). - After completing meaningful work, save context: run
/neo:saveor ask NEO to update the brain. - When you correct a repeated mistake, add the rule here or ask neo-shadow to record it in
.neo/brain/LESSONS.md.
Commands
<!-- The commands that gate "done". Filled by /neo:init from your answers. -->- Build:
<fill: build command> - Test:
<fill: test command> - Lint/typecheck:
<fill: check command>
Rules
<!-- Project-specific rules that must hold on every change. Examples below — replace with real ones. -->- Match existing patterns before inventing new ones; check neighboring files first.
- Never commit unless explicitly asked.
- Run the test command before declaring any change complete.
Compact Instructions
<!-- Injected into Claude Code's compaction prompt. Keeps compaction brain-aware. -->- Always preserve: the current focus, open todos, and any unverified or uncommitted changes.
- The second brain in
.neo/brain/is the source of truth for project memory — prefer pointing to it over restating its content. - If work was done that the brain does not yet reflect, note explicitly that a
/neo:saveis pending.
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.