solvent-brain
CLAUDE.md1 starsChanged 49 days agoMITView on GitHub
Close ritual - before a session ends: 1. Run pending checks and scripts. 2. Update NOW.md: threads, next actions, last-session line, files touched. 3. Append a dated entry to log/YYYY-MM.md. 4. Trim inbox.md: mark done, promote, demote. 5. Commit and push. Boot ritual - on a cold start, read in this order: CLAUDE.md -> NOW.md -> inbox.md (active) -> last 1-2 log entries. Open with a short list of what changed since the last session. Rules: - Use absolute dates.…
In this repository2 other files it gives its agents.
- skeptical-reviewerSkill
- <skill-name>Skill
The file
We split this CLAUDE.md into the rules it gives an agent
7 rules. About 0 are common, 7 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
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 21
Every page has frontmatter: title, type, status, owner, updated, sources.
- Distinctive: line 22
Every new page gets at least two inbound links.
- Distinctive: line 35
Run pending checks and scripts.
- Distinctive: line 36
Update NOW.md: threads, next actions, last-session line, files touched.
- Distinctive: line 46
Use absolute dates. Convert "next week" to YYYY-MM-DD.
- Distinctive: line 47
Check "Ruled out" before proposing any approach.
- Distinctive: line 51
When compacting, the summary must keep exactly: active thread IDs and next actions, every file changed this session, unpushed commits, …
≈ “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
CLAUDE.md - Knowledge Base Operating Contract
Mission
You maintain a structured, cross-linked knowledge base for <team/practice>. I curate, ask questions and direct. You read sources and write the wiki.
Layers
- raw/ Immutable sources (exports, transcripts, docs). Read only. Never edit.
- wiki/ Pages you own. Create, update, cross-link and lint them.
- CLAUDE.md This contract. We change it together.
Special files in wiki/
- index.md Catalog of every page, by type. Update on every change.
- inbox.md Open questions and follow-ups.
- NOW.md What is in flight right now. Read it first on every session.
- log/ Append-only activity log, one file per month.
Rules
- Enrich before you create. Check index.md for an existing page first.
- Cite, don't restate. Each figure lives on one canonical page; link to it.
- Every page has frontmatter: title, type, status, owner, updated, sources.
- Every new page gets at least two inbound links.
- Flag contradictions with a callout. Never silently overwrite.
- Proceed on reversible edits. Stop and ask before deletes, production writes, or anything that changes a validated baseline.
Session rituals
- Open: read CLAUDE.md, NOW.md, inbox.md, the last log entry.
- Close: update NOW.md, append to the log, list files touched, then commit.
Session continuity
Session context is temporary. The files are the memory.
Close ritual - before a session ends:
- Run pending checks and scripts.
- Update NOW.md: threads, next actions, last-session line, files touched.
- Append a dated entry to log/YYYY-MM.md.
- Trim inbox.md: mark done, promote, demote.
- Commit and push.
Boot ritual - on a cold start, read in this order: CLAUDE.md -> NOW.md -> inbox.md (active) -> last 1-2 log entries. Open with a short list of what changed since the last session.
Rules:
- Use absolute dates. Convert "next week" to YYYY-MM-DD.
- Check "Ruled out" before proposing any approach.
- A thread untouched for 10+ days is stale: re-confirm before acting.
- NOW.md, index.md and inbox.md have one writer at a time.
When compacting, the summary must keep exactly: active thread IDs and next actions, every file changed this session, unpushed commits, figures quoted this session, and any decision I ratified, verbatim.
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.

