brain-init
Skill73 starsChanged 3 months agoMITView on GitHub
Scaffold a file-based memory system (index, decision ledger, open questions, session log, optional product truth file) so a project can serve as a durable second brain. Use when the user wants to set up memory, an external brain, or the ballast structure in a project.
In this repository15 other files it gives its agents.
- checkpointSkill
- decision-ledgerSkill
- doctorSkill
- goalSkill
- knowledge-baseSkill
- pinSkill
- proof-standardSkill
- recallSkill
- rehearsalSkill
- reportSkill
- researcherSkill
- scheduleSkill
- setupSkill
- skill-forgeSkill
- verify-gateSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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
- Very specific: line 12
Create memory/ in the project root and copy these templates from this skill's templates/ directory, filling <project> placeholders with the …
- Very specific: line 19
If the user keeps rules in .claude/ballast.rules.json, leave it untouched.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill 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
Brain scaffold
Set up the ballast memory structure in the current project. Decide everything you can yourself; report what you created instead of asking questions.
Steps
- Create
memory/in the project root and copy these templates from this skill'stemplates/directory, filling<project>placeholders with the actual project name:templates/00-INDEX.md→memory/00-INDEX.mdtemplates/DECISIONS.md→memory/DECISIONS.mdtemplates/OPEN-QUESTIONS.md→memory/OPEN-QUESTIONS.mdtemplates/SESSION-LOG.md→memory/SESSION-LOG.mdtemplates/PRODUCT-TRUTH.md→memory/PRODUCT-TRUTH.md— only if the project is (or documents) a product; skip for pure-knowledge projects and say so
- Append the session-start block from
templates/CLAUDE-snippet.mdto the project'sCLAUDE.md(create the file if missing; if the block is already there, don't duplicate it). The snippet is tool-neutral — if the project also uses Codex, append the same block toAGENTS.md(seedocs/CODEX.md). - If the user keeps rules in
.claude/ballast.rules.json, leave it untouched; if they ask for a starter catalog, copyrules/ballast.rules.example.jsonfrom the plugin root to.claude/ballast.rules.jsonand tell them to prune it. - Report: files created, files skipped (and why), and the one-line habit — "decisions get recorded the moment they're confirmed."
Conventions (explain these to the user once, briefly)
- The index is the map.
00-INDEX.mdsays what lives where and the write rules. New file types get a row there first. - The ledger is append-only. See the decision-ledger skill — never edit, only supersede.
- Open questions never dissolve silently. Unresolved items are registered in
OPEN-QUESTIONS.mdand closed with a link to the decision that resolved them. The same file holds readings in force — an "ok" that could have meant anything, written down as what the user said plus what you assumed — so a non-answer never quietly becomes a decision. - The session log is cheap insurance. A few dated bullets per working session; when context resets, this is the recovery path.
- Claims carry labels; product claims carry proof. See verify-gate and proof-standard.
- The scaffold is a floor, not a ceiling. Other skills grow
memory/later — checkpoint addsCHECKPOINT.md,checkpoints/, and the single-useHANDOFF.md; verified reference material accumulates undermemory/knowledge/. Don't pre-create these; give each a row in the index when it first appears.
Part of ballast — foundations first, every solved path kept, done means checks pass.
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.

