c-brain
01Plugin Claude Code
C Brain — a persistent, growing knowledge trunk for command-line agents.
Plugin Claude Code
C Brain — a persistent, growing knowledge trunk for command-line agents.
Plugin Claude Code
A memory that grows. Your agent is brilliant within a session and amnesic between two — this gives it a persistent knowledge trunk on your machine: what you work out once is distilled into a note, filed, linked, and surfaced automatically next time, from any project. It makes no request of its own — no telemetry, no…
Agent
Keeps the OVERALL COHESION of the trunk — reads the whole graph topology (links, subsets, similarities) to weave missing links, connect isolated notes, spot disconnected islands and inconsistent placement. The wide view, where the gardener files note by note. Run it periodically, or when the tree starts to fragment.
Agent
Manages the freshness of the trunk — proposes archiving dead weight, never deletes on its own.
Agent
Red team of the trunk — puts notes through the wringer to hunt what is stale, false, contradicted or unverifiable. Run it periodically, or on a specific note or area, to keep the trunk HONEST. It does not rewrite knowledge, it tests it.
Agent
Turns a raw work session (sessions/archive/ notes, .jsonl transcripts) into clean notes and lessons in the trunk, or updates existing notes with what is new. Run it after a session worth capturing.
Agent
Tends the trunk (/.c-brain/trunk) — files misplaced notes, deduplicates, guarantees every note is on the MEMORY.md + lessons/INDEX.md map, weaves and repairs [[...]] links, masks secrets. Run it after a work session, or when the tree looks untidy.
Agent
Watches and frees the Mac's physical resources (RAM, CPU, heat) — hunts abandoned processes, compressed memory, permanent animations. Run it when the machine heats up, drags, spins its fans, when the battery melts, or periodically for a status report. Never touches the trunk's knowledge nor its software infrastructure.
Agent
Repairs the trunk's machine infrastructure — hooks, symlinks, capsule, wiring. Never the content of the notes.
Agent
Writes cross-cutting syntheses — connects what has been learned about one theme across several projects into a dense essay.
Hook
Runs when a session starts, executing plugin_bootstrap.py, brain_anticipate.py and check_update.py via python3 with --hook (3 commands). From Yuno15-bb/c-brain.
Hook
Runs when you submit a prompt, before the agent sees it, executing inject_recall.py via python3. From Yuno15-bb/c-brain.
Hook
Runs before the agent uses a tool for Write, Edit, MultiEdit and NotebookEdit tool calls, executing pre_snapshot.py via python3. From Yuno15-bb/c-brain.
Hook
Runs after a tool call finishes for Write, Edit, Read, Write, Edit, MultiEdit and NotebookEdit tool calls, executing brain_status.py, on_fiche_write.py, track_read.py and post_diff.py via python3 (4 commands). From Yuno15-bb/c-brain.
Hook
Runs when a session ends, executing archive_session.py, auto_maintain.py and session_close.py via python3 (3 commands). From Yuno15-bb/c-brain.
Skill Claude CodeCodex
Turn what was just worked out into a C Brain note — filed in the right zone, linked to what it relates to, indexed. Use when the user says "remember this", "save that", "note it down", "distill this session", or when a non-obvious problem has just been solved and the reasoning would otherwise be lost.
Skill Claude CodeCodex
Check the health of the C Brain installation and trunk — dead links, unindexed notes, broken hooks, stale state. Use when recall seems to return nothing, when notes are not being saved, when the user says C Brain "is not working", or before trusting the trunk for something important.
Skill Claude CodeCodex
Search the C Brain trunk for notes relevant to a subject, and read the ones that matter. Use when the user asks what they already know about something, wants past decisions on a topic, says "did we solve this before", "what do I have on X", "check my notes", or when a task smells like something already worked out once.