Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add hooks/yuno15-bb/c-brain/post-tool-usegit clone --depth 1 https://github.com/Yuno15-bb/c-brainGrade A, and why
PostToolUse scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the commands this hook runs, not an audit. A hook is shell that executes on your machine at the event it names, which is why every command in it is printed with what was found.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
70% identical to TaskCompleted — 39 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"PostToolUse": [
{
"_why": "SESSION LIVENESS. Every other PostToolUse entry matches a SLICE of the tools — Read for one, Write|Edit for the others — so a session spent in Bash, Grep or Task emitted no sign of life at all and the capsule hid the orb mid-work (measured: a status 654 s stale while the session never stopped). This one matches everything on purpose: the question is 'is Claude still working', and any tool running is the answer. It refreshes LIVENESS only, never the activity label.",
"matcher": "*",
"hooks": [
{
"type": "command",
"command": "python3 \"${CLAUDE_PLUGIN_ROOT}/hooks/brain_status.py\" heartbeat",
"timeout": 5
}
]
},
{
"matcher": "Write|Edit",
"hooks": [
{
"type": "command",
"command": "python3 \"${CLAUDE_PLUGIN_ROOT}/hooks/on_fiche_write.py\"",
"timeout": 15
}
]
},
{
"matcher": "Read",
"hooks": [
{
"type": "command",
"command": "python3 \"${CLAUDE_PLUGIN_ROOT}/hooks/track_read.py\"",
"timeout": 10
}
]
},
{
"matcher": "Write|Edit|MultiEdit|NotebookEdit",
"hooks": [
{
"type": "command",
"command": "python3 \"${CLAUDE_PLUGIN_ROOT}/companion/hooks/post_diff.py\"",
"timeout": 8
}
]
}
]
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 45 lines scan A efa9006ff40e
PostToolUse is a hook published in the GitHub repository Yuno15-bb/c-brain (2 stars, last pushed 8d ago), licensed Apache-2.0. Its token cost is not measured: a hook is shell that never enters the context. A static security scan graded it A with 0 findings. It is 70% identical to TaskCompleted, differing in 39 lines, and is treated as a copy.
Other hooks, from other repositories
SessionStart
Runs when a session starts, executing session-start.sh. From HKUDS/LightRAG.
SessionStart
Runs when a session starts, executing skeptic-suggest.sh via bash. From gambletan/cortex.
SessionStart
Runs when a session starts, running agent-recall-session-start. From mnardit/agent-recall.
SessionEnd
Runs when a session ends, executing hook.sh via bash. From 6m1w/claude-sound-fx.
SessionStart
Runs when a session starts, executing plugin-setup.sh via bash. From foxtrottwist/shortcuts-mcp.
SubagentStop
Runs when a subagent finishes, executing cc-notifier.sh. From TakashiKakizoe1109/cc-notifier-voice.