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/mimfort/rag_for_git/pre-tool-usegit clone --depth 1 https://github.com/mimfort/rag_for_gitGrade A, and why
PreToolUse 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.
What it actually says
{
"PreToolUse": [
{
"matcher": "mcp__reviewer__publish_review|mcp__plugin_rag-reviewer_reviewer__publish_review",
"hooks": [
{
"type": "command",
"command": "python3 \"${CLAUDE_PLUGIN_ROOT}/hooks/review_cost.py\""
}
]
}
]
}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 · 13 lines scan A 1c272768436a
PreToolUse is a hook published in the GitHub repository mimfort/rag_for_git (21 stars, last pushed 2d ago), licensed MIT. 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other hooks, from other repositories
PreToolUse
Runs before the agent uses a tool for Grep and Bash tool calls, executing agentmap-nudge.mjs via node (2 commands). From raymondchins/agentmap.
PreToolUse
Runs before the agent uses a tool for Bash, Edit, Write, MultiEdit and NotebookEdit tool calls, executing log-bash.py, block-generated.py and warn-scope.py via python3 (3 commands). From paullukic/coograph.
SessionStart
Runs when a session starts, executing report-graph.py via python3. From paullukic/coograph.
PreToolUse
Runs before the agent uses a tool for Bash, Bash, Bash, Edit, Write, Edit and Write tool calls, executing pre-commit-zetetic.sh, pre-push-review.sh, pre-push-provenance.sh, pre-edit-layer-check.sh and pre-tool-claim-gate.sh (5 commands). From cdeust/ai-architect-mcp-codebase.
PostToolUse
Runs after a tool call finishes for Bash, Bash, Edit, Write, WebFetch and WebSearch tool calls, executing post-commit-difficulty.sh, post-commit-lab-notebook.sh, post-edit-balance.sh and post-research-provenance.sh (4 commands). From cdeust/ai-architect-mcp-codebase.
SessionStart
Runs when a session starts, executing session-start.sh and session-start-research.sh (2 commands). From cdeust/ai-architect-mcp-codebase.