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/corvidae-coding-projects/thermite/pre-tool-usegit clone --depth 1 https://github.com/Corvidae-Coding-Projects/ThermiteGrade 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.
This is a copy
89% identical to PostToolUse — 24 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
{
"PreToolUse": [
{
"hooks": [
{
"command": "HOOK=\"$(git rev-parse --show-toplevel 2>/dev/null)/.claude/hooks/pre-web-check.py\"; if [ -f \"$HOOK\" ]; then python3 \"$HOOK\"; else exit 0; fi",
"timeout": 5,
"type": "command"
}
],
"matcher": "WebFetch|WebSearch"
},
{
"hooks": [
{
"command": "HOOK=\"$(git rev-parse --show-toplevel 2>/dev/null)/.claude/hooks/work-check.py\"; if [ -f \"$HOOK\" ]; then python3 \"$HOOK\"; else exit 0; fi",
"timeout": 3,
"type": "command"
}
],
"matcher": "Write|Edit|Bash"
},
{
"hooks": [
{
"command": "HOOK=\"$(git rev-parse --show-toplevel 2>/dev/null)/tooling/spec-discipline.py\"; if [ -f \"$HOOK\" ]; then python3 \"$HOOK\"; else exit 0; fi",
"timeout": 5,
"type": "command"
},
{
"command": "HOOK=\"$(git rev-parse --show-toplevel 2>/dev/null)/tooling/anti-pattern-gate.py\"; if [ -f \"$HOOK\" ]; then python3 \"$HOOK\"; else exit 0; fi",
"timeout": 5,
"type": "command"
}
],
"matcher": "Write|Edit"
}
]
}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 · 39 lines scan A 9344caaa13d0
PreToolUse is a hook published in the GitHub repository Corvidae-Coding-Projects/Thermite (53 stars, last pushed 25d 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. It is 89% identical to PostToolUse, differing in 24 lines, and is treated as a copy.
Other hooks, from other repositories
SessionStart
Runs when a session starts, running ana _capture. From anatomia-dev/anatomia.
PreToolUse
Runs before the agent uses a tool for Write, Edit, Bash, mcp__.*, WebFetch and WebSearch tool calls, executing pre-tool-gate.mjs via node (4 commands). From kirollosatef/customgpt-claude-quadruple-verification.
PostToolUse
Runs after a tool call finishes, executing post-tool-audit.mjs via node. From kirollosatef/customgpt-claude-quadruple-verification.
SessionStart
Runs when a session starts, executing bootstrap-repo.sh with --init and --recursive (4 commands). From dravr-ai/dravr-embacle.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing sounio_coord_agent_hook.py via python3 with --agent. From Sounio-lang/sounio.
PostToolUse
Runs after a tool call finishes for Write and Edit tool calls, executing format_and_lint.sh. From supabase/supabase.