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/michael-harris/devteam/pre-tool-usegit clone --depth 1 https://github.com/michael-harris/devteamGrade 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": "Edit|Write",
"hooks": [
{
"type": "command",
"command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.js\" pre-tool-use-hook",
"description": "Validate tool calls, check iteration limits, circuit breaker"
},
{
"type": "prompt",
"prompt": "The agent is about to modify a file. Check if this modification is within the current task scope. The task scope should be defined in the agent's prompt context. If the file being modified is clearly unrelated to the task (e.g., modifying auth code when the task is about UI styling), return ok:false with a reason. If it's reasonable, return ok:true.",
"description": "LLM-based scope pre-check — catches obvious scope violations before they happen"
}
]
},
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/run-hook.js\" pre-tool-use-hook",
"description": "Validate bash commands, check for dangerous operations"
}
]
}
]
}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 · 29 lines scan A c19d48a66215
PreToolUse is a hook published in the GitHub repository michael-harris/devteam (18 stars, last pushed 6mo 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
PostToolUse
Runs after a tool call finishes for mcp__basic-memory__write_note, mcp__basic-memory__edit_note, Edit and Write tool calls, executing post-bm-write-validate.sh and post-file-edit.sh via bash (2 commands). From voxpelli/vp-claude.
PostToolUse
Runs after a tool call finishes for Edit and Write tool calls, executing post-file-edit.sh via bash. From voxpelli/claude-beads.
PostToolUse
Runs after a tool call finishes for Write and Edit tool calls, executing lint-on-save.sh, detect-stack-drift.sh and tool-latency.sh (3 commands). From luiseiman/dotforge.
Stop
Runs when the agent finishes a response, executing session-report.sh. From luiseiman/dotforge.
Stop
Runs when the agent finishes a response, executing session-memory.sh via bash. From odere-pro/claude-wiki-pages-plugin.
PostToolUse
Runs after a tool call finishes for Write, Edit and MultiEdit tool calls, executing post-wiki-write.sh and post-ingest-summary.sh via bash (2 commands). From odere-pro/claude-wiki-pages-plugin.