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/vukkt/token-warden/stopgit clone --depth 1 https://github.com/vukkt/token-wardenGrade A, and why
Stop 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
{
"Stop": [
{
"hooks": [
{
"type": "command",
"command": "cd \"${CLAUDE_PLUGIN_ROOT}\" && { [ -f node_modules/.warden-deps-ok ] || { npm ci --no-audit --no-fund --silent && touch node_modules/.warden-deps-ok; }; } && ./node_modules/.bin/tsx src/collect.ts || true",
"timeout": 120
}
]
}
]
}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 610b4ec4584d
Stop is a hook published in the GitHub repository vukkt/token-warden (13 stars, last pushed 4d 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 Bash, WebFetch, WebSearch, mcp__.*, Write and Edit tool calls, executing syntax-coach.py, scan-output.sh, log-write.sh and validate-json-schema.sh (4 commands). From ariaxhan/kernel-claude.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing context-usage.py, route-request.sh and post-compact-restore.sh (3 commands). From ariaxhan/kernel-claude.
PreCompact
Runs before the context is compacted, executing pre-compact-commit.sh. From ariaxhan/kernel-claude.
SessionEnd
Runs when a session ends, executing session-end.sh. From ariaxhan/kernel-claude.
PermissionRequest
Runs when the agent asks permission for an action for Bash tool calls, executing auto-approve-safe.sh. From ariaxhan/kernel-claude.
PostToolUseFailure
Runs when a tool call fails for Edit, Write and Bash tool calls, executing capture-error.sh. From ariaxhan/kernel-claude.