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/carta/plugins/post-tool-usegit clone --depth 1 https://github.com/carta/pluginsGrade 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
89% identical to PreToolUse — 15 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": [
{
"matcher": "mcp__(.*[Cc]arta.*|2827383e-1775-4df3-b6ff-04d5392f6d18|640916d9-5e0c-4d0b-830a-03500fa93e5e|1af3c326-9402-463c-ba5c-d62de59cf57b|8eb65db0-0cbd-4f50-833b-3057c150d41a|33b9b857-8443-4b2d-b191-2d9b6c50eb86)__.*",
"hooks": [
{
"type": "command",
"command": "\"${CLAUDE_PLUGIN_ROOT}/hooks/dispatch.sh\" cache-commands",
"timeout": 5
},
{
"type": "command",
"command": "\"${CLAUDE_PLUGIN_ROOT}/hooks/dispatch.sh\" track-corporation",
"timeout": 5
}
]
}
]
}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 · 19 lines scan A 602130b02e39
PostToolUse is a hook published in the GitHub repository carta/plugins (12 stars, last pushed 3d 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 89% identical to PreToolUse, differing in 15 lines, and is treated as a copy.
Other hooks, from other repositories
SessionStart
Runs when a session starts, running an inline shell check. From n24q02m/imagine-mcp.
Stop
Runs when the agent finishes a response, running /Users/roman/.dotnet/tools/multiagent-setup hook stop-guard. From Neftedollar/FsLangMCP.
BeforeTool
Runs on the BeforeTool event, running npx -y cc-safety-net hook --gemini-cli. From kenryu42/gemini-safety-net.
AfterAgent
Runs on the AfterAgent event, executing phase-gate.js and ralph-retry.js via node (2 commands). From richardcb/oh-my-gemini.
SubagentStop
Runs when a subagent finishes, executing office-status-hook.js via node. From KbWen/agent-virtual-office.
Stop
Runs when the agent finishes a response, executing stop-review-gate-hook.mjs via node. From abiswas97/gemini-plugin-cc.