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/haabe/mycelium/pre-tool-usegit clone --depth 1 https://github.com/haabe/myceliumGrade 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 3d 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
59% identical to SessionStart — 99 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.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"PreToolUse": [
{
"matcher": "Write|Edit|MultiEdit",
"hooks": [
{
"type": "command",
"command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/gate.sh",
"timeout": 5,
"statusMessage": "Mycelium preflight gate + secret scan"
},
{
"type": "command",
"command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/discovery-gate.sh",
"timeout": 5,
"statusMessage": "Mycelium discovery gate (new source files in discovery-untouched projects)"
},
{
"type": "command",
"command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/brownfield-gate.sh",
"timeout": 5,
"statusMessage": "Mycelium brownfield gate (one-shot: existing code, no discovery state)"
},
{
"type": "command",
"command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/scope-gate.sh",
"timeout": 5,
"statusMessage": "Mycelium scope enforcement"
},
{
"type": "command",
"command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/framework-guard.sh",
"timeout": 5,
"statusMessage": "Mycelium framework-guard (dogfood-mode only)"
},
{
"type": "command",
"command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/autonomous-evidence-guard.sh",
"timeout": 5,
"statusMessage": "Mycelium autonomous-evidence-guard (autonomous-mode only)"
},
{
"type": "command",
"command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/absence-claim-guard.sh"
},
{
"type": "command",
"command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/correction-attribution-guard.sh"
}
]
},
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/framework-guard.sh",
"timeout": 5,
"statusMessage": "Mycelium framework-guard (Bash — dogfooWhat 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.
- 3d ago First seen · 104 lines scan A 33904f76542a
PreToolUse is a hook published in the GitHub repository haabe/mycelium (45 stars, last pushed 3d 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 59% identical to SessionStart, differing in 99 lines, and is treated as a copy.
Other hooks, from other repositories
SessionStart
Runs when a session starts, executing context-validation.sh via bash. From mattgierhart/PRD-driven-context-engineering.
SubagentStop
Runs when a subagent finishes, executing subagent-memory-save.sh via bash. From mattgierhart/PRD-driven-context-engineering.
Stop
Runs when the agent finishes a response, executing sot-update-trigger.sh via bash. From mattgierhart/PRD-driven-context-engineering.
PostToolUse
Runs after a tool call finishes for Write and Edit tool calls, executing sot-sync-reminder.sh via bash. From mattgierhart/PRD-driven-context-engineering.
PreToolUse
Runs before the agent uses a tool for Write and Edit tool calls, executing traceability-gate.sh via bash. From mattgierhart/PRD-driven-context-engineering.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing skill-hunter-hook.sh. From mturac/skill-hunter.