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/chachamaru127/claude-code-harness/subagent-startgit clone --depth 1 https://github.com/Chachamaru127/claude-code-harnessGrade A, and why
SubagentStart 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 yesterday.
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
94% identical to PreToolUse — 47 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
{
"SubagentStart": [
{
"matcher": "worker|reviewer|video-scene-generator",
"hooks": [
{
"type": "command",
"command": "/bin/bash -c 'valid_root(){ local r=\"${1:-}\"; [ -n \"$r\" ] && [ -x \"$r/bin/harness\" ] && [ -f \"$r/.claude-plugin/plugin.json\" ] && /usr/bin/grep -q \"\\\"name\\\"[[:space:]]*:[[:space:]]*\\\"claude-code-harness\\\"\" \"$r/.claude-plugin/plugin.json\"; }; root=\"${CLAUDE_PLUGIN_ROOT:-}\"; if ! valid_root \"$root\"; then root=\"\"; for c in \"${CLAUDE_PROJECT_DIR:-}\" \"$PWD\" \"$HOME/.claude/plugins/marketplaces/claude-code-harness-marketplace\" \"$HOME/.claude/plugins/cache/claude-code-harness-marketplace/claude-code-harness/\"*; do if valid_root \"$c\"; then root=\"$c\"; break; fi; done; fi; if ! valid_root \"$root\"; then echo \"[claude-code-harness] plugin root not found; hook skipped\" >&2; exit 0; fi; exec \"$root/bin/harness\" \"$@\"' _ hook subagent-start",
"timeout": 10
}
]
}
]
}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.
- yesterday First seen · 14 lines scan A 9592b652beac
SubagentStart is a hook published in the GitHub repository Chachamaru127/claude-code-harness (3,071 stars, last pushed 2d 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 94% identical to PreToolUse, differing in 47 lines, and is treated as a copy.
Other hooks, from other repositories
SubagentStop
Runs when a subagent finishes, executing subagent-stop.sh. From softspark/ai-toolkit.
SubagentStop
Runs when a subagent finishes, executing cc10x_event_logger.py via python3. From romiluz13/cc10x.
SubagentStop
Runs when a subagent finishes, executing memx-hook.mjs via node. From NeoLi00/memX.
Stop
Runs when the agent finishes a response, executing dag-tripwire.py and ledger-tripwire.py via python3 (2 commands). From Buckeyes22/subagent-model-routing.
SubagentStart
Runs when a subagent starts, executing agent-state-reporter.js via node. From bjornjee/agent-dashboard.
SubagentStop
Runs when a subagent finishes, running an inline shell check. From ArdurAI/ardur.