agentmods.dev

SubagentStart

An automated check that runs when a collaboration subagent starts. It starts a Python script supplied by the collaboration setup.

In plain words
What is it for?
It helps attach startup processing to subagents whose tool calls use the collab- prefix.
Why use it?
It provides a consistent point for preparing or recording the start of work by a delegated agent.

Hook

2 1mo ago A scan tokens not measured original MIT
View the source file AgentBuildersApp/eight-eyes
Install

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.

agentmods
npx agentmods add hooks/agentbuildersapp/eight-eyes/subagent-start
Clone the repo
git clone --depth 1 https://github.com/AgentBuildersApp/eight-eyes
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade 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 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.

hooks/hooks.json · 13 lines

What it actually says

{
  "SubagentStart": [
    {
      "matcher": "collab-",
      "hooks": [
        {
          "type": "command",
          "command": "python3 ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/collab_subagent_start.py"
        }
      ]
    }
  ]
}
Changes

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.

  1. 2d ago First seen · 13 lines scan A 5b42f5d395e9

Subscribe to this mod's changes

SubagentStart is a hook published in the GitHub repository AgentBuildersApp/eight-eyes (2 stars, last pushed 1mo 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 2026-08-31.

Building agentsCode reviewLanguagesai-code-reviewclaude-codecodex-clicopilot-clidefense-in-depth
Related

Other hooks, from other repositories

UserPromptSubmit

Runs when you submit a prompt, before the agent sees it, executing behavior-feedback.sh, prompt-submit.sh and subagent-stance.sh (3 commands). From tdwhere123/do-it.

tdwhere123/do-it · not measured

SubagentStart

Runs when a subagent starts, executing stop-that-shit-claude.cjs via node. From lennney/stop-that-shit.

lennney/stop-that-shit · not measured

SubagentStart

Runs when a subagent starts, running an inline shell check. From goondocks-co/open-agent-kit.

goondocks-co/open-agent-kit · not measured

SubagentStop

Runs when a subagent finishes, running an inline shell check. From goondocks-co/open-agent-kit.

goondocks-co/open-agent-kit · not measured

SubagentStart

Runs when a subagent starts for ^(prewalk:)?prewalk-executor$ tool calls, executing handoff_lifecycle.py via python3. From TerenceLiu98/prewalk.

TerenceLiu98/prewalk · not measured

SubagentStop

Runs when a subagent finishes for ^(prewalk:)?prewalk-executor$ tool calls, executing handoff_lifecycle.py via python3. From TerenceLiu98/prewalk.

TerenceLiu98/prewalk · not measured