agentmods.dev

Stop

A stop hook that runs a shell command when the coding agent finishes responding. A hook is an automated action attached to a particular event.

In plain words
What is it for?
Use it to run the configured backchannel check when the agent stops.
Why use it?
It provides a way to perform a final check or notification automatically at the end of each response.

Hook

1 1mo ago A scan tokens not measured copy · 56% MIT
View the source file j-ronk/backchannel
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/j-ronk/backchannel/stop
Clone the repo
git clone --depth 1 https://github.com/j-ronk/backchannel
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 56% copy Near-identical to another mod in the catalogue.
Security

Grade 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 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.

Origin

This is a copy

56% identical to SessionStart — 7 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.

client/hooks/hooks.json · 12 lines

What it actually says

{
  "Stop": [
    {
      "hooks": [
        {
          "type": "command",
          "command": "\"${CLAUDE_PLUGIN_ROOT}/bin/backchannel\" onstop"
        }
      ]
    }
  ]
}
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. yesterday First seen · 12 lines scan A 8fc49d8b3b71

Subscribe to this mod's changes

Stop is a hook published in the GitHub repository j-ronk/backchannel (1 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. It is 56% identical to SessionStart, differing in 7 lines, and is treated as a copy.

CollaborationDevOps and cloudai-agentsaws-cdkclaude-codeclaude-code-pluginend-to-end-encryption
Related

Other hooks, from other repositories

SessionEnd

Runs when a session ends, executing session-log.sh, transcript-archive.sh, loom.sh and session-autosave.sh with --quiet (4 commands). From egregore-labs/egregore.

egregore-labs/egregore · not measured

WorktreeRemove

Runs when a git worktree is removed, executing worktree-remove.sh. From egregore-labs/egregore.

egregore-labs/egregore · not measured

PostToolUse

Runs after a tool call finishes for Write, Edit and Bash tool calls, executing post-merge-sync-reminder.sh, main-tree-dirty-detector.sh and main-tree-git-cwd-detector.sh (4 commands). From go-to-k/cdkd.

go-to-k/cdkd · not measured

PreCompact

Runs before the context is compacted, running an inline shell check. From go-to-k/cdkd.

go-to-k/cdkd · not measured

PreToolUse

Runs before the agent uses a tool for Read, Edit, Write, Bash, Glob, Grep, Edit, Write, Bash, EnterWorktree, EnterPlanMode, Edit, Write, Bash, EnterPlanMode, Bash and Bash tool calls, executing boundary-check.sh, onboarding-guard.sh, branch-guard.sh, infra-hint.sh and release-guard.sh (5 commands). From…

egregore-labs/egregore · not measured

Stop

Runs when the agent finishes a response, executing stop-warn.sh and stop-unmerged-lane-warn.sh (2 commands). From go-to-k/cdkd.

go-to-k/cdkd · not measured