agentmods.dev

Stop

A completion hook that runs a shell script after the agent finishes a response to check for differences between the project and its README.

In plain words
What is it for?
Use it to run check-readme-drift.sh automatically at the end of an agent response.
Why use it?
It can reveal documentation drift—when the README no longer matches the code or project state—after work is completed.

Hook for Claude Code

4 1mo ago A scan tokens not measured copy · 45% MIT
View the source file osouthgate/agent-plus
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/osouthgate/agent-plus/stop
Clone the repo
git clone --depth 1 https://github.com/osouthgate/agent-plus

Made for: Claude Code.

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 45% 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

45% 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.

.claude/settings.json · 12 lines

What it actually says

{
  "Stop": [
    {
      "hooks": [
        {
          "type": "command",
          "command": "bash $CLAUDE_PROJECT_DIR/.claude/hooks/check-readme-drift.sh"
        }
      ]
    }
  ]
}
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 1de3b831a424

Subscribe to this mod's changes

Stop is a hook published in the GitHub repository osouthgate/agent-plus (4 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 45% identical to SessionStart, differing in 7 lines, and is treated as a copy.

LanguagesWriting and docsagent-toolsclaude-codeclaude-code-pluginclipython
Related

Other hooks, from other repositories

SubagentStart

Runs when a subagent starts, executing writ-subagent-start.sh via bash. From infinri/Writ.

infinri/Writ · not measured

PostToolUse

Runs after a tool call finishes for Bash, WebFetch, WebSearch, Write, Edit, Write, Edit, Write, Edit, Write, Edit, Write, Edit, NotebookEdit, Write, Write, Edit, Write and Edit tool calls, executing inject-tier-workflow.sh, writ-web-capture.sh, validate-file.sh, writ-bible-authoring-push.sh, validate-handoff.sh…

infinri/Writ · not measured

PreToolUse

Runs before the agent uses a tool for ExitPlanMode, Read, Read, Grep, Read, Glob, Write, Edit, NotebookEdit, Write, Edit, NotebookEdit, Write, Edit, Task, Bash, Bash, Write, Write and Write tool calls, executing validate-exit-plan.sh, writ-read-junk-gate.sh, writ-read-rag.sh, writ-debug-code-gate.sh…

infinri/Writ · not measured

SubagentStop

Runs when a subagent finishes, executing writ-blackbox-capture.sh and writ-subagent-stop.sh via bash (2 commands). From infinri/Writ.

infinri/Writ · not measured

PostToolUseFailure

Runs when a tool call fails, executing writ-blackbox-capture.sh via bash. From infinri/Writ.

infinri/Writ · not measured

PreCompact

Runs before the context is compacted, executing writ-precompact.sh via bash. From infinri/Writ.

infinri/Writ · not measured