Stop

A group of automatic checks that run when the coding agent finishes a response. The checks inspect formatting and types, validate changelog entries, and require evidence from another agent before declaring a merge ready.

In plain words
What is it for?
Use it to run end-of-response type and format checks, check changelog entries, and enforce evidence requirements for merge decisions.
Why use it?
It catches common quality and release-record problems after edits are made. It also prevents a merge-ready result when required review work was skipped.

Hook

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/koroqe/claude-code-sdlc/stop
Clone the repo
git clone --depth 1 https://github.com/Koroqe/claude-code-sdlc
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

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 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 · 29 lines

What it actually says

{
  "Stop": [
    {
      "hooks": [
        {
          "id": "stop:typecheck-format",
          "type": "command",
          "description": "Runs the project's declared format and typecheck commands once over everything edited this response. No-ops visibly when the project declares no such command.",
          "command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/lib/run-hook.js\" --hook stop:typecheck-format",
          "timeout": 180
        },
        {
          "id": "stop:changelog-guard",
          "type": "command",
          "description": "Checks the shape of a changelog entry written this response, and that it is not a duplicate under today.",
          "command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/lib/run-hook.js\" --hook stop:changelog-guard",
          "timeout": 20
        },
        {
          "id": "stop:gate-evidence",
          "type": "command",
          "description": "Blocks a MERGE READY verdict in a session where no subagent ever ran. Every other guard fires on an action taken; this is the only one that can fire on a step that was skipped, because an omission produces no tool call to intercept. Narrow by design: it asserts one unambiguous thing rather than guessing which gate mapped to which agent.",
          "command": "node \"${CLAUDE_PLUGIN_ROOT}/hooks/lib/run-hook.js\" --hook stop:gate-evidence",
          "timeout": 10
        }
      ]
    }
  ]
}
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 · 29 lines scan A d02c3b78f12e

Subscribe to this mod's changes

Stop is a hook published in the GitHub repository Koroqe/claude-code-sdlc (51 stars, last pushed 4d 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 2026-08-30.