watch

A command that reviews a branch’s merge request, posts findings, and keeps checking it on a schedule until issues are fixed or answered. A merge request is a proposed code change awaiting review.

In plain words
What is it for?
Use it to review merge requests, hand work back to the author, wait for a new ready state, revisit open discussions, and check later changes.
Why use it?
It coordinates repeated review rounds and avoids reviewing work while it is still being changed.

Command

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 commands/fprochazka/claude-code-plugins/watch
Clone the repo
git clone --depth 1 https://github.com/fprochazka/claude-code-plugins
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,768 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.07768
Opus 5 $0.00013 $0.03884
Sonnet 5 $0.00005 $0.01554
Haiku 4.5 $0.00003 $0.00777

Measured 2d ago against content hash 461c09d1a1fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

watch 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 body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

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.

plugins/code-review/commands/watch.md · 413 lines

How it starts

The opening of the file, as written. The whole thing — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Watch the MR Until the Review Is Settled

Run a full code review of the current branch's merge request, post it, hand the work back to the author, and then watch on a schedule until every blocking finding and every suggestion has been addressed in code or refuted with a reply.

The handshake invariant. Ready-for-review means the MR is not draft AND the ticket is in REVIEW_STATE. Back-to-work means the MR is draft AND the ticket is in WORK_STATE. The two flags always move together. Whoever hands the ball over sets both.

That is what paces this command. After posting a round of findings, hand the work back — ticket to WORK_STATE, MR to draft. Only when both flags say ready-for-review again does the next round run. This keeps the review out of work-in-progress instead of commenting on every half-finished push.

review → post → ticket to WORK_STATE + MR to draft → [wait]
   → author sets MR ready + ticket to REVIEW_STATE
   → sync the local branch onto the author's new head
   → revisit every open thread, reply, resolve what is settled
   → review the delta, post new findings
   → anything still open? ticket to WORK_STATE + MR to draft, wait again
   → nothing open? leave it ready in REVIEW_STATE and stop

This command is the reviewer side of an MR. It is the mirror image of /sdlc:mr-babysit, which is the author side. The distinction matters and is enforced below: this command never edits, commits, pushes, or rebases locally, and never resolves the author's threads.

$ARGUMENTS

Stance — you are the reviewer, not the author

For the whole lifetime of this command, including every cron pass:

  • Never change the code. No Edit, no Write into the repo, no git commit, no git push, no local git rebase, no git checkout of a different branch, no stash. If a finding has an obvious fix, describe it in the comment. Do not apply it.
  • Never resolve a thread the author opened. You may resolve your own finding threads, and only once you have verified in the diff that the finding is genuinely addressed.
  • Never promise anything on the MR. Comment bodies state findings, facts, verification results, and open questions. They do not say "we will fix", "a follow-up is coming", "this will be improved", or any softer paraphrase. If a fix belongs in the picture, describe it as an option in the comment and raise the commitment question with the user in the conversation instead.

Read the full file on GitHub · 413 lines

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 · 413 lines · 26 tokens per session scan A 461c09d1a1fa

Subscribe to this mod's changes

watch is a command published in the GitHub repository fprochazka/claude-code-plugins (11 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 7,768 once invoked, about $0.0001 per session on Opus 5. 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.