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.
npx skills add fprochazka/claude-code-plugins --skill review-handshakegit clone --depth 1 https://github.com/fprochazka/claude-code-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/fprochazka/claude-code-plugins/review-handshake)<a href="https://agentmods.dev/skills/fprochazka/claude-code-plugins/review-handshake"><img src="https://agentmods.dev/badge/skills/fprochazka/claude-code-plugins/review-handshake/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fprochazka/claude-code-plugins/review-handshake"><img src="https://agentmods.dev/badge/skills/fprochazka/claude-code-plugins/review-handshake.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00119 | $0.01478 |
| Opus 5.5 | $0.00048 | $0.00591 |
| Sonnet 5.5 | $0.00024 | $0.00296 |
| Haiku 4.5 | $0.00012 | $0.00148 |
Grade A, and why
review-handshake 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 25d 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
review-handshake
Two agents share one merge request: the author side, /sdlc:mr-babysit, which changes code, and the reviewer side, /code-review:watch, which never does. They never talk to each other directly. They agree on the state of the MR through the conventions below, and every one of them is read at run time from the MR and the ticket, never from memory.
Whose court the ball is in
The ticket carries the ball. The MR's draft flag says only whether the work was ever handed over.
- The author works. The MR is draft, the ticket is in
WORK_STATE. - The author hands over: the MR is marked ready and the ticket moves to
REVIEW_STATE. Neither side sets the draft flag again, but GitLab may: a push whose commit title starts withfixup!orWIPre-drafts the MR on its own. So marking ready is part of every move toREVIEW_STATE, not only the first, and it is a no-op when the MR is already ready. - The reviewer reviews. Either it comments that all is good and leaves the ticket in
REVIEW_STATE, since approving and merging is a human's decision, or it posts its findings and moves the ticket back toWORK_STATE. It does not touch the draft flag. - The author addresses the feedback, marks the MR ready again in case a push re-drafted it, and moves the ticket back to
REVIEW_STATE. The author side also moves the ticket toWORK_STATEitself when it takes work back after a handover, a red pipeline for example, with a comment saying why.
So ready for review is the ticket in REVIEW_STATE and the MR not draft; back to work is the ticket in WORK_STATE. The one broken state is a draft MR under a ticket in REVIEW_STATE: work that was never handed over, marked as if it were. A command that finds it does not repair it for the other side and does not comment on the mismatch; it waits.
The state names come from the teamwork:workflow-identify skill, resolved once per run and never hardcoded. With tracker: none nothing but the draft flag is left to carry the ball, so it carries it both ways: draft is back to work, ready is ready for review, and the reviewer re-drafts to hand back.
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.
- 25d ago First seen · 58 lines · 119 tokens per session scan A 4076cfa11911
review-handshake is a skill published in the GitHub repository fprochazka/claude-code-plugins (15 stars, last pushed 7d ago), licensed MIT. It adds 119 tokens to every session and 1,478 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-22.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.