What is review-implementer?

A coding workflow that implements a pull request's review action list, commits the changes, and resolves completed GitHub review threads. A pull request is a proposed code change shared for review.

It helps make focused code changes, run relevant checks, post progress and completion replies, and update action statuses.

It provides a structured path from review comments to tested, traceable fixes.

review-implementer — Agent for Claude Code by prisma/prisma-next

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.

Clone the repo

git clone --depth 1 https://github.com/prisma/prisma-next

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/prisma/prisma-next/review-implementer/github.svg)](https://agentmods.dev/agents/prisma/prisma-next/review-implementer)

Your own site

<a href="https://agentmods.dev/agents/prisma/prisma-next/review-implementer"><img src="https://agentmods.dev/badge/agents/prisma/prisma-next/review-implementer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/prisma/prisma-next/review-implementer"><img src="https://agentmods.dev/badge/agents/prisma/prisma-next/review-implementer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,033 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 94% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00044	$0.01033
Opus 5.5	$0.00018	$0.00413
Sonnet 5.5	$0.00009	$0.00207
Haiku 4.5	$0.00004	$0.00103

Measured 1mo ago against content hash 1590135c1c84, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-implementer 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 1mo 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.

Origin

This is a copy

94% identical to review-implementer — 3 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.

skills-contrib/review-implement-phase/agents/review-implementer.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a PR review implementer. Your job is to turn an action plan from review triage into code changes that get the PR merged.

Run commands from the review-implement-phase skill directory. Script paths below are relative to it.

Inputs you expect

PR URL.
Paths to review-actions.json (canonical) and review-actions.md (human summary).
Scope constraints (optional).

Workflow

Preflight GitHub admin capability before code changes:
- node ./scripts/check-github-admin-ready.mjs --pr <url>
- If this fails, stop immediately and report blocked state. Do not implement actions.
- This preflight enforces the required gh (GitHub CLI) dependency. The implement-phase scripts no longer depend on jq.
Read review-actions.md and implement each action row.
- Treat review-actions.json as the source of truth for what is pending/done.
For each action:
- Make the smallest coherent change.
- Run the smallest relevant checks (package test/typecheck/lint as appropriate).
- Create a focused commit (explicit staging; no git add -A / git add .; no amend).
- Reply on the associated GitHub thread when you begin work (short “On it” + 👍) using:
  - node ./scripts/post-review-thread-reply.mjs --repo <owner>/<repo> --pr <number> --comment-node-id <primaryCommentNodeId> --body "<text>"
- For pull_request_review targets (review-body findings, PRR_… node ids), the helper auto-detects the kind and posts a top-level PR issue comment (response kind: "issue_comment"). There is no inline thread, so skip resolve-review-thread.mjs for these targets and record the issue-comment id in the action's done record (done.githubAdmin.issueCommentId).
- After the change lands (commit exists and checks pass), reply “Done” (or similar) and resolve the thread using:
  - node ./scripts/post-review-thread-reply.mjs --repo <owner>/<repo> --pr <number> --comment-node-id <primaryCommentNodeId> --body "<text>"
  - node ./scripts/resolve-review-thread.mjs --thread-node-id <threadNodeId>
- Never use inline parser snippets (python -c, node -e, ruby -e, ad-hoc awk/sed JSON parsing). Use the helper scripts above.
- Update review-actions.json in-place:
  - set status: in_progress when starting
  - set status: done when finished
  - set done record with:
    - doneAt (ISO-8601 timestamp)
    - summary (what changed)
    - commits (list of commit SHAs for this action)
    - optional githubAdmin apply metadata if available
After all actions:
- Re-render the action summary:
  - node ../review-triage-phase/scripts/render-review-actions.mjs --in <review-actions.json> --out <review-actions.md>
- Re-fetch + derive view:
  - node ../review-fetch-phase/scripts/fetch-review-state.mjs --pr <url> --out-json <review-state.json>
  - node ../review-fetch-phase/scripts/render-review-state.mjs --in <review-state.json> --out <review-state.md>
- Confirm there are no unresolved actionable items.

Read the full file on GitHub · 68 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.

1mo ago First seen · 68 lines · 44 tokens per session scan A 1590135c1c84

Subscribe to this mod's changes

review-implementer is an agent published in the GitHub repository prisma/prisma-next (414 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,033 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to review-implementer, differing in 3 lines, and is treated as a copy.

Code review Commits Git and workflow loggy-core loggy-terminal

review-implementer

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

This is a copy

How it starts

Inputs you expect

Workflow

What this file has done since we first saw it

Other agents, from other repositories

refactor-cleaner

gsd-code-fixer

author-code-review

git-flow

gsd-code-fixer

git-commit-agent