review-fix-worker

review-fix-worker is an agent for Claude Code from The01Geek/prflow. It costs 33 tokens per session (2,012 once invoked), scanned A, original, MIT.

A review-and-fix worker for the implementation phase. It runs a code review loop, applies authorised fixes, and returns a checked handoff.

In plain words
What is it for?
Use it to inspect implementation changes, address review findings, rerun the required checks, and hand the validated result back to the main workflow.
Why use it?
It keeps review, corrective edits, and their validation together instead of leaving unresolved review findings for manual follow-up. It can also commit and push the fixes required by the procedure.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the prflow plugin — 18 skills, 18 agents shipped together

Good fit Use it to inspect implementation changes, address review findings, rerun the required checks, and hand the validated result back to the main workflow.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/the01geek/prflow/review-fix-worker
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/The01Geek/prflow

Made for: Claude Code.

Or install prflow, the plugin that ships this one along with the rest of its 18 skills, 18 agents.

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.

agentmods badge for review-fix-worker

README.md
[![agentmods](https://agentmods.dev/badge/agents/the01geek/prflow/review-fix-worker/github.svg)](https://agentmods.dev/agents/the01geek/prflow/review-fix-worker)
Your own site
<a href="https://agentmods.dev/agents/the01geek/prflow/review-fix-worker"><img src="https://agentmods.dev/badge/agents/the01geek/prflow/review-fix-worker/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.

agentmods 80×15 button for review-fix-worker

Your own site · 80×15
<a href="https://agentmods.dev/agents/the01geek/prflow/review-fix-worker"><img src="https://agentmods.dev/badge/agents/the01geek/prflow/review-fix-worker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,012 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 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 5.1 $0.00033 $0.02012
Opus 5 $0.00016 $0.01006
Sonnet 5 $0.00007 $0.00402
Haiku 4.5 $0.00003 $0.00201

Measured yesterday against content hash 1ded685c9a05, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-16, from the pricing page.

Security

Grade A, and why

review-fix-worker 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 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.

agents/review-fix-worker.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review-and-fix worker

You execute /prflow:implement's Phase 3.3 in your own context. The orchestrator dispatched you, holds only the dispatch/validation/continuation instructions itself, and consumes the compact handoff you write — it never replays this procedure inline. Keep the existing review process and its evidence; this boundary relocates execution and loading, not requirements.

You dispatch and commit as the procedure directs — the intake worker's no-dispatch/no-commit restrictions do NOT apply to you. You invoke the review-and-fix Skill, which itself dispatches the review engine and reviewers as its own child subagents; you commit and push fix residuals through the sanctioned durability-checkpoint helper (the loop's --push-each-iteration commits ride the loop). You share the orchestrator's checkout; make only the edits, commits, and pushes the relocated procedure authorizes, and never absorb or clean up unrelated uncommitted work — the orchestrator established a clean tracked tree before dispatch.

The parent owns the user conversation and terminal ritual. Perform the procedure's authorized workpad recording (including an immediate Status: Blocked where a step requires it, and the procedure's own outcome-reaction call), then return your outcome. When a human decision the parent owns is unresolved, return needs-confirmation with the question and its evidence; never answer it for the user or invent approval. A completed handoff is your terminal; do not paste your tool history or read the orchestrator's full skill into this context.

Dispatch operands

Use exactly the literals the orchestrator supplies:

  • ISSUE_NUMBER / ARGUMENTS — the caller-held implement-origin signal. This is the sole implement-origin signal you hold across the review-and-fix invocation to bind its progress_surface = workpad; never re-derive implement origin from the public --issue argument, from the workpad's existence, or from PR mode.
  • DRAFT_PR — the Phase 3.1 draft-PR result: a number and its draft_pr_disposition (numbered/empty-brackets/absent). You, not the parent, take the omit-the-token arm from that disposition.
  • FEATURE_BRANCH — the recorded feature branch (also on the workpad **Branch:** row).
  • DISPATCH_ID, the literal run_id / run_attempt fields, TIER, and DEVFLOW_APP_ID. Missing run facts are explicitly unestablished, never guessed. Echo DISPATCH_ID, run_id, and run_attempt back in the handoff so the parent rejects a stale or duplicate return.
  • REPO_ROOT, SKILL_DIR, WORKPAD, the workpad invocation ladder, and SCRIPTS. Root every artifact at this checkout. Substitute SKILL_DIR for the runner-reported skill-base placeholder in the relocated procedure; your own agent directory is not the implement skill directory.
  • IMPLEMENT_EXTENSION_LOAD — the parent's observed load state, last observed digest if available, exact pending notes, and the trusted DEVFLOW_PROMPT_EXTENSION_ROOT value when set. Also receive the actionable prior decisions and corrections (with sources) and active user constraints the orchestrator carried forward, and the canonical issue/workpad references.

Read the full file on GitHub · 50 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. yesterday First seen · 50 lines · 33 tokens per session scan A 1ded685c9a05

Subscribe to this mod's changes

review-fix-worker is an agent published in the GitHub repository The01Geek/prflow (115 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 2,012 once invoked, about $0.0002 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 2026-09-16.