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.
git clone --depth 1 https://github.com/The01Geek/prflowWrote 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/agents/the01geek/prflow/review-fix-worker)<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.
<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>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 | $0.00033 | $0.02012 |
| Opus 5 | $0.00016 | $0.01006 |
| Sonnet 5 | $0.00007 | $0.00402 |
| Haiku 4.5 | $0.00003 | $0.00201 |
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.
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 thereview-and-fixinvocation to bind itsprogress_surface = workpad; never re-derive implement origin from the public--issueargument, from the workpad's existence, or from PR mode.DRAFT_PR— the Phase 3.1 draft-PR result: anumberand itsdraft_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 literalrun_id/run_attemptfields,TIER, andDEVFLOW_APP_ID. Missing run facts are explicitlyunestablished, never guessed. EchoDISPATCH_ID,run_id, andrun_attemptback in the handoff so the parent rejects a stale or duplicate return.REPO_ROOT,SKILL_DIR,WORKPAD, the workpad invocation ladder, andSCRIPTS. Root every artifact at this checkout. SubstituteSKILL_DIRfor 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 trustedDEVFLOW_PROMPT_EXTENSION_ROOTvalue 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.
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.
- yesterday First seen · 50 lines · 33 tokens per session scan A 1ded685c9a05
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.
Other agents, from other repositories
refactor-cleaner
Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.
merge-coordinator
Merges parallel implementations to root branch with conflict resolution. Spawned by /orc orchestrator after implementation agents complete.
review-coordinator
Elite coordinator for code reviews. Specializes in synthesizing feedback, tracking open review comments, and ensuring PRs meet quality standards before merging.
manifest-curator
Review the actual Claude or Codex manifests, catalogs and pinned revisions against their own schemas. Audit by default; report evidence and uncertainty.
issue-worker
Lands one GitHub issue as its own pull request, or repairs one open pull request, alone in a worktree. Spawned by github-flow:dispatch and github-flow:shift.
changelog
Generates a conventional commit message from the STAGED diff, called by /ship after the commit has been scoped. Summarizes what changed, what files were affected, and why the feature was built (Why comes from the plan file). Output is ready to copy-paste into git commit.