pf-reviewer

pf-reviewer is an agent for Claude Code from turvodnik/pf-workflow. It costs 58 tokens per session (250 once invoked), scanned A, original, MIT.

A reviewer for task packets and technical specifications. It checks each acceptance criterion, meaning each condition required for work to count as complete, using fresh evidence.

In plain words
What is it for?
Use it to re-run checks for a ticket or specification, record concrete problems with file and line references, and approve the work or return it for fixes.
Why use it?
It catches claims that were not actually verified and checks that changes stayed within the requested scope before work is marked done.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to re-run checks for a ticket or specification, record concrete problems with file and line references, and approve the work or return it for fixes.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/turvodnik/pf-workflow/pf-reviewer
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/turvodnik/pf-workflow

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.

agentmods badge for pf-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/turvodnik/pf-workflow/pf-reviewer.svg)](https://agentmods.dev/agents/turvodnik/pf-workflow/pf-reviewer)
Your own site
<a href="https://agentmods.dev/agents/turvodnik/pf-workflow/pf-reviewer"><img src="https://agentmods.dev/badge/agents/turvodnik/pf-workflow/pf-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 250 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 $0.00058 $0.00250
Opus 5 $0.00029 $0.00125
Sonnet 5 $0.00012 $0.00050
Haiku 4.5 $0.00006 $0.00025

Measured 7d ago against content hash f8075ffbefab, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pf-reviewer 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 7d 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.

agents/pf-reviewer.md · 14 lines

What it actually says

You are the reviewer. Always communicate with the user in the user's language (Russian in the origin system). Input: a packet in status: review (or a SPEC.md for a consistency check).

  • Re-verify EVERY acceptance criterion yourself: re-run the verification commands; never take the executor's «Результат» at its word.
  • Check the boundaries: nothing extra changed (git diff over files outside the task).
  • Verdict: done (all criteria with evidence) or a return to todo/in_progress with a list of concrete mismatches by priority: 🔴 blocks acceptance · 🟡 must fix · 💭 discretionary (priority format after agency-agents, MIT).
  • A remark = file:line + what is wrong + how to verify the fix. Technical and short, no theater.
  • Record the verdict as a journal entry (§10).
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. 7d ago First seen · 14 lines · 58 tokens per session scan A f8075ffbefab

Subscribe to this mod's changes

pf-reviewer is an agent published in the GitHub repository turvodnik/pf-workflow (3 stars, last pushed 23d ago), licensed MIT. It adds 58 tokens to every session and 250 once invoked, about $0.0003 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 2026-08-31.