task-reviewer

task-reviewer is an agent for Claude Code from unclutter-pro/atlas. It costs 65 tokens per session (246 once invoked), scanned A, original, MIT.

A read-only reviewer that checks a completed non-code task against its stated acceptance criteria. Acceptance criteria are the conditions a result must meet to be considered complete.

In plain words
What is it for?
Verifying research, writing, configuration changes, and other deliverables, then approving them or requesting specific revisions.
Why use it?
It catches missing, inaccurate, or incomplete work before the result is reported to the user.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/unclutter-pro/atlas/task-reviewer
Clone the repo
git clone --depth 1 https://github.com/unclutter-pro/atlas

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 task-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/unclutter-pro/atlas/task-reviewer.svg)](https://agentmods.dev/agents/unclutter-pro/atlas/task-reviewer)
Your own site
<a href="https://agentmods.dev/agents/unclutter-pro/atlas/task-reviewer"><img src="https://agentmods.dev/badge/agents/unclutter-pro/atlas/task-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 246 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00065 $0.00246
Opus 5 $0.00032 $0.00123
Sonnet 5 $0.00013 $0.00049
Haiku 4.5 $0.00006 $0.00025

Measured 3d ago against content hash b307c6ed4bb5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-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 3d 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.

.claude/agents/task-reviewer.md · 37 lines

What it actually says

You are a task reviewer verifying that deliverables meet their acceptance criteria.

Process

  1. Read the original task description and acceptance criteria
  2. Examine the result thoroughly
  3. Verify every criterion is addressed
  4. Make an approve/revise decision

Decision Guidelines

Approve when:

  • All acceptance criteria are met
  • No major gaps or inaccuracies

Request revision when:

  • Acceptance criteria are NOT met
  • Result contains factual errors or significant gaps
  • Critical information is missing

Do NOT request revision for:

  • Minor style preferences
  • Nice-to-have improvements beyond the criteria
  • Theoretical concerns with low probability

Restrictions

  • Read-only — do NOT modify any files
  • Focus only on verifying results against requirements
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. 3d ago First seen · 37 lines · 65 tokens per session scan A b307c6ed4bb5

Subscribe to this mod's changes

task-reviewer is an agent published in the GitHub repository unclutter-pro/atlas (2 stars, last pushed 15d ago), licensed MIT. It adds 65 tokens to every session and 246 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.