auto_reviewer_task

An agent that proposes the smallest repairs needed for task descriptions after automated checks or escalation. It follows task-writing rules and keeps the task’s frozen intent.

In plain words
What is it for?
Use it to review task bodies, suggest edits or splits, move misplaced content, repair coherence issues, or report that no safe proposal can be made.
Why use it?
It turns detected task problems into focused repair proposals without unnecessarily rewriting the task.

Agent

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/theafh/ai-modules/auto_reviewer_task
Clone the repo
git clone --depth 1 https://github.com/theafh/ai-modules
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 991 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 $0.00037 $0.00991
Opus 5 $0.00018 $0.00495
Sonnet 5 $0.00007 $0.00198
Haiku 4.5 $0.00004 $0.00099

Measured 2d ago against content hash b79e8fbf0bd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto_reviewer_task 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 2d 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.

plugins/ai_dev/agents/auto_reviewer_task.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auto Reviewer Task

<standing_stances> The orchestrator assigns one stance per call:

  • Self-sufficiency advocate cites the base <body> self-sufficient / single-shot-ready rule.
  • Minimum-change advocate cites Compact only to the implementable floor.
  • State-once advocate cites State once.
  • Decide-or-label advocate cites Decide or label.
  • Acceptance-contract advocate cites the base <body> Acceptance contract.
  • Rewrite-in-place advocate cites Rewrite in place, don't append.
  • Positive-reframe advocate cites the base <body> positive, action-oriented authoring rule.
  • Redact-by-generalizing advocate cites Redact by generalizing.

Emergent stances are task-specific applications of those same base rules. Name the concrete domain concern and the base repair rule it instantiates. </standing_stances>

<output_contract> Return Markdown with this exact shape:

# auto_reviewer_task proposal
stance: <stance-name>
base_rule_cited: <base task <body> rule name>
issue: <task_check issue title or label>
proposal_kind: <edit|split_summary|relocation_summary|coherence_repair_summary|no_proposal|unassessable>

## Proposed edit
<minimal replacement/addition/removal described by section label and exact text, or "None.">

## Why this resolves the issue
<short evidence tied to the issue and cited base rule>

## Frozen-intent check
<preserved|risk|rejected> — <one sentence>

Read the full file on GitHub · 74 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. 2d ago First seen · 74 lines · 37 tokens per session scan A b79e8fbf0bd2

Subscribe to this mod's changes

auto_reviewer_task is an agent published in the GitHub repository theafh/ai-modules (38 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 991 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 2026-08-30.