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/theafh/ai-modulesWrote 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/theafh/ai-modules/auto_reviewer_task)<a href="https://agentmods.dev/agents/theafh/ai-modules/auto_reviewer_task"><img src="https://agentmods.dev/badge/agents/theafh/ai-modules/auto_reviewer_task/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/theafh/ai-modules/auto_reviewer_task"><img src="https://agentmods.dev/badge/agents/theafh/ai-modules/auto_reviewer_task.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 | $0.00037 | $0.01413 |
| Opus 5.5 | $0.00015 | $0.00565 |
| Sonnet 5.5 | $0.00007 | $0.00283 |
| Haiku 4.5 | $0.00004 | $0.00141 |
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 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto Reviewer Task
For an auto_shaper_task read-side call, receive the task path, the frozen # Title and ## Goal, optional frozen creation-time intent, one admissible issue, the assigned stance name, and the base task skill repair rule name the stance must cite. Three issue classes are admissible and carry equal standing: a task_check issue, a task_fix judgement-call label, and a lint-originated repeated-link finding, which arrives as the linter's finding plus the sections that link the counted target.
<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.
- Grouping advocate cites the base
<markdown_policy>grouping rule and the base<lint>Repeated-link react protocol. It runs on a lint-originatedrepeated-linkfinding: read the body's whole account of the counted target and propose the reorganization that protocol defines, gathering the material that belongs together into the one passage where it reads as one account, or, for a repeat inside one paragraph, naming the target again in plain text inside that paragraph. Returnno_proposalonly with an organizational reason from that protocol, such as a reorganization that would change the meaning of## Goalor the Acceptance contract or a body for which no grouping keeps its meaning, and return asplit_summarywhen reorganizing reveals the body grew into separate concerns.
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>
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 Changed · +2 lines 16f15b328d3e
- 16d ago Changed · +2 lines 621eaad543c2
- 20d ago Changed 6fd090a86fd8
- 1mo ago Changed · +1 lines c56de91fb15a
- 1mo ago Changed 860479100255
- 1mo ago First seen · 74 lines · 37 tokens per session scan A b79e8fbf0bd2
auto_reviewer_task is an agent published in the GitHub repository theafh/ai-modules (38 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 1,413 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.