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.
npx skills add zgbrenner/agentcounsel --skill ai-feature-reviewgit clone --depth 1 https://github.com/zgbrenner/agentcounselWrote 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/skills/zgbrenner/agentcounsel/ai-feature-review)<a href="https://agentmods.dev/skills/zgbrenner/agentcounsel/ai-feature-review"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/ai-feature-review/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/skills/zgbrenner/agentcounsel/ai-feature-review"><img src="https://agentmods.dev/badge/skills/zgbrenner/agentcounsel/ai-feature-review.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 | $0.00036 | $0.02961 |
| Opus 5 | $0.00018 | $0.01481 |
| Sonnet 5 | $0.00007 | $0.00592 |
| Haiku 4.5 | $0.00004 | $0.00296 |
Grade A, and why
AI Feature Review 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Feature Review
Purpose
Produce a structured, attorney-ready legal issues register for a product feature that uses artificial intelligence or machine learning. This skill spots legal exposure across training-data rights, output ownership and infringement, transparency and disclosure obligations, privacy and data use, automated-decision concerns, vendor terms, and high-risk use cases. It routes AI-vendor contract questions to ai-vendor-terms-review and broader AI risk triage to model-risk-triage. It produces draft legal work product for attorney review — not legal advice, not a regulatory clearance, and not a determination that the feature is lawful.
Use When
- A team is building, shipping, or updating a feature that uses an AI model, machine learning system, or algorithmic decision-making component.
- A product manager, engineer, or counsel asks to "review the legal risks of this AI feature," "check if we can use this model," or "what do we need to disclose?"
- A launch review (see
launch-review) has flagged an AI or algorithmic component for deeper analysis. - An existing AI feature is being modified in a material way: new model, new data inputs, new output use case, or new user population.
- The feature involves a vendor-supplied AI model and the team needs a legal issues overview before completing vendor contracting (route contract detail to
ai-vendor-terms-review). - The feature involves automated decisions that affect users in consequential ways (credit, employment, health, housing, content moderation, pricing).
Required Inputs
- Feature description: what the feature does, how users interact with it, and what is new or changed.
- Model(s) used: whether the model is in-house (trained or fine-tuned internally) or vendor-supplied (API, embedded, or licensed). Include model name or vendor name if known.
- Training and input data: what data was used to train or fine-tune the model (if in-house), and what data the model receives at inference time (user inputs, uploaded files, third-party data, etc.).
- Outputs and how they are used: what the model produces (text, images, scores, classifications, recommendations, decisions), and how those outputs are displayed to or acted upon by users or internal systems.
- User-facing disclosures: what, if anything, the product currently discloses to users about AI use, automated decision-making, or the nature of the outputs.
- Human-oversight design: whether and how a human reviews, approves, or can override AI outputs before they affect users.
- Target markets and users: geographies, user demographics, and any vulnerable populations (minors, patients, financial consumers, job seekers).
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.
- 9d ago First seen · 151 lines · 36 tokens per session scan A b36fb50f119f
AI Feature Review is a skill published in the GitHub repository zgbrenner/agentcounsel (19 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 2,961 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 2026-09-03.
Other skills, from other repositories
policy
Define and enforce decision policies, compliance rules, and exceptions over Semantica graphs. Uses ContextGraph.checkdecisionrules/enforcedecisionpolicy and context.PolicyEngine.
801-regulations-eu-ai-act
Use when reviewing, designing, or modifying Java enterprise systems that use AI, LLMs, AI agents, RAG, tool calling, workflow automation, or model-based decision support and need EU AI Act regulatory awareness. This should trigger for requests such as Review a Java AI system for EU AI Act controls; Design governance…
813-regulations-iso-42001
Use when reviewing, designing, or modifying Java enterprise systems that use GenAI, LLMs, AI-assisted coding, RAG, AI agents, generated code, generated dependencies, prompt workflows, external model providers, or AI-enabled business logic and need ISO/IEC 42001 AI management system-aware engineering guidance. Part of…
ai-privacy-assessment
Guides the combined DPIA and AI Act conformity assessment for AI systems processing personal data. Covers EDPB-EDPS Joint Opinion 5/2021, training data lawfulness under Art. 6 and Art. 9, Art. 22 automated decision-making, algorithmic bias detection, and NIST AI RMF MAP function. Keywords: AI privacy, DPIA, AI Act…
runtime-admissibility-review
Determines whether a specific AI-agent action, output, recommendation, or proposed commitment remains admissible for execution or institutional reliance under current authority, delegated scope, evidence, facts, policy, risk, escalation, and revocation conditions. Use this Skill before an enterprise or regulated AI…
agent-authority-charter-builder-arkadiy-miteiko
Creates an Agent Authority Charter for enterprise or regulated AI agents before deployment. Use this Skill when a user needs to define what an AI agent is allowed to do, who delegated authority to it, what actions are permitted or prohibited, when human approval is required, what evidence must be preserved, and how…