council-review

council-review is a skill for Claude Code, Codex from strikersam/autonomous-ai-agency. It costs 44 tokens per session (781 once invoked), scanned A, original, MIT.

A multi-review process for checking code changes before they are merged. It asks separate reviewers to examine security, correctness, performance, and maintainability.

In plain words
What is it for?
Use it before merging a pull request, when deciding whether a change is safe to release, or when reviewing a risky module.
Why use it?
It helps reveal risks that one general review may miss, especially in production code or sensitive areas such as authentication, keys, agent tools, and routing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

Good fit Use it before merging a pull request, when deciding whether a change is safe to release, or when reviewing a risky module.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/strikersam/autonomous-ai-agency/council-review
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.

Any agent
npx skills add strikersam/autonomous-ai-agency --skill council-review
Clone the repo
git clone --depth 1 https://github.com/strikersam/autonomous-ai-agency

Made for: Claude Code, Codex.

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 council-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/council-review/github.svg)](https://agentmods.dev/skills/strikersam/autonomous-ai-agency/council-review)
Your own site
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/council-review"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/council-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.

agentmods 80×15 button for council-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/council-review"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/council-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 781 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00044 $0.00781
Opus 5 $0.00022 $0.00391
Sonnet 5 $0.00009 $0.00156
Haiku 4.5 $0.00004 $0.00078

Measured 12d ago against content hash e9e1bdcf23d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

council-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 12d 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/skills/council-review/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: council-review

When to Use

Use this skill:

  • Before merging any PR that changes production code
  • When asked "is this safe?" or "can this go out?"
  • After a self-review that feels uncertain
  • For any change to risky modules (auth, keys, agent tools, routing)

Instructions

Step 1 — Gather the diff

git diff main...HEAD                    # all changes vs main
git diff --stat main...HEAD             # file summary

Step 2 — Run each reviewer role independently

For each role below, read the diff and answer the questions for that role. Record findings in a structured review comment.


Role 1: Security Reviewer

Questions to answer:

  • Does this change introduce or weaken an auth check?
  • Are any secrets, tokens, or API keys potentially exposed?
  • Does any new code accept untrusted input without validation?
  • Are file paths sanitized? (especially in agent/tools.py)
  • Does any new dependency introduce a known CVE?

Role 2: Correctness Reviewer

Questions to answer:

  • Does the implementation match the stated goal?
  • Are edge cases handled (empty input, None, zero, very long strings)?
  • Are error conditions propagated correctly?
  • Would any existing test fail after this change?
  • Are there any off-by-one errors, race conditions, or type mismatches?

Role 3: Performance Reviewer

Questions to answer:

  • Does this change add any blocking I/O on the async path?
  • Are there any N+1 query or repeated expensive computation patterns?
  • Does any new loop run on every request?
  • Is caching appropriate? (especially for health checks, model registry)

Role 4: Maintainability Reviewer

Questions to answer:

  • Is the code readable without inline explanation?
  • Are variable names clear?
  • Are new abstractions justified or is this over-engineering?
  • Does this add duplication that should be shared?
  • Is the module boundary respected? (don't let routing logic leak into proxy.py)

Step 3 — Produce a council verdict

Read the full file on GitHub · 121 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. 12d ago First seen · 121 lines · 44 tokens per session scan A e9e1bdcf23d2

Subscribe to this mod's changes

council-review is a skill published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 781 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 2026-08-31.