Borrowing it
Nothing to install: this file belongs to namastexlabs/automagik-tools. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/namastexlabs/automagik-tools/main/.claude/skills/council-router/SKILL.mdgit clone --depth 1 https://github.com/namastexlabs/automagik-toolsWrote 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/namastexlabs/automagik-tools/council-router)<a href="https://agentmods.dev/skills/namastexlabs/automagik-tools/council-router"><img src="https://agentmods.dev/badge/skills/namastexlabs/automagik-tools/council-router/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/namastexlabs/automagik-tools/council-router"><img src="https://agentmods.dev/badge/skills/namastexlabs/automagik-tools/council-router.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 | $0.00031 | $0.00381 |
| Opus 5.5 | $0.00012 | $0.00152 |
| Sonnet 5.5 | $0.00006 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
council-router 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 1mo 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.
This is a copy
100% identical to council-router — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Council Router
Routes reviews to specialized council members based on code context.
When to Invoke Council
- PR reviews with significant changes
- Architecture decisions or design proposals
- New dependency additions
- Security-sensitive code modifications
- Performance-critical path changes
- API surface changes
Routing Rules
| Context | Route To | Why |
|---|---|---|
| Security-sensitive code (auth, crypto, input validation) | @sentinel | Troy Hunt mindset - security-first |
| Performance-critical paths (hot loops, data processing) | @benchmarker | Matteo Collina - measure everything |
| New dependencies or abstractions | @questioner | Ryan Dahl - challenge assumptions |
| API changes (public interfaces, CLI) | @ergonomist | Sindre Sorhus - DX obsession |
| Deployment configs (Docker, K8s, CI/CD) | @operator, @deployer | Kelsey + Guillermo - ops reality |
| Observability code (logging, metrics, tracing) | @measurer, @tracer | Bryan + Charity - production debugging |
| Architecture decisions (module boundaries, patterns) | @architect | Linus - systems thinking |
| Complex abstractions (over-engineering risk) | @simplifier | TJ - elegant minimalism |
Usage
When a review context matches multiple categories, invoke multiple council members. Each member votes: APPROVE, REJECT, or MODIFY with rationale.
Agent Aliases
All council members are available as Claude agents:
- @questioner, @benchmarker, @simplifier
- @sentinel, @ergonomist, @architect
- @operator, @deployer, @measurer, @tracer
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.
- 1mo ago First seen · 43 lines · 31 tokens per session scan A dfae59e92070
council-router is a skill published in the GitHub repository namastexlabs/automagik-tools (15 stars, last pushed 10mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 381 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to council-router, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
make-pr-easy-to-review
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".
thermo-nuclear-code-quality-review
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…