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 alonbaron/claude-skills --skill ask-the-councilgit clone --depth 1 https://github.com/alonbaron/claude-skillsWrote 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/alonbaron/claude-skills/ask-the-council)<a href="https://agentmods.dev/skills/alonbaron/claude-skills/ask-the-council"><img src="https://agentmods.dev/badge/skills/alonbaron/claude-skills/ask-the-council/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/alonbaron/claude-skills/ask-the-council"><img src="https://agentmods.dev/badge/skills/alonbaron/claude-skills/ask-the-council.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 | $0.00051 | $0.01329 |
| Opus 5.5 | $0.00020 | $0.00532 |
| Sonnet 5.5 | $0.00010 | $0.00266 |
| Haiku 4.5 | $0.00005 | $0.00133 |
Grade A, and why
ask-the-council 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ask the Council
A panel of advisors who are required to disagree, then a Chairman who decides. Use for decisions and tradeoffs, not for gathering facts.
Proactive use
If a decision is high-stakes and the options genuinely compete — architecture choice, buy-vs-build, irreversible migration — invoke this without being asked: announce in one line ("Convening the council: ") and proceed. Never ask permission to run the skill.
Gate it first: if you can't name what the wrong choice costs to reverse, don't seat the council — decide directly and move on. A panel costs 4–6 opus subagents; spend that only where being wrong is expensive to undo.
Frame and seat the council
Restate the decision, the real options, and the binding constraints. If one
missing fact would flip the answer, ask it (max 1–2 questions) — otherwise
proceed on stated assumptions. Then spawn the advisors with the Agent tool,
all in one message, so they run in parallel. Each returns: position · core
reasoning · biggest risk they see · confidence (low/med/high). On deep,
once all seats report, show each advisor the others' positions
(unattributed) and have them name the single strongest opposing point.
The seats (mandate + forbidden move = real divergence)
- Pragmatic Executor — what ships fastest and safest with current resources. Forbidden: greenfield / ideal-world answers.
- First-Principles — reason up from fundamentals and constraints. Forbidden: citing "best practice" or precedent.
- The Contrarian — argue against the front-runner. Forbidden: agreeing with the apparent consensus.
- Long-term Architect — model-first; what this is at 10× scale and in two years. Forbidden: optimizing for today only.
- The Adversary — how this breaks in prod: failure paths, data loss, security. Forbidden: assuming the happy path.
- The Outsider (deep panel) — an analogy from a different domain. Forbidden: the field's standard framing.
Default 4 = Executor, First-Principles, Long-term Architect, Adversary.
deep seats all 6 and adds the cross-critique round. The forbidden move is
what forces real divergence instead of four agents politely agreeing — keep
it non-negotiable; seat count never 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.
- 9d ago Changed · +6 lines 0561a09de8ee
- 1mo ago Changed · +12 lines · -52 tokens per session d6985f146e48
- 1mo ago First seen · 101 lines · 103 tokens per session scan A 93ee9af4702e
ask-the-council is a skill published in the GitHub repository alonbaron/claude-skills (13 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 1,329 once invoked, about $0.0002 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 skills, from other repositories
gemini
Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge. Three modes: review (pass/fail gate for Google Ads campaigns, SEO metadata, or code), challenge (adversarial stress-test that tries to break your changes), and consult (open Q&A with Gemini…
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
security-architecture-review
Reviews a design or change for security before it ships — authentication and authorization, data handling, secrets, dependencies, and the secure-development practices around it. Use this to review an architecture or pull request for security, set secure coding standards, choose or tune SAST and DAST tooling, assess a…
pr-threads-address
Address PR review feedback by systematically working through every unresolved PR review thread on the current branch's PR - analyze each comment, make the requested code changes (with tests where useful), commit, and optionally reply and resolve.
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.