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 tsenart/council-skill --skill councilgit clone --depth 1 https://github.com/tsenart/council-skillWrote 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/tsenart/council-skill/council)<a href="https://agentmods.dev/skills/tsenart/council-skill/council"><img src="https://agentmods.dev/badge/skills/tsenart/council-skill/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/tsenart/council-skill/council"><img src="https://agentmods.dev/badge/skills/tsenart/council-skill/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 | $0.00048 | $0.00952 |
| Opus 5 | $0.00024 | $0.00476 |
| Sonnet 5 | $0.00010 | $0.00190 |
| Haiku 4.5 | $0.00005 | $0.00095 |
Grade A, and why
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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Council
Use this skill when the user wants a multi-perspective council rather than a single answer. Good triggers include:
- "run a council on this"
- "get multiple perspectives"
- "debate this decision"
- "stress test this plan"
- architecture, product, strategy, debugging, risk, or founder tradeoffs
If $ARGUMENTS is non-empty, treat it as the problem statement. Otherwise ask
the user for the question to deliberate on.
First Step
Read only the references you need:
references/profiles.yamlfor panel selectionreferences/protocol.mdfor orchestrationreferences/verdict-template.mdfor final output shapereferences/personas/<member>.mdonly for the members you actually select
Defaults
- Prefer 3 members unless the user asks for a full panel or the problem is unusually ambiguous.
- Default to
classic+architectureif nothing else is specified. - Keep the final verdict compact unless the user asks to see the rounds.
Workflow
1. Resolve The Panel
Honor, in order:
- explicit
--members - explicit
--triad - explicit
--profile - keyword triad match
- fallback default
2. Round 1: Independent Analysis
- Run each selected member independently.
- Keep round 1 blind-first: each member sees only the problem statement and their own persona text.
- Ask for a compact standalone analysis that ends with a clear verdict, confidence, and where the member may be wrong.
Preferred orchestration:
- If the host supports explicit subagents or forked contexts, use one independent delegate per selected member.
- In Codex, prefer
spawn_agent, thensend_inputandwait_agent. - In Amp, prefer one
oraclecall per selected member. - In Claude Code, use parallel or forked agent contexts when they are available. If they are not easy to access, keep the protocol in the main session and separate the member outputs clearly.
Suggested round 1 packet:
You are operating as one member of a structured council.
Persona:
{persona}
Problem:
{problem}
Produce a compact standalone analysis.
End with a clear verdict, confidence, and where you may be wrong.
Do not anticipate the other members.
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/personas/ada.md 700 B
- references/personas/aristotle.md 629 B
- references/personas/aurelius.md 672 B
- references/personas/elon.md 747 B
- references/personas/feynman.md 679 B
- references/personas/lao-tzu.md 669 B
- references/personas/machiavelli.md 666 B
- references/personas/musashi.md 640 B
- references/personas/socrates.md 633 B
- references/personas/steve-jobs.md 920 B
- references/personas/sun-tzu.md 659 B
- references/personas/torvalds.md 622 B
- references/personas/watts.md 683 B
- references/profiles.yaml 5.4 KB
- references/protocol.md 2.6 KB
- references/verdict-template.md 657 B
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 · 141 lines · 48 tokens per session scan A c4c760de2863
council is a skill published in the GitHub repository tsenart/council-skill (6 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 952 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…