council

council is a skill for Claude Code from yogirk/agent-council. It costs 67 tokens per session (955 once invoked), scanned A, original, MIT.

A command for asking several command-line AI agents, such as Codex and Gemini, to consider the same question independently before a chairman combines their answers. It is intended for technical decisions and investigations.

In plain words
What is it for?
Getting multiple perspectives on architecture choices, code reviews, debugging hypotheses, and other questions where independent analysis helps.
Why use it?
It gives architecture, review, and debugging questions more than one independent viewpoint. The final synthesis makes the differing opinions easier to compare.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex.

Good fit Getting multiple perspectives on architecture choices, code reviews, debugging hypotheses, and other questions where independent analysis helps.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yogirk/agent-council/claude-code
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 yogirk/agent-council --skill claude-code
Clone the repo
git clone --depth 1 https://github.com/yogirk/agent-council

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/yogirk/agent-council/claude-code/github.svg)](https://agentmods.dev/skills/yogirk/agent-council/claude-code)
Your own site
<a href="https://agentmods.dev/skills/yogirk/agent-council/claude-code"><img src="https://agentmods.dev/badge/skills/yogirk/agent-council/claude-code/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

Your own site · 80×15
<a href="https://agentmods.dev/skills/yogirk/agent-council/claude-code"><img src="https://agentmods.dev/badge/skills/yogirk/agent-council/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 955 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.
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 $0.00067 $0.00955
Opus 5.5 $0.00027 $0.00382
Sonnet 5.5 $0.00013 $0.00191
Haiku 4.5 $0.00007 $0.00096

Measured 2mo ago against content hash f267384ed583, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

skills/claude-code/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Council

Convene a multi-agent council to deliberate on a question. You (Claude) are the chairman. Other CLI agents (Codex, Gemini) provide independent opinions. You synthesize the final verdict.

Usage

The user invokes /council "their question" or /council --with-review "their question".

Step 1: Dispatch the council

Run this bash block. Replace {QUESTION} with the user's actual question text.

COUNCIL_BIN=""; for _d in "$HOME/.claude/skills/agent-council" "$HOME/.agents/skills/agent-council" "$HOME/.gemini/skills/agent-council" "$(git rev-parse --show-toplevel 2>/dev/null)"; do [ -x "$_d/bin/council" ] && COUNCIL_BIN="$_d/bin/council" && break; [ -x "$_d/council" ] && COUNCIL_BIN="$_d/council" && break; done; [ -z "$COUNCIL_BIN" ] && COUNCIL_BIN="$(which council 2>/dev/null || echo "bin/council")"
QUESTION_FILE=$(mktemp /tmp/council-q-XXXXXX)
cat <<'COUNCIL_EOF' > "$QUESTION_FILE"
{QUESTION}
COUNCIL_EOF
SLUG=$(basename "$(git rev-parse --show-toplevel 2>/dev/null || pwd)")
SESSION_DIR=$($COUNCIL_BIN --question-file "$QUESTION_FILE" --project "$SLUG")
rm -f "$QUESTION_FILE"
echo "SESSION_DIR=$SESSION_DIR"

If the user passed --with-review, add that flag to the council command. If the user passed --quick, add that flag instead.

Step 2: Read the council opinions

After the bash block completes, read the opinion files from the session directory:

  1. Read $SESSION_DIR/meta.json to understand the session structure
  2. Read each file in $SESSION_DIR/stage1/ (opinion_codex.json, opinion_gemini.json, etc.)
  3. If --with-review was used, also read files in $SESSION_DIR/stage2/

Step 3: Synthesize as chairman

You are the chairman. You have the full conversation context with the user PLUS the council opinions. Produce the synthesis:

  • Consensus: Where all agents agree
  • Divergence: Where agents disagree. State each position fairly with agent name.
  • Recommendation: Your synthesized answer drawing from the strongest elements.
  • Confidence:
    • If all agree: HIGH — Strong consensus across models.
    • If majority agrees: MEDIUM — Majority view with notable dissent.
    • If fundamental disagreement: LOW — Agents fundamentally disagree. For each agent, state: Agent name (their confidence): their position. End with: "This is a decision you should make yourself, not delegate to the council."

Read the full file on GitHub · 99 lines

Files

What ships with it

6 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.

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. 2mo ago First seen · 99 lines · 67 tokens per session scan A f267384ed583

Subscribe to this mod's changes

council is a skill published in the GitHub repository yogirk/agent-council (92 stars, last pushed 7mo ago), licensed MIT. It adds 67 tokens to every session and 955 once invoked, about $0.0003 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.

Related

council compared with skills from other repositories

council next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
councilyogirk/agent-councilSkill927mo agoMITA67Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code