agentmods.dev

council_runner

council_runner is a skill for Claude Code, Codex from jxoesneon/Ciel. It costs 19 tokens per session (687 once invoked), scanned A, original, Apache-2.0.

A tool that runs a three-stage review by five evaluators, then combines their results into one chairperson's verdict. It can use parallel or sequential subagents depending on the command-line environment.

In plain words
What is it for?
Use it to score an artifact, anonymize first-round results, run cross-review, synthesize votes, and save the review outcome.
Why use it?
It organizes several independent opinions and produces a recorded, weighted conclusion instead of requiring manual coordination.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Claude Code; mentions Gemini CLI.

not rated 1repo changed 1mo ago A scan 19 tokens original Apache-2.0

Good fit Use it to score an artifact, anonymize first-round results, run cross-review, synthesize votes, and save the review outcome.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jxoesneon/ciel/council_runner
View source ↗ jxoesneon/Ciel
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 jxoesneon/Ciel --skill council_runner
Clone the repo
git clone --depth 1 https://github.com/jxoesneon/Ciel

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_runner

README.md
[![agentmods](https://agentmods.dev/badge/skills/jxoesneon/ciel/council_runner/github.svg)](https://agentmods.dev/skills/jxoesneon/ciel/council_runner)
Your own site
<a href="https://agentmods.dev/skills/jxoesneon/ciel/council_runner"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/council_runner/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_runner

Your own site · 80×15
<a href="https://agentmods.dev/skills/jxoesneon/ciel/council_runner"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/council_runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 687 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 $0.00019 $0.00687
Opus 5.5 $0.00008 $0.00275
Sonnet 5.5 $0.00004 $0.00137
Haiku 4.5 $0.00002 $0.00069

Measured 1mo ago against content hash 8c7e78ab0e87, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

council_runner 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.

ciel.skill/seed_skills/council_runner/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

council_runner

Orchestrate the 3-stage Council of Five.

Operations

  • council.run(scope, artifact, context?) — returns Chairman verdict.
  • council.stage1(members, artifact) — parallel scoring.
  • council.anonymize(stage1_outputs) — Stage 2 prep.
  • council.stage2(members, anonymized) — cross-review.
  • council.chairman(stage2_outputs, weights) — synthesis.
  • council.record(run_id, payload) — persist to ~/.ciel/council/<id>/.

I/O Contract

io_contract:
  input: { scope, artifact, "context?" }
  output: { verdict, weighted_score, pivotal_lens, votes, run_id }
  idempotent: no (but deterministic with seed)
  side_effects: [fs, "network?"]

Runtime Adaptation

  • Claude Code: nested subagents (see adapters/claude_code/COUNCIL_INVOCATION.md).
  • Gemini CLI: parallel top-level subagents.
  • Devin: five parallel run_subagent dispatches per stage (see adapters/devin/COUNCIL_INVOCATION.md).
  • Generic: sequential inline.

Enforcement Contract

Member-as-subagent is a mechanism, not prose (docket council-20260923-conversation-audit, mechanism M1). Every run MUST:

  1. Write the evidence pack to a readable path and dispatch each member as an individual subagent — never inline deliberation, never truncated member output. The Chairman synthesizes ALL member verdicts; it may not adopt a subset.

  2. Record per-member spawn receipts and stage artifacts under ~/.ciel/council/<run_id>/:

    spawn_receipts.json   {"mode":"subagent"|"inline","members":{name:{stage1_agent_id,stage2_agent_id}}}
members/<member>.stage1.json
members/<member>.stage2.json
verdict.json          # chairman docket

  3. mode: "inline" is a degraded fallback only — it MUST be declared; verification flags it unverified_member_isolation. A run with no receipts fails verification outright.

  4. After the docket, run python3 scripts/council_verify.py <run_id> — validates completeness and emits structured member verdicts to ~/.ciel/improvements/signals/council-<run_id>.json for the improvement loop.

Read the full file on GitHub · 69 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. 1mo ago Changed · +28 lines 8c7e78ab0e87
  2. 1mo ago First seen · 41 lines · 19 tokens per session scan A f2be5801c67f

Subscribe to this mod's changes

council_runner is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 4d ago), licensed Apache-2.0. It adds 19 tokens to every session and 687 once invoked, about $0.0001 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 2026-08-31.

Autonomous AgentsBuilding agentsClaude Codeagentic-workflowsaicouncilgemini-climulti-agent-systemsrisk:lowruntime:anyscope:both
Related

Other skills, from other repositories

Code Quality Review

Conduct a comprehensive code quality review focused on clean code, architecture, and project standards.

asap-protocol/asap-protocol · 21 tokens

surge

Use when a user provides a PRD, spec, or detailed requirements document and needs a full project delivered through iterative expert orchestration — multi-round analyze/research/design/implement/QA cycles with convergence detection. NOT for: single-file edits, quick prototypes, simple Q&A, or tasks without a written…

carbonshow/intent-fluid · 66 tokens

ai-native-software-dev

Use when the user asks to build, change, modernize, or reconstruct non-trivial software with an AI-native workflow, including greenfield development, work in an existing codebase, or authorized reference-based product reconstruction; also use when lifecycle planning, architecture, implementation, testing, review…

carbonshow/intent-fluid · 101 tokens

expert-redteam-review

Use when a user asks to evaluate a complex, high-impact, ambiguous, cross-functional, or hard-to-reverse decision; mentions expert panel, red team, adversarial review, rebuttal, judge, arbitration, risk review, challenge assumptions, poke holes, or wants stronger decision quality than a normal review.

carbonshow/intent-fluid · 67 tokens

code-review

Revisão holística pré-commit (estilo PR Review). Valida o diff contra as 3 memórias vivas, a spec da task e Clean Code, em paralelo ao QA/Security (fan-out); a evidência de teste é exigida no join. Executada pelo Tech Lead; veredito escrito em review.md.

rcelebrone/DotAgents · 73 tokens

compound

Persistência de aprendizados nas memórias vivas ao final de cada ciclo. Use para "atualizar memória", "guardar aprendizados" ou "sincronizar contexto do projeto". Executada pelo Tech Lead após o PO definir Status entregue.

rcelebrone/DotAgents · 52 tokens