An optional review process in which specialist sub-agents examine a pull request involving a hard-to-reverse decision, such as a schema change, public API, or pricing change. A chair combines their findings into one verdict.

Use it before merging high-stakes pull requests and, when wired up, after a critical signal identifies affected files or artifacts.

It adds focused review to changes where reverting later could be costly or risky, without requiring the process for routine pull requests.

council — Skill for Claude Code by GuitarAlchemist

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 GuitarAlchemist/ga --skill council

Clone the repo

git clone --depth 1 https://github.com/GuitarAlchemist/ga

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/guitaralchemist/ga/council/github.svg)](https://agentmods.dev/skills/guitaralchemist/ga/council)

Your own site

<a href="https://agentmods.dev/skills/guitaralchemist/ga/council"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/guitaralchemist/ga/council"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,098 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.

Model	Per session	Once invoked
Fable 5.1	$0.00098	$0.03098
Opus 5	$0.00049	$0.01549
Sonnet 5	$0.00020	$0.00620
Haiku 4.5	$0.00010	$0.00310

Measured 9d ago against content hash c25ed97f5a37, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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 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.

.claude/skills/council/SKILL.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/council

A virtual council of specialist sub-agents convened to review a PR that touches a known one-way door. Inspired by claude-codex-forge's /council pattern — five voices, one chair, one synthesized verdict, written to state/quality/council/<head-sha>.json and posted as a PR comment.

This is opt-in by design. It does not auto-fire on every PR. The operator invokes it on PRs they would lose sleep about reverting. For routine review, use /octo:review or the existing chatbot-iterate tribunal gate.

Auto-invocation triggers

/council is opt-in by default. One auto-trigger is reserved (wiring in a follow-up; see below):

Critical-severity algedonic signal lands in the inbox. Per the algedonic-channel contract (docs/contracts/2026-05-24-algedonic-channel.contract.md, §7), a signal with severity == "critical" SHOULD auto-fire /council with the signal's affected_artifacts standing in for the PR diff.

Invocation form (when wired):
```
/council --signal <id>
```
The skill reads the signal from state/algedonic/inbox.jsonl, treats affected_artifacts as the door-touch set, and proceeds from Step 3 (advisor convening) — skipping Steps 1–2 because there is no PR to resolve.

The synthesized verdict is appended back to the inbox as an info signal with supersedes: [<original-id>] and the council's resolution text. This closes the loop: the operator sees one tile go from "critical, unacked" to "council resolved" without manual ack.

Status: documented, not yet wired. This PR ships the contract and the Heartbeat algedonic tile. The watcher that actually triggers /council on a critical signal is a follow-up (it needs to live somewhere — Vite middleware, a sidecar process, or a session-start hook — and that choice is its own design decision).

No other auto-triggers exist. Routine PR review still goes through /octo:review or chatbot-iterate.

Read the full file on GitHub · 292 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.

9d ago First seen · 292 lines · 98 tokens per session scan A c25ed97f5a37

Subscribe to this mod's changes

council is a skill published in the GitHub repository GuitarAlchemist/ga (2 stars, last pushed today), licensed MIT. It adds 98 tokens to every session and 3,098 once invoked, about $0.0005 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.

Code review

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

rework-rate

Measure and interpret PR rework rate — the emerging 5th DORA metric.

bradygaster/squad · 20 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

code-reviewer

Code review specialist focused on patterns, bugs, security, and performance.

RightNow-AI/openfang · 17 tokens

agent-teams-simplify-and-harden

Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…

LeoYeAI/openclaw-master-skills · 115 tokens