council

council is a skill for Claude Code, Codex from epicsagas/plugins. It costs 64 tokens per session (625 once invoked), scanned A, original, Apache-2.0.

A structured discussion workflow for difficult architecture, technology, or design choices. Four independent viewpoints examine long-term design, risks, practicality, and available evidence before producing a combined recommendation.

In plain words
What is it for?
Use it to compare valid approaches, review trade-offs, identify risks, and reach a reasoned technical decision.
Why use it?
It reduces the chance that one early opinion or assumption determines a decision without considering alternatives and failure cases.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to compare valid approaches, review trade-offs, identify risks, and reach a reasoned technical decision.

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

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

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

agentmods 80×15 button for council

Your own site · 80×15
<a href="https://agentmods.dev/skills/epicsagas/plugins/council"><img src="https://agentmods.dev/badge/skills/epicsagas/plugins/council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 625 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 $0.00064 $0.00625
Opus 5 $0.00032 $0.00313
Sonnet 5 $0.00013 $0.00125
Haiku 4.5 $0.00006 $0.00063

Measured 4d ago against content hash d689eb0c0fda, 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 4d 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.

.hermes/epic/skills/council.SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

4-voice deliberation: Architect · Skeptic · Pragmatist · Critic. Each evaluates independently, then a synthesis is produced.

Usage

/council <decision or question>

The four voices

🏗️ Architect

  • Focuses on long-term system design, extensibility, and maintainability
  • Asks: "How does this scale? What are the boundaries? What patterns apply?"
  • Argues for the cleanest design

🔍 Skeptic

  • Looks for flaws, hidden risks, and failure modes
  • Asks: "What could go wrong? What assumptions are untested? What are the edge cases?"
  • Argues for the safest approach

⚡ Pragmatist

  • Prioritizes speed, simplicity, and immediate value
  • Asks: "What's the fastest path? What can we defer? What's good enough?"
  • Argues for the simplest approach

📊 Critic

  • Evaluates trade-offs with data, benchmarks, and precedents
  • Asks: "What does the evidence say? What have others done? What are the measurable differences?"
  • Argues for the most evidence-based approach

Process

  1. State the question — clarify the decision and constraints
  2. Recall contextharness_mem_recall to surface past decisions on related topics
  3. Each voice responds independently — no voice sees another's response
  4. Synthesize — identify consensus, list disagreements, recommend a path
  5. Recordharness_mem_add the decision with reasoning as type "decision"
  6. Linkharness_mem_link to any related prior decisions

Output format

## Decision: <question>

### Architect
<2-3 paragraph argument>

### Skeptic
<2-3 paragraph argument>

### Pragmatist
<2-3 paragraph argument>

### Critic
<2-3 paragraph argument>

### Synthesis
- **Consensus:** <what all 4 agree on>
- **Disagreement:** <where voices diverge>
- **Recommendation:** <final recommendation with reasoning>
- **Risk:** <highest-risk aspect regardless of choice>

When to use council vs. just decide

Situation Use council?
Two+ valid approaches with real trade-offs ✅ Yes
Simple choice with obvious best answer ❌ Just decide
User explicitly asks for deliberation ✅ Yes
Reversible decision with low stakes ❌ Just decide
Architecture change affecting multiple components ✅ Yes

Read the full file on GitHub · 82 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. 4d ago First seen · 82 lines · 64 tokens per session scan A d689eb0c0fda

Subscribe to this mod's changes

council is a skill published in the GitHub repository epicsagas/plugins (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 64 tokens to every session and 625 once invoked, about $0.0003 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 2026-09-05.

Related

Other skills, from other repositories

deps-audit

Use when auditing, updating, or securing project dependencies. Covers multi-language dependency detection, security vulnerability scanning, outdated package identification, unused dependency detection, and update strategies for npm, pip, cargo, and go.

Sagargupta16/claude-skills · 46 tokens

git-advanced

Use when performing complex git operations -- rebasing, cherry-picking, resolving merge conflicts, bisecting bugs, managing stashes, cleaning history, or working with monorepos. Goes beyond basic commit/push/pull.

Sagargupta16/claude-skills · 50 tokens

refactoring

Use when restructuring code without changing behavior -- extracting functions, renaming, moving files, reducing duplication, migrating between patterns (JS to TS, CJS to ESM), or addressing code smells. Covers safe refactoring workflows for any language.

Sagargupta16/claude-skills · 51 tokens

repo-polish

Use when setting up new repositories, auditing existing ones, or preparing repos for public visibility. Generates .gitignore, .env.example, README, and LICENSE files. Detects committed secrets and flags security issues.

Sagargupta16/claude-skills · 46 tokens

starter-session-audit

Use when the user asks to audit a session for uncaptured learnings. Activates on "audit this session", "session audit", "what did we miss", "end of session check", or "/starter-session-audit". Scans the conversation for corrections, preferences, decisions, and new context, then proposes where to save each.

Sagargupta16/claude-skills · 73 tokens

clean-code

Use when the user writes new Python, or asks for review, refactor, or cleanup of Python code, names, comments/docstrings, functions, or tests. Applies Robert Martin's complete Clean Code catalog -- naming, functions, comments, DRY, boundary conditions, and tests -- to the code being changed.

Sagargupta16/claude-skills · 66 tokens