Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Council Rules

ASecurity

Full Council Structure — Core Five Divisions (Architecture/Implementation/Quality/Security/Testing) + Extended Eleven Divisions (Compliance/UX/Ops/Data/Finance/Risk/Strategy/People/ESG/AI-Ethics/Comms) with veto authority + agent rosters + per-division personas (collective experience, core principles, key deliverables, checklists, red flags) + Conversation Rules (order of speaking, research depth, disagreement protocol, escalation to user). Use when authoring/editing agent files, running Coun...

12 stars
0 votes
0 copies
0 views
Added 10/6/2026
ai-agentsgonodetestingcode-reviewfrontendsecurity

Security Analysis

A100/100

Pro scans all 8 files and shows the line behind each finding

Scanned 10/6/2026

$npx -y skills add Nmor/the-council --skill council-rules --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Council Rules?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Council Rules
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/nmor-council-rules-the-council/badge)](https://www.skillsdirectory.com/skills/nmor-council-rules-the-council)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: council-rules
description: Full Council Structure — Core Five Divisions (Architecture/Implementation/Quality/Security/Testing) + Extended Eleven Divisions (Compliance/UX/Ops/Data/Finance/Risk/Strategy/People/ESG/AI-Ethics/Comms) with veto authority + agent rosters + per-division personas (collective experience, core principles, key deliverables, checklists, red flags) + Conversation Rules (order of speaking, research depth, disagreement protocol, escalation to user). Use when authoring/editing agent files, running Council debates, resolving division tiebreakers, or training new contributors on Council conventions.
disable-model-invocation: true
---

# Council Rules — Full Division Detail + Personas + Conversation Rules

> **Size budget: 25 KB.** Check: wc -c. Gate: node ~/.claude/scripts/token-budget.mjs --check
>
> Migrated 2026-06-02 from `~/.claude/CLAUDE.md` lines 79-239
> (Council Structure + Extended Eleven), lines 748-849
> (Conversation Rules), lines 1416-1680 (Division Personas) +
> `~/.claude/rules/common/council-triggers.md` content.
> Sister skill: [`council-protocol`](../council-protocol/SKILL.md)
> which holds the Phase 0/1/2/3 templates.

## When to activate

This skill fires when:

- Any agent file under `~/.claude/agents/` is opened or edited
- Any plan file is opened (planners need Council structure)
- Any file matching `council-*.md` under `rules/common/` is touched
- Workspace `COUNCIL.md` files are opened

The Floor rules `council-default.md` + `council-triggers.md`
declare WHEN divisions engage; this skill provides the FULL
DETAIL on each division — their agent rosters, personas,
checklists, and the conversation rules that govern multi-
division debates.

## Standards Cited

The frameworks the division catalogue triggers on and reviews against; the triggers and
vetoes that apply them live in the references.

- **OWASP Top 10**: Division 4's baseline review checklist
- **GDPR** (incl. Article 22 automated decisions, Article 8 children), **CCPA / CPRA**
- **HIPAA / HITECH** and **42 CFR Part 2**: the health sub-cluster
- **PCI-DSS**: the payments sub-cluster
- **FERPA / COPPA**: the education sub-cluster
- **ISO/IEC 27001**, **ISO 9001:2026**, **ISO 14001**, **ITIL 4**: the frameworks the
  division structure was researched against (`references/trigger-catalog.md`)
- **WCAG 2.2 AA**: accessibility on user-facing and assessment paths

## Routing table

This skill is `paths:`-gated, so whatever it holds is added to the always-on
Floor IN FULL whenever a glob matches. The detail therefore lives in
`references/`; this page routes to it. Read only the row(s) the task needs.

| Topic | Read this |
| --- | --- |
| Core Five — structure + agent roster (Divisions 1-5: leads, models, responsibilities, when to engage, frontend skill auto-activation) | [`references/core-five-divisions.md`](references/core-five-divisions.md) |
| Extended Eleven — leads + veto authority (Divisions 6-16 summaries: auto-fire signals, veto/escalation) | [`references/extended-eleven-divisions.md`](references/extended-eleven-divisions.md) |
| Conversation rules (order of speaking, research-depth minimums per division, disagreement protocol, escalation-to-user format) | [`references/conversation-rules.md`](references/conversation-rules.md) |
| Division personas (collective experience, core principles, deliverables, review checklists, quality metrics, OWASP + severity tables, secure-coding patterns, red flags) | [`references/division-personas.md`](references/division-personas.md) |
| Agent delegation + orchestration (available-agents table, immediate agent usage, parallel Task execution, multi-perspective analysis) | [`references/agent-delegation.md`](references/agent-delegation.md) |
| Full per-division trigger catalog (every file glob, keyword set, change-scope trigger + veto authority; payments / health / education sub-clusters; cross-cutting composition; how triggers are evaluated) | [`references/trigger-catalog.md`](references/trigger-catalog.md) |
| Model-tier ladders + availability (tier capability table, resolution algorithm, `~/.claude/.local/model-availability`, graceful degradation, alias currency, anti-patterns) | [`references/model-tier-ladders.md`](references/model-tier-ladders.md) |

## Cross-references

- `~/.claude/skills/council-protocol/SKILL.md` — sister skill: Phase 0/1/2/3 templates + Research
  Requirements + Post-Implementation Review
- `~/.claude/rules/common/council-default.md` — Floor: Council always convenes
- `~/.claude/rules/common/principal-level-mandate.md` — Floor: quality bar every division enforces
- `~/.claude/agents/architect.md` — Division 1 lead
- `~/.claude/agents/planner.md` — Division 1 lead
- `~/.claude/agents/security-reviewer.md` — Division 4 lead
- `~/.claude/agents/code-reviewer.md` — Division 3 lead
- `~/.claude/agents/tdd-guide.md` — Division 5 lead
- `~/.claude/agents/compliance-reviewer.md` — Division 6 lead (VETO)
- `~/.claude/agents/risk-reviewer.md` — Division 11 lead (VETO)
- `~/.claude/agents/ai-ethics-reviewer.md` — Division 15 lead (VETO)

## Why this skill exists

The Council Structure detail, Extended Eleven specifics,
per-division personas, conversation rules, and disagreement
protocols are REFERENCE material the assistant consults when:

- Authoring or editing an agent file (the agent IS one of these
  division roles; the skill clarifies the role's scope)
- Running a Council debate that needs the full per-division
  checklist (most everyday tasks invoke divisions from memory
  via Floor's `council-default.md`)
- Resolving a tiebreaker the Floor rules can't (Floor names the
  veto matrix; this skill names the divisions' personas in
  enough detail to inform the casting vote)

Everyday code work doesn't need this level of detail loaded;
the Council Phase 1 happens from memory + Floor knowledge.
This skill exists to provide the durable record when the
assistant authors something Council-shaped (an agent file, a
plan, a runbook, an ADR).

Migration provenance: CLAUDE.md lines 79-239 (Council Structure +
Extended Eleven), 748-849 (Conversation Rules), 1416-1680
(Division Personas) → moved here 2026-06-02 as part of the
lazy-rules-loading plan.

Attribution

NmorNmor
View sourceSee grades on GitHubMore from Nmor →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →