Skip to content
Back to skills

Council

ASecurity

Route substantive engineering work to the relevant Council rules, skills and one justified specialist review.

  • 12 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 6, 2026
ai-agentstestingsecurity

Works with

  • claude code

Security analysis

A100/100

Scanned October 6, 2026

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

Installs into .claude/skills of the current project.

Are you the author of Council?

Add the live security badge to your README. It updates with every re-scan.

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

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

Download with Pro
SKILL.md
---
name: council
description: Route substantive engineering work to the relevant Council rules, skills and one justified specialist review.
---

# Council

Follow the compact working contract in `~/.claude/CLAUDE.md`. Inspect existing work
and the project's authoritative plan; consider architecture, implementation,
quality, security and testing. Work in the main session by default. Invoke one
bounded specialist only when an independent investigation or review adds evidence.

Find only relevant resources under `~/.claude/skills/`, `~/.claude/agents/` and
`~/.claude/rules-library/`. Search filenames/descriptions before reading a selected
file. Do not enumerate or read the whole library into the conversation.

Before editing, read `rules-library/common/coding-style.md` and the applicable
language's coding/testing rules. Use `skills/council-rules/SKILL.md` for specialist
routing when needed; detailed protocol templates are for explicitly deep reviews.
The other skills remain manually invocable and readable under compact discovery.

Read only the current handoff and relevant plan sections. Continue the accepted
task after compaction; do not reload historical plans, rerun intake or repeat valid
reviews. Keep verbose logs in files and return concise results and evidence paths.
Preserve user sessions, memory and other agents' work. User scope and existing
authorization take precedence over imported procedural examples.

Primary reference: [Claude Code skills](https://code.claude.com/docs/en/skills).

> Size budget: 4 KB. Check: wc -c; gate: token-budget.mjs --check.

Attribution

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

Loading comments…