agentleFS
Sign inStart free
qyndexqyndex/claude-init/.claude/skills/constitution/SKILL.md

constitution

Skill2 starsChanged 5 months agoMITView on GitHub

Author or amend the project constitution at .claude/CLAUDE.md. Use when starting a brand-new project, when a major architectural principle shifts, or when the team wants to lock in non-negotiables. Modeled on github/spec-kit's /speckit.constitution.

6 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the existing constitution: if any. Identify what's working and what's drift.

    line 16
  2. Distinctive:

    Linkable: Use anchors so other files can deep-link.

    line 46

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Constitution

You are about to write or amend the project constitution at .claude/CLAUDE.md. This file is the single source of truth for every agent in this repo. It overrides defaults; the user overrides it.

Process

  1. Read the existing constitution if any. Identify what's working and what's drift.
  2. Interview the user (max 4 questions) on:
    • Primary tech stack and runtime
    • Non-negotiable quality bars (test coverage, security gates, performance targets)
    • Deployment cadence and environment topology
    • Any incident-driven rules ("never X again because Y")
  3. Draft the constitution with the sections in this template (see .claude/CLAUDE.md for the canonical structure).
  4. Validate — under 200 lines, no fluff, every rule has a why.
  5. Save to .claude/CLAUDE.md and stage for commit.

Sections required

  1. North star (1 paragraph)
  2. Non-negotiables (5-10 hard rules)
  3. Workflow / phases
  4. Agent team roster
  5. Memory system
  6. Token discipline
  7. Security guardrails
  8. Quality bar (the shipping checklist)
  9. Auto-mode rules
  10. Decision-making defaults
  11. House style
  12. Bootstrap + maintenance pointers

Hard rules for the constitution itself

  • Under 200 lines. Link out for details.
  • Every rule explains why. A rule with no rationale gets ignored.
  • No platitudes. "Write good code" is not a rule. "Functions ≤ 50 LOC" is.
  • Linkable. Use anchors so other files can deep-link.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free