agentleFS
NagiliantNagiliant/Genesis-Legacy-V2/skills/genesis-amend/SKILL.md

Amend

Skill2 starsChanged 5 months agoApache-2.0View on GitHub

Formally amend the constitution, with mandatory impact analysis before any change lands. The constitution is supreme law; amendments are versioned and their downstream effects scanned first.

2 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

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Impact analysis (always first): Before applying anything, scan for downstream impact:

    line 14
  2. Distinctive:

    Write the change to the constitution.

    line 29
  3. Very specific:

    Update the project-state.md session log.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Amend — Change the Constitution

The formal process for changing the constitution, with mandatory impact analysis before any change lands. The constitution is supreme law; amendments are versioned and their downstream effects are scanned first.

Process

  1. Identify the amendment. Take the section number as an argument, or show the constitution's table of contents and ask. Amendment types: tech stack, quality gates, conventions, architecture decisions.
  2. Impact analysis (always first). Before applying anything, scan for downstream impact:

    • Approval records — scan active features' approvals/master.json and group-N.json for records referencing the affected section or the constraints being changed.
    • Implementation dependencies — search feature directories for specs referencing the section, micro specs constrained by the changing rule, and completed implementations that may need review.

    Present a summary with a risk level:

    Impact Analysis for Amendment:
    AFFECTED FEATURES:        {list with approval status}
    APPROVAL RECORDS:         {count} reference affected constraints
    IMPLEMENTATIONS AT RISK:  {count} completed implementations
    RISK LEVEL: {Low | Medium | High | Critical}

    --impact stops here (analysis only). If risk is High/Critical and --force is not set, refuse: "This amendment affects {N} active features. Use --force to proceed, or resolve in-progress work first."

  3. Apply the amendment. On approval:
    1. Draft the amendment text with its rationale.
    2. Write the change to the constitution.
    3. Append to the constitution's changelog (the versioning record):
      | #{NNN} | {date} | S{section} | {summary} | {rationale} |
      The sequential #NNN is the amendment's version identifier; the changelog is the durable history.
    4. Update the project-state.md session log.
    5. Downstream cleanup checklist — after applying, verify every reference still holds:

      • other specs referencing the amended section — still accurate?
      • design-doc sections describing the amended area — updated?
      • skill/doc examples referencing the amended behavior — updated?
      • coverage maps (FR/AC) — do they still add up?
      • shared file paths — do other specs that touch them know?

      Fix any failing check before committing. Amendments that don't propagate leave stale references that the final audits catch.

  4. Commit. A single scoped commit, e.g. amend: constitution section {N} — {summary}.

Natural language triggers

- "amend the constitution"
- "change a project rule"
- "what would this amendment affect"

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.