Constitute

Constitute is a skill for Claude Code from Nagiliant/Genesis-Legacy-V2. It costs 23 tokens per session (660 once invoked), scanned A, original, Apache-2.0.

A tool for writing or reviewing a project constitution: the rules for its mission, technology, architecture, coding standards, testing, security, and documentation.

In plain words
What is it for?
Use it after project discovery to create the constitution, or review it against feature specifications and ADRs—short records of important technical decisions.
Why use it?
It gives later work a shared set of enforceable rules and can reveal when approved plans or architecture decisions conflict with those rules.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the genesis-spec-kit plugin — 23 skills shipped together

Good fit Use it after project discovery to create the constitution, or review it against feature specifications and ADRs—short records of important technical decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nagiliant/genesis-legacy-v2/genesis-constitute
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 Nagiliant/Genesis-Legacy-V2 --skill genesis-constitute
Clone the repo
git clone --depth 1 https://github.com/Nagiliant/Genesis-Legacy-V2

Made for: Claude Code.

Or install genesis-spec-kit, the plugin that ships this one along with the rest of its 23 skills.

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 Constitute

README.md
[![agentmods](https://agentmods.dev/badge/skills/nagiliant/genesis-legacy-v2/genesis-constitute/github.svg)](https://agentmods.dev/skills/nagiliant/genesis-legacy-v2/genesis-constitute)
Your own site
<a href="https://agentmods.dev/skills/nagiliant/genesis-legacy-v2/genesis-constitute"><img src="https://agentmods.dev/badge/skills/nagiliant/genesis-legacy-v2/genesis-constitute/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 Constitute

Your own site · 80×15
<a href="https://agentmods.dev/skills/nagiliant/genesis-legacy-v2/genesis-constitute"><img src="https://agentmods.dev/badge/skills/nagiliant/genesis-legacy-v2/genesis-constitute.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 660 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 $0.00023 $0.00660
Opus 5 $0.00012 $0.00330
Sonnet 5 $0.00005 $0.00132
Haiku 4.5 $0.00002 $0.00066

Measured 11d ago against content hash 8e77c43abc8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

Constitute 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 11d 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.

skills/genesis-constitute/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Constitute — Write the Supreme Law

Create the constitution: the project's mission, technology/tools, architecture and organizational principles, standards, testing and quality philosophy, quality gates, security, performance, documentation, and version-control strategy. Everything built afterward must comply. The constitution is supreme — no spec, skill, or instruction may contradict it.

Runs immediately after discovery. Hard gate: refuses if .genesis/discovery/context.md is missing ("Run /genesis-discover first").

Inputs

  • .genesis/discovery/context.md (required)
  • .genesis/project-state.md
  • .genesis/templates/constitution-template.md
  • (--review) all .genesis/features/*/spec.md and .genesis/design/decisions/* (ADRs)

Process

  1. --review mode: read the existing constitution + all approved specs + ADRs and produce a drift report — sections that conflict with specs, shifted tech choices, abandoned patterns, suggested amendments. Then stop.
  2. Otherwise, read discovery and draft from the template.
  3. Populate the sections: Project Mission · Technology Stack (explicit, versioned — this is law) · Architecture Principles · Code Standards · Testing Philosophy · Quality Gates · Security & Compliance · Performance Expectations · Documentation Requirements · Version Control Strategy · Amendment Process.
  4. Quality Gates are load-bearing for the rest of the kit: name the exact build / test / lint commands the project uses (e.g. npm test, cargo test, pytest). /genesis-accept runs these and records the results.
  5. Present for review; iterate until the user explicitly approves.
  6. Log key decisions into the project-state.md Key Decisions table. Optionally offer to generate git hooks (commit-msg, pre-commit) and a CI workflow derived from the gates.

Mode additions

  • Brownfield: add a Legacy Handling section — for each area not meeting the constitution, mark Immediate refactor / Progressive migration (with deadline) / Grandfather clause (optional sunset).
  • Lowfield: reframe the code sections — Technology Stack → Tools & Formats · Architecture → Organizational Principles · Code Standards → Content Standards (voice, tone, style, terminology) · Testing → Quality Standards · Quality Gates → Completion Criteria.

Read the full file on GitHub · 52 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. 11d ago First seen · 52 lines · 23 tokens per session scan A 8e77c43abc8e

Subscribe to this mod's changes

Constitute is a skill published in the GitHub repository Nagiliant/Genesis-Legacy-V2 (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 660 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

auth-doctor

Diagnose and fix issues in existing auth setups. Scans environment, files, security, middleware, OAuth, database, and dangerous code patterns. Produces scored health report with actionable fixes.

ShipWithAI/shipwithai-plugins · 42 tokens

init

Set up the Claude Code harness for this project. Configures CLAUDE.md, permissions, hooks, MCP servers, agents, and SSOT docs based on your stack and chosen tier. Run on first setup or when CLAUDE.md is missing or has [PLACEHOLDER] markers. Trigger phrases: "set up harness", "configure claude", "onboard project"…

ShipWithAI/shipwithai-plugins · 96 tokens

new-project

Start a new project from scratch. 3-phase interview: project goals → tech stack → architecture → conventions. Scaffolds using official tools then configures the Claude Code harness. Run on an empty directory. Trigger phrases: "start a new project", "create project from scratch", "greenfield setup", "I have an empty…

ShipWithAI/shipwithai-plugins · 78 tokens

setup-memory

Configure project memory: write CLAUDE.md with architecture context and (Tier 3) set up a self-sustaining .claude/memory/ lifecycle — SessionStart load hook, Stop save-nudge hook, and a /save-memory skill that distills each session. Called by init or standalone to configure the memory pillar. Trigger phrases: "setup…

ShipWithAI/shipwithai-plugins · 89 tokens

optimize-harness

Analyze Claude Code tool call logs and suggest harness improvements based on actual usage patterns. Requires observability enabled + 7 days of data. Trigger phrases: "optimize harness", "harness suggestions", "improve my setup", "analyze tool usage", "what hooks should I add".

ShipWithAI/shipwithai-plugins · 64 tokens

implementation-plan

Define an incremental, reviewable, production-safe implementation plan for the active task and persist it as IMPLEMENTATIONPLAN.md plus a TASKSTATE.md update. Breaks work into the smallest safe slices with objective, exact scope, ordering rationale, key risks, validation approach, exit criteria, and work complexity…

Mozurok/fhorja.dev · 207 tokens