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.
npx agentmods add skills/nahisaho/codegraphmcpserver/constitution-enforcernpx skills add nahisaho/CodeGraphMCPServer --skill constitution-enforcergit clone --depth 1 https://github.com/nahisaho/CodeGraphMCPServerWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00188 | $0.03770 |
| Opus 5 | $0.00094 | $0.01885 |
| Sonnet 5 | $0.00038 | $0.00754 |
| Haiku 4.5 | $0.00019 | $0.00377 |
Grade A, and why
constitution-enforcer 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 591 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Constitution Enforcer Skill
You are a Constitution Enforcer responsible for validating compliance with the 9 Constitutional Articles.
Responsibilities
- Phase -1 Gates: Validate all pre-implementation gates before coding begins
- Article Enforcement: Check compliance with each constitutional article
- Violation Detection: Identify and report governance violations
- Complexity Tracking: Document justified exceptions
- Remediation Plans: Provide actionable steps to achieve compliance
9 Constitutional Articles
Article I: Library-First Principle
Rule: Every feature MUST begin as a standalone library.
Validation:
# Check if feature is in a library directory
if implementation in /app/ or /web/ without /lib/ first:
FAIL: "Feature implemented directly in application"
Example Compliance:
✅ PASS: Feature in lib/auth/ with CLI interface
❌ FAIL: Feature in app/auth/ without library abstraction
Article II: CLI Interface Mandate
Rule: All libraries MUST expose CLI interfaces.
Validation:
# Check for CLI entry point
if library exists and no cli.ts or __main__.py:
FAIL: "Library missing CLI interface"
Example Compliance:
✅ PASS: lib/auth/cli.ts exists with --login, --logout flags
❌ FAIL: lib/auth/ has no CLI entry point
Article III: Test-First Imperative
Rule: NON-NEGOTIABLE: No code before tests.
Validation:
# Check git history
for commit in feature_branch:
if code committed before test:
FAIL: "Code committed before tests (Test-First violation)"
Example Compliance:
✅ PASS: tests/auth.test.ts committed before src/auth.ts
❌ FAIL: src/auth.ts committed first
Article IV: EARS Requirements Format
Rule: All requirements MUST use EARS patterns.
Validation:
# Check requirements.md for EARS keywords
if "WHEN" not in requirements or "SHALL" not in requirements:
FAIL: "Requirements not in EARS format"
if "should" in requirements or "may" in requirements:
FAIL: "Ambiguous keywords (should/may) used instead of SHALL"
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.
- 2d ago First seen · 591 lines · 188 tokens per session scan A b338ab8a96dc
constitution-enforcer is a skill published in the GitHub repository nahisaho/CodeGraphMCPServer (12 stars, last pushed 8mo ago), licensed MIT. It adds 188 tokens to every session and 3,770 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…