speckit.constitution

speckit.constitution is a skill for Claude Code, Codex from wedabro/bro-skills. It costs 21 tokens per session (509 once invoked), scanned A, original, MIT.

A project governance manager that creates and maintains a constitution: a document containing the project’s technical rules and non-negotiable requirements. It can cover infrastructure, security, coding standards, Docker, and monorepo rules.

In plain words
What is it for?
Use it to record the technology stack, security requirements, environment and container rules, shared-package contracts, and build requirements for a project.
Why use it?
It gives coding agents a shared source of truth for decisions that should remain consistent across the project. A monorepo is one repository containing multiple applications or packages.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it to record the technology stack, security requirements, environment and container rules, shared-package contracts, and build requirements for a project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wedabro/bro-skills/speckit.constitution
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 wedabro/bro-skills --skill speckit.constitution
Clone the repo
git clone --depth 1 https://github.com/wedabro/bro-skills

Made for: Claude Code, Codex.

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 speckit.constitution

README.md
[![agentmods](https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.constitution/github.svg)](https://agentmods.dev/skills/wedabro/bro-skills/speckit.constitution)
Your own site
<a href="https://agentmods.dev/skills/wedabro/bro-skills/speckit.constitution"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.constitution/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 speckit.constitution

Your own site · 80×15
<a href="https://agentmods.dev/skills/wedabro/bro-skills/speckit.constitution"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.constitution.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 509 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 $0.00021 $0.00509
Opus 5 $0.00010 $0.00254
Sonnet 5 $0.00004 $0.00102
Haiku 4.5 $0.00002 $0.00051

Measured 10d ago against content hash 9addf5ffd24b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

speckit.constitution 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 10d 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.

.agents/skills/speckit.constitution/SKILL.md · 48 lines

What it actually says

🎯 Mission

Create and maintain constitution.md — the "supreme law" that every agent must comply with.

📥 Input

  • Developer provides: tech stack, principles, constraints
  • .agents/knowledge_base/infrastructure.md (if available)

📋 Protocol

  1. Collected from developers:
    • Tech stack (frameworks, DB, language)
    • Docker ports (cấu hình qua biến môi trường)
    • Coding principles (VD: No hardcode, API-first)
    • Security requirements
  2. Create/update .agents/memory/constitution.md with REQUIRED sections:
    • §1 Infrastructure: Docker-first policy, port allocation, environments
    • §2 Security: No root containers, no hardcoded secrets, multi-stage builds
    • §3 Code Standards: Language, naming conventions, ENV policy
    • §4 Non-Negotiables: List of rules that should NEVER be violated
    • §5 Monorepo Rules (if monorepo):
      • Shared Package Contract: type exports is the source of truth
      • Build Independence: each app must be compiled independently
      • Package exports must match actual file structure
    • §6 Docker Deployment Rules:
      • Volume shadowing ( - .:/app ) is PROHIBITED in production/beta
      • Dockerfile COPY paths must exist
      • CMD entrypoint must match build output
      • Next.js apps must have a public/ folder
    • §7 Build-time Safety (if Next.js):
      • SSG pages (sitemap, generateStaticParams): API calls must be try-catch
      • fetchApi must return null/empty if API_URL is undefined
    • §8 Pre-Deploy Checklist:
      • docker compose build succeeded
      • All services Up (not Restarting )
      • Health check: 200 OK
  3. Validate: Each section must have at least 1 specific rule, not general.

📤 Output

  • File: .agents/memory/constitution.md

🚫 Guard Rails

  • Constitution does NOT contain implementation details (HOW) — only rules (WHAT).
  • Each rule must be testable (can be verified with code/check).
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. 10d ago First seen · 48 lines · 21 tokens per session scan A 9addf5ffd24b

Subscribe to this mod's changes

speckit.constitution is a skill published in the GitHub repository wedabro/bro-skills (2 stars, last pushed 14d ago), licensed MIT. It adds 21 tokens to every session and 509 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.