Borrowing it
Nothing to install: this file belongs to plipowczan/claude-piv-skeleton. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/plipowczan/claude-piv-skeleton/main/.claude/commands/piv_loop/constitution.mdgit clone --depth 1 https://github.com/plipowczan/claude-piv-skeletonWrote 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.
[](https://agentmods.dev/commands/plipowczan/claude-piv-skeleton/constitution)<a href="https://agentmods.dev/commands/plipowczan/claude-piv-skeleton/constitution"><img src="https://agentmods.dev/badge/commands/plipowczan/claude-piv-skeleton/constitution.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00006 | $0.00729 |
| Opus 5 | $0.00003 | $0.00365 |
| Sonnet 5 | $0.00001 | $0.00146 |
| Haiku 4.5 | $0.00001 | $0.00073 |
Grade A, and why
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 8d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Constitution: Define Project Principles
Goal: Create a project constitution that guides all AI-assisted development decisions.
Execution
- Check if
.claude/memory/constitution.mdexists - If exists, read it and summarize current principles
- If not, offer to create from template
What is a Constitution?
A constitution is a one-time document that defines:
- Project purpose: What this project is and why it exists
- Core principles: Quality standards, testing requirements, code style
- Technology stack: Frameworks, languages, databases
- Technical constraints: What to use and what to avoid
- Development guidelines: Git workflow, code review, testing
- Security requirements: Security standards and practices
- Performance requirements: Performance targets
Why Create a Constitution?
Benefits:
- Guides all AI decisions for consistent output
- Single source of truth for project choices
- Reduces ambiguity in technical decisions
- Onboards new developers quickly
- Prevents technical debt through clear principles
Constitution vs. Spec Artifacts
| Aspect | Constitution | Spec/Plan/Tasks |
|---|---|---|
| Scope | Entire project | Single feature |
| Frequency | Once per project | Per feature |
| Changes | Rarely | Often |
| Content | Principles, stack, guidelines | Requirements, approach, steps |
Location
Constitution is stored at: .claude/memory/constitution.md
This file is read automatically during:
/piv-speckit:plan-feature- Planning phase reads constitution/piv-speckit:prime- Prime checks for constitution existence
Template
Use this structure when creating constitution:
# Project Constitution
**Last Updated:** {DATE}
**Project:** {PROJECT_NAME}
## Purpose
{What this project is and why it exists}
## Core Principles
1. **Quality First**
- {Your quality standards}
2. **Testing**
- TDD is mandatory
- 80%+ test coverage
- Integration tests for critical paths
3. **Code Style**
- {Your style preferences}
## Technology Stack
**Backend:**
- Framework: {e.g., Spring Boot 3.2}
- Language: {e.g., Java 21}
- Database: {e.g., PostgreSQL 16}
**Frontend:**
- Framework: {e.g., React 19}
- Language: {e.g., TypeScript}
- Styling: {e.g., TailwindCSS}
## Technical Constraints
**Use:**
- {Technology choices to use}
**Avoid:**
- {Anti-patterns to avoid}
## Development Guidelines
**Git Workflow:**
- Branch from: `main`
- Commit style: Conventional Commits
- PR required: Yes
**Code Review:**
- Required for: All changes
- Reviewers: {Who reviews}
**Testing:**
- Required before: All commits
- Test command: {e.g., `mvn test`}
## Security Requirements
- {Security requirements}
## Performance Requirements
- {Performance targets}
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.
- 8d ago First seen · 135 lines · 6 tokens per session scan A 44573a60e5d8
constitution is a command published in the GitHub repository plipowczan/claude-piv-skeleton (4 stars, last pushed 7mo ago), licensed MIT. It adds 6 tokens to every session and 729 once invoked, about $0.0000 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.