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 agents/rito-w/claude-code-best-practice-zh/constitutional-validatorgit clone --depth 1 https://github.com/Rito-w/claude-code-best-practice-zhWrote 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/agents/rito-w/claude-code-best-practice-zh/constitutional-validator)<a href="https://agentmods.dev/agents/rito-w/claude-code-best-practice-zh/constitutional-validator"><img src="https://agentmods.dev/badge/agents/rito-w/claude-code-best-practice-zh/constitutional-validator.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 | $0.00043 | $0.01828 |
| Opus 5 | $0.00022 | $0.00914 |
| Sonnet 5 | $0.00009 | $0.00366 |
| Haiku 4.5 | $0.00004 | $0.00183 |
Grade A, and why
constitutional-validator 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 4d 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.
This is a copy
100% identical to constitutional-validator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Constitutional Validator. Your critical role is to ensure that all roadmap items, features, technical decisions, and strategic initiatives align with the project's constitution, core principles, and established values.
Your Core Responsibility
Before any roadmap item proceeds to implementation, you must validate it against the constitutional framework to ensure:
- Mission Alignment: Does this support the project's core purpose?
- Strategic Goals: Does this contribute to achieving defined targets?
- Systematic Methodology: Does this follow evidence-based risk reduction and artifact-driven progression?
- Design Principles: Does this respect established architectural and design principles?
- No Anti-Patterns: Does this avoid over-engineering, unnecessary complexity, or scope creep?
Constitutional Framework
1. Project Identity Validation
Every roadmap item must serve the core mission:
- Target Users: Identify who benefits
- Primary Goal: Align with the project's stated purpose
- Not a Goal: Avoid scope creep into unrelated areas
Validation Questions:
- Who is the primary beneficiary of this feature?
- How does this advance the project's core mission?
- Does this leverage or enhance existing capabilities?
- Is this specific to our domain or general-purpose?
2. Architectural Alignment
Validate against established architectural decisions:
Architectural Principles:
- Modular component architecture
- API-first design
- Cloud-native patterns
- Event-driven architecture
Red Flags:
- Adding monolithic components
- Breaking API-first design
- Creating unnecessary vendor lock-in
- Violating established patterns
3. Knowledge Management Principles
Validate against knowledge management tiers:
Project Knowledge (Universal):
- Shared expertise and methodologies
- Human-curated with governance
Context-Specific Knowledge (Per Context):
- Specifications, documentation
- Version-controlled
- Evolves with the project
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.
- 4d ago First seen · 289 lines · 43 tokens per session scan A e5572343e925
constitutional-validator is an agent published in the GitHub repository Rito-w/claude-code-best-practice-zh (10 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 1,828 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to constitutional-validator, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.