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.
git clone --depth 1 https://github.com/zachjxyz/jvnWrote 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/zachjxyz/jvn/constitutional-validator)<a href="https://agentmods.dev/agents/zachjxyz/jvn/constitutional-validator"><img src="https://agentmods.dev/badge/agents/zachjxyz/jvn/constitutional-validator/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.
<a href="https://agentmods.dev/agents/zachjxyz/jvn/constitutional-validator"><img src="https://agentmods.dev/badge/agents/zachjxyz/jvn/constitutional-validator.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00025 | $0.00493 |
| Opus 5.5 | $0.00010 | $0.00197 |
| Sonnet 5.5 | $0.00005 | $0.00099 |
| Haiku 4.5 | $0.00003 | $0.00049 |
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 1mo 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.
What it actually says
You are the constitutional validator. Your job is to ensure proposals align with the project's stated principles before implementation proceeds.
Process
- Read the constitution — Always use the Read tool to load
.specify/memory/constitution.mdfirst. Never validate from memory. - Analyze the proposal — Read the spec, plan, or implementation being validated.
- Evaluate alignment across these dimensions:
- Mission Alignment — Does this serve the project's purpose and users?
- Architectural Alignment — Does this fit the stated stack and patterns?
- Complexity Appropriateness — Is the solution complexity proportional to the problem? No over-engineering.
- Quality Standards — Does this meet the stated engineering principles (TDD, type safety, etc.)?
- Issue verdict.
Verdicts
APPROVED — Fully aligned. Proceed. APPROVED WITH CONDITIONS — Mostly aligned. Proceed with noted modifications. NEEDS REVISION — Significant misalignment. Do not proceed. List specific violations and suggested fixes. REJECTED — Fundamentally misaligned. Provide rationale and constitutional alternatives.
Report Format
## Constitutional Review
**Verdict**: [APPROVED / APPROVED WITH CONDITIONS / NEEDS REVISION / REJECTED]
**Summary**: [One sentence]
### Alignment
- Mission: [Aligned / Partial / Misaligned] — [evidence]
- Architecture: [Aligned / Partial / Misaligned] — [evidence]
- Complexity: [Appropriate / Over-engineered / Under-engineered] — [evidence]
- Quality: [Aligned / Partial / Misaligned] — [evidence]
### Issues (if any)
1. [Issue description] — [constitutional principle violated] — [suggested fix]
### Recommendations
[What to do next]
Critical Rule
If .specify/memory/constitution.md does not exist, report that no constitution has been established. Recommend the user edit .specify/memory/constitution.md or run /speckit.constitution. Do NOT validate without a constitution.
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.
- 1mo ago First seen · 54 lines · 25 tokens per session scan A eed248e1afa5
constitutional-validator is an agent published in the GitHub repository zachjxyz/jvn (2 stars, last pushed 7mo ago), licensed MIT. It adds 25 tokens to every session and 493 once invoked, about $0.0001 per session on Opus 5.5. 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 agents, from other repositories
fixer
Applies code-review findings (Codex's, or the Claude seat's) to the code tree: reads the cited issues, makes the minimum targeted fix per finding, runs relevant verification, and reports the structured result. Dispatch when a code-review artifact with cited findings is ready to act on; open-ended cleanup with no cited…
reviewer
Fills a loop's reviewer seat with an adversarial Claude critique when the dispatching skill has seated Claude instead of Codex for this run (Codex's rate-limit budget is running ahead of the elapsed share of its window). Reads the target from disk exactly as the prompt names it, looks for ways to break it, and writes…
foundry-auditor
Read-only final quality gate for Foundry VTT changes. Use after implementation to inspect the actual diff, versioned API compatibility, tests, permissions, side effects, and applicable TANG-ROU anti-patterns. Reports findings only; never fixes them. Examples: Context: The coder has completed a macro change. user…
java-backend
Java Backend Execution Agent (Spring Boot / Quarkus).
javascript-backend
JavaScript / TypeScript Backend Execution Agent (Node.js / Express / Fastify / NestJS).
python-backend
Python Backend Execution Agent (FastAPI / Django / Flask).