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/commands/zachjxyz/jvn/design)<a href="https://agentmods.dev/commands/zachjxyz/jvn/design"><img src="https://agentmods.dev/badge/commands/zachjxyz/jvn/design/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/commands/zachjxyz/jvn/design"><img src="https://agentmods.dev/badge/commands/zachjxyz/jvn/design.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 | $0.00007 | $0.00687 |
| Opus 5 | $0.00003 | $0.00344 |
| Sonnet 5 | $0.00001 | $0.00137 |
| Haiku 4.5 | $0.00001 | $0.00069 |
Grade A, and why
design 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design — Create the Technical Plan
You are orchestrating the planning phase. Follow these steps exactly.
User Input
$ARGUMENTS
If no feature name is provided, detect the current feature from the git branch name or the most recent specs/ directory.
Step 1: Generate Base Plan via Spec-Kit
Use the Skill tool to invoke the speckit-plan skill:
Skill(skill: "speckit-plan")
This generates:
specs/{feature}/plan.md— core implementation planspecs/{feature}/data-model.md— database schemaspecs/{feature}/contracts/— API contracts- Runs
update-agent-context.shto sync project context
Wait for completion.
Step 2: Architectural Review
Use the Task tool to invoke the architect agent:
Task(subagent_type: "architect",
description: "Architectural review of plan",
prompt: "Review the plan at specs/{feature}/plan.md and the spec at specs/{feature}/spec.md.
Evaluate:
- Component architecture and boundaries
- Data model design against PostgreSQL + SQLAlchemy patterns
- API contracts and endpoint design (FastAPI conventions)
- Technology choices against the stack (FastAPI + PostgreSQL + SQLAlchemy + PyTorch + pandas)
- Scalability, security, and maintainability risks
- ML pipeline design and model serving strategy
Append an '## Architectural Review' section to plan.md with your findings.")
Step 3: Constitutional Validation
Use the Task tool to invoke the constitutional-validator agent:
Task(subagent_type: "constitutional-validator",
description: "Validate plan against constitution",
prompt: "Validate the plan at specs/{feature}/plan.md against the project constitution at .specify/memory/constitution.md.
Check all dimensions: mission alignment, architectural alignment, complexity appropriateness, quality standards.
Append a '## Constitutional Review' section to plan.md with your verdict and findings.")
GATE: If the verdict is REJECTED or NEEDS REVISION, STOP. Present the issues to the user. Do NOT proceed to task generation.
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 · 94 lines · 7 tokens per session scan A 8c79d322905e
design is a command published in the GitHub repository zachjxyz/jvn (2 stars, last pushed 6mo ago), licensed MIT. It adds 7 tokens to every session and 687 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
fix-issue
Command "fix-issue" from KhaiTrang1995/claude-code-structure, covering /project:fix-issue – fix issue command, usage, description, shell steps and run tests after fix.
review
Command "review" from KhaiTrang1995/claude-code-structure, covering /project:review – code review command, usage, description, output format and shell step.
audit
Audit a project's Claude Code adoption and show the score with recommendations.
fix
Fix this project's missing Claude Code setup by writing real CLAUDE.md content, skills, and subagents.
generate-agents
Generate a few subagents matched to this project's detected language(s).
checklist
Generate a custom checklist for the current feature based on user requirements.