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/build)<a href="https://agentmods.dev/commands/zachjxyz/jvn/build"><img src="https://agentmods.dev/badge/commands/zachjxyz/jvn/build.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 | $0.00015 | $0.00891 |
| Opus 5 | $0.00008 | $0.00445 |
| Sonnet 5 | $0.00003 | $0.00178 |
| Haiku 4.5 | $0.00002 | $0.00089 |
Grade A, and why
build 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 7d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/build — Implement the Feature
You are orchestrating the implementation phase. Follow these steps exactly.
User Input
$ARGUMENTS
Parse arguments:
- Feature name (or detect from git branch / most recent
specs/directory) --phase N— execute specific phase only (optional)
Prerequisites
Before starting, verify these files exist:
specs/{feature}/spec.mdspecs/{feature}/plan.mdspecs/{feature}/tasks.md
If any are missing, tell the user which step to run first (/spec, /design).
Phase Implementation Loop
For each phase in specs/{feature}/tasks.md:
Step 1: Implement
Use the Skill tool to invoke spec-kit implementation for the current phase:
Skill(skill: "speckit-implement")
Tell it to follow TDD: write the failing test first, then implement the minimal code to pass.
Step 2: Run Tests
Use the Skill tool to invoke webapp-testing for validation:
Skill(skill: "webapp-testing")
Run Playwright tests against the implementation. If tests fail, fix and re-run before proceeding.
Step 3: Code Review
Use the Task tool to invoke the code-reviewer agent:
Task(subagent_type: "code-reviewer",
description: "Review Phase N implementation",
prompt: "Review the implementation changes for Phase N of {feature}.
Check: correctness, TDD compliance, security, performance, maintainability.
Use your preloaded review-checklist and test-driven-development skills.
Provide your verdict: APPROVED / APPROVED WITH SUGGESTIONS / NEEDS REVISION.")
If NEEDS REVISION: Present the blockers to the user, fix the issues, then re-run the review.
Step 4: User Validation Gate
STOP. Present the following to the user and wait for their decision.
## Phase N Validation
### Deliverables
- [x] [Deliverable 1] — [what was done]
- [x] [Deliverable 2] — [what was done]
### Files Changed
| File | Change | Lines |
|------|--------|-------|
| path | add/modify | ±N |
### Tests
- Unit: [PASS/FAIL]
- Integration: [PASS/FAIL]
- Build: [SUCCESS/FAIL]
### Code Review
- Verdict: [reviewer's verdict]
- Issues: [list or "none"]
**Your decision:**
- PASS — proceed to next phase
- CONDITIONAL PASS — note issues, proceed
- FAIL — fix issues before proceeding
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.
- 7d ago First seen · 148 lines · 15 tokens per session scan A 560edf0c935c
build is a command published in the GitHub repository zachjxyz/jvn (2 stars, last pushed 6mo ago), licensed MIT. It adds 15 tokens to every session and 891 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.
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.