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 commands/vimalk0703/shipworthy/diagnosegit clone --depth 1 https://github.com/Vimalk0703/shipworthyWrote 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/vimalk0703/shipworthy/diagnose)<a href="https://agentmods.dev/commands/vimalk0703/shipworthy/diagnose"><img src="https://agentmods.dev/badge/commands/vimalk0703/shipworthy/diagnose.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 | $0.00000 | $0.00560 |
| Opus 5 | $0.00000 | $0.00280 |
| Sonnet 5 | $0.00000 | $0.00112 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
diagnose 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before executing this command, output:
⚓ shipworthy › command:
/diagnose— analyzing project infrastructure gaps
Run a full project infrastructure diagnosis.
Unlike /audit (which reviews code quality), this command checks what's missing entirely from the project.
Process
-
Run through the
project-diagnosisskill checklist:- Testing infrastructure (test directory, runner, coverage, actual tests)
- CI/CD configuration (workflows, test step, lint step)
- Security basics (.env in .gitignore, no hardcoded secrets, input validation, dependency audit)
- Code quality tools (linter, formatter, type checking)
- Architecture & documentation (architecture spec, README, .gitignore)
- Deployment readiness (health endpoint, structured logging, error tracking, env config)
-
Present findings organized by severity:
- Critical — fix immediately (security risks, secrets exposure)
- High — fix soon (no tests, no input validation)
- Medium — improve when convenient (no CI, no linter)
- Low — nice to have (no health endpoint, no .env.example)
- Passed — checks that passed (show as confirmation)
-
After presenting the report, ask the user:
"Want me to auto-fix what I can? I'll create missing configs and infrastructure files. I won't modify existing code without your approval."
-
If the user approves, dispatch the
project-doctoragent (viasubagent-driven-development) to fix the gaps. -
After fixes, re-run the checklist and show before/after comparison.
Example Output
## Project Diagnosis Report
### Critical (fix immediately)
- [ ] .env not in .gitignore — secrets may be committed to git
### High (fix soon)
- [ ] No test files found — need tests/ directory and at least one test
- [ ] No input validation on API routes — install Zod and validate inputs
### Medium (improve when convenient)
- [ ] No CI configuration — need .github/workflows/ci.yml
- [ ] No linter — need ESLint with strict config
### Low (nice to have)
- [ ] No health endpoint for monitoring
- [ ] No .env.example documenting required environment variables
### Passed
- [x] .gitignore exists
- [x] README.md exists
- [x] TypeScript strict mode enabled
- [x] No hardcoded secrets detected
- [x] Dependencies have no critical vulnerabilities
---
Score: 5/12 checks passed
Want me to auto-fix what I can?
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 · 65 lines · 0 tokens per session scan A 947d118adcb5
diagnose is a command published in the GitHub repository Vimalk0703/shipworthy (7 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 560 tokens. 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
dare-blueprint
Gera somente DARE/BLUEPRINT.md a partir do DARE/DESIGN.md.
dare-rust-workspace
Decisão e migração de Cargo workspace multi-crate para projetos Rust/Axum. Cobre dois cenários.
dare-laravel-api
Padrões DARE para APIs REST em Laravel 11 + PHP 8.3. Strict Types, FormRequests, Services, Resources, Repositories, Eloquent + casts, tratamento global de exceções, testes Pest, PHPStan/Larastan nível 8.
dare-refine
Analisa a complexidade de uma task e, quando alta, quebra em sub-tasks menores com escopo bem delimitado. Pode ser chamada.
dare-review
Audita uma task implementada cruzando a spec (DARE/EXECUTION/ .md) com os arquivos reais que ela tocou. Detecta stubs, mocks fora de testes, funções vazias, TODOs, retorno-fantasma — e valida critério-a-critério se a implementação satisfaz o que a spec prometeu.
dare-bugfix-design
Diagnostica bug em projeto existente e planeja correção cirúrgica via Método DARE. Gera DARE/DESIGN-Bugfix-[Nome].md com causa raiz, riscos de regressão e plano de ação mínimo.