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/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/context)<a href="https://agentmods.dev/commands/vimalk0703/shipworthy/context"><img src="https://agentmods.dev/badge/commands/vimalk0703/shipworthy/context/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/vimalk0703/shipworthy/context"><img src="https://agentmods.dev/badge/commands/vimalk0703/shipworthy/context.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 | $0.00000 | $0.00701 |
| Opus 5.5 | $0.00000 | $0.00280 |
| Sonnet 5.5 | $0.00000 | $0.00140 |
| Haiku 4.5 | $0.00000 | $0.00070 |
Grade A, and why
context 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before executing this command, output:
⚓ shipworthy › command:
/context— analyzing context health and completeness
Run a context health analysis for this project. Invoke the context-manager skill and check these dimensions:
Process
1. Context Infrastructure
Check which standard files exist in .shipworthy/:
| File | Purpose | Status |
|---|---|---|
architecture.md |
Architecture constraints and mandatory rules | exists / missing |
regression-fence.md |
Anti-pattern protection (NEVER/ALWAYS rules) | exists / missing |
config.json |
Project configuration and preset | exists / missing |
INDEX.md |
Memory index (auto-generated) | exists / missing |
learnings/ |
At least one learning file | exists / missing |
sessions/ |
At least one session file | exists / missing |
decisions/ |
Architecture decision records | exists / missing |
plans/ |
Implementation plans | exists / missing |
Also check if CLAUDE.md exists at the project root.
2. Regression Fence Health
- Count rules (H2 headings in
regression-fence.md) - 0 rules = no protection — recommend running
/retroafter next session - 1-15 rules = healthy
- 16-20 rules = near cap, consider pruning stale entries
- Check if any rules reference files/functions that no longer exist in the codebase
3. Session Signals
- Does
.shipworthy/.session-signalsexist? - If yes, count lines — these are unprocessed signals from hooks
- If > 0: recommend running
/retroor starting a new session (auto-retro triggers at session start)
4. Context Completeness
- Estimate total characters loaded at session start (architecture spec + fence + plans + sessions + learnings)
- Show percentage of 8000-char context budget used
- Identify gaps: "You have architecture.md but no regression fence — corrections from past sessions will repeat"
5. Actionable Suggestions
Based on analysis, suggest specific next actions. Examples:
- "12 unprocessed signals — run
/retroto convert them into learnings and fence entries" - "No regression fence yet — it will be auto-created when you run
/retroafter your next work session" - "3 learning files cover overlapping topics —
/retrowill offer to consolidate them" - "Architecture spec missing — start building with
/scaffoldor thearchitecture-awarenessskill" - "CLAUDE.md has no pointer to
.shipworthy/— consider adding:Read .shipworthy/INDEX.md for full project memory"
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 · 77 lines · 0 tokens per session scan A 944c1d71a596
context is a command published in the GitHub repository Vimalk0703/shipworthy (6 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 701 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-reverse
Camada semântica da engenharia reversa (Fase 0 / brownfield). Roda depois do comando dare reverse, que já varreu o código e gerou os esqueletos. Sua função é preencher as inferências que o CLI determinístico não faz: propósito, domínio, responsabilidades e os diagramas de fluxo ("como a coisa funciona").
dare-rust-leptos
Guia de desenvolvimento Leptos para projetos DARE. Cobre decisão de variante, idioms obrigatórios, antipatterns, tipos compartilhados e templates de tasks.
dare-rust-workspace
Decisão e migração de Cargo workspace multi-crate para projetos Rust/Axum. Cobre dois cenários.
dare-security
Guia completo de segurança para todas as fases do DARE. Use para: revisar o DESIGN/BLUEPRINT com foco em segurança, implementar controles em uma task específica, ou auditar o projeto existente.
dare-blueprint
Gera somente DARE/BLUEPRINT.md a partir do DARE/DESIGN.md.
dare-dag-build
Regenera apenas o DARE/dare-dag.yaml a partir do DARE/BLUEPRINT.md já existente, sem refazer o blueprint nem as specs. Útil quando o BLUEPRINT mudou pouco mas você precisa que o grafo reflita o novo estado.