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 skills add shipwrights/core --skill shipwrights-spec-approvegit clone --depth 1 https://github.com/shipwrights/coreWrote 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/skills/shipwrights/core/shipwrights-spec-approve)<a href="https://agentmods.dev/skills/shipwrights/core/shipwrights-spec-approve"><img src="https://agentmods.dev/badge/skills/shipwrights/core/shipwrights-spec-approve.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 | $0.00054 | $0.00438 |
| Opus 5 | $0.00027 | $0.00219 |
| Sonnet 5 | $0.00011 | $0.00088 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
shipwrights-spec-approve 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.
What it actually says
/shipwrights-spec-approve — accept a drafted spec
You have read the plan document at <spec.output_dir>/<id>-*.md and decided it's good to build.
What you do
- Validate the spec exists and is at
status: drafted. - Re-run citation enforcement on the plan body against the manifest at
.shipwrights/specs/<id>.manifest.json. This catches the case where the user edited the plan between draft and approve and introduced uncited claims. - Flip frontmatter
status: drafted→status: approved. - Commit on a small chore branch:
chore(spec): approve <id>. - Print next-step: hand off to the standard build pipeline (which works against the approved spec the same way it works against an approved epic).
Hard rules
- Refuse if the spec isn't
drafted. Other statuses need different handling (revise, cancel, or simply later in the pipeline). - Refuse if the working tree is dirty. The approve commit should be a clean marker.
- Honour
spec.enforcement. Strict mode blocks on uncited claims; loose mode warns.
Failure modes
| Symptom | What to do |
|---|---|
Spec at approved/building/... |
Refuse; suggest the right next slash command for that state |
| Manifest missing | In strict mode, refuse; in loose mode, warn and proceed |
| Dirty working tree | Refuse; ask user to commit/stash |
| Edits to the plan introduced uncited claims | List them; suggest revise |
Output
✓ Spec <id> approved.
Next: /shipwrights-spec-build <id>
The CLI implementation lives at lib/commands/spec-approve.mjs — same behaviour either way.
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 · 41 lines · 54 tokens per session scan A 061cd3d7ad54
shipwrights-spec-approve is a skill published in the GitHub repository shipwrights/core (2 stars, last pushed 1mo ago), licensed MIT. It adds 54 tokens to every session and 438 once invoked, about $0.0003 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 skills, from other repositories
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
vertical-real-estate
Residential-proptech domain knowledge so architect / pm aren't naive when speccing real-estate products (listings, lead-crm, transaction-coordination, property-mgmt). Codifies MLS/IDX reality, listing status lifecycle + syndication canonical-source, long-cycle lead nurture, transaction-coordination as the high-pain…
product-economics
Does this product make money at a price someone will pay? Forces contribution margin, a price with a stated basis, and a bottom-up market size — each number labelled measured / assumed / unknown, so a guess can never be read as a calculation.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
cost-model
Standardized cost-estimation framework for greatcto plans. Forces explicit LLM cost, infra cost, human-supervision time, and the (defensible) human-equivalent comparison. Output format is parsable by the board's /api/cost path — must follow exactly.
migration-ready-schema
Data-model rules that make a schema importable from day one, so the migration-import-engineer is never blocked on missing columns. Every SMB Product-Builder product must let a customer bring their data from an incumbent (ServiceTitan/Toast/Mindbody/Shopify) — that requires provenance (sourceref) and rollback…