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 skills/shipwrights/core/shipwrights-upgradenpx skills add shipwrights/core --skill shipwrights-upgradegit 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-upgrade)<a href="https://agentmods.dev/skills/shipwrights/core/shipwrights-upgrade"><img src="https://agentmods.dev/badge/skills/shipwrights/core/shipwrights-upgrade.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 | $0.00059 | $0.01055 |
| Opus 5 | $0.00030 | $0.00528 |
| Sonnet 5 | $0.00012 | $0.00211 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
shipwrights-upgrade 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 6d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/shipwrights-upgrade — bump templates + run migrations
When the plugin updates and the consumer wants the new templates, schema fixes, or new defaults — without losing their edits.
What you do
1. Pre-checks
- Working tree clean. Refuse if dirty.
.shipwrights.ymlexists. Refuse if not (direct to/shipwrights-init).- Read the current config's
versionfield. - Read the plugin's
lib/migrations/directory — list of migrations from version N → N+1.
2. Run config migrations
For each migration from <consumer-version> to <plugin-current-version>:
- Load
migrations/<from>-to-<to>.mjs. - Apply: takes the parsed config, returns the migrated config.
- Migrations are pure functions — they don't write files; they transform the YAML object.
After all migrations: write the new .shipwrights.yml with version: <plugin-current-version> and the migrated content. Don't write yet — accumulate; commit at the end.
3. Diff templates
For each path under templates/:
- Render the current plugin's template against the migrated config. Call this
template-current. - Read the consumer's existing file (if any). Call this
consumer-current. - Read the plugin's template at the consumer's previous installed version. Call this
template-old. (Tracked via.shipwrights/installed.json.)
Three cases:
- Consumer hasn't edited —
consumer-current == template-old. Just writetemplate-currentover it. No conflict. - Plugin hasn't changed —
template-current == template-old. Skip silently. - Both changed — 3-way merge between
template-old(base),consumer-current(theirs),template-current(ours). If clean: write the merge. If conflicted: write the file with conflict markers and add it to a "conflicts" list for the user to resolve.
4. Show the plan
Upgrading @shipwrights/core: 0.1.0 → 0.2.0
Config migrations:
- 1-to-2: rename `lock.kind` → `lock.backend`
- 2-to-3: add `telemetry.budget_per_epic_tokens` default
Templates:
- .github/workflows/auto-merge-low-tier.yml: clean update
- scripts/shipwrights/integrate-scratch.mjs: 3-way merge clean
- scripts/shipwrights/update-epic-after-merge.mjs: ⚠ CONFLICT — resolve manually
- docs/process/team-orchestration.md: skipped (consumer-owned)
New files this version:
- scripts/shipwrights/cost-telemetry.mjs
Proceed? [y/N]
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.
- 6d ago First seen · 112 lines · 59 tokens per session scan A a71db9ae530e
shipwrights-upgrade is a skill published in the GitHub repository shipwrights/core (2 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,055 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…