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 lgbarn/shipyard --skill shipyard-mapgit clone --depth 1 https://github.com/lgbarn/shipyardWrote 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/lgbarn/shipyard/shipyard-map)<a href="https://agentmods.dev/skills/lgbarn/shipyard/shipyard-map"><img src="https://agentmods.dev/badge/skills/lgbarn/shipyard/shipyard-map/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/skills/lgbarn/shipyard/shipyard-map"><img src="https://agentmods.dev/badge/skills/lgbarn/shipyard/shipyard-map.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 | $0.00088 | $0.00468 |
| Opus 5.5 | $0.00035 | $0.00187 |
| Sonnet 5.5 | $0.00018 | $0.00094 |
| Haiku 4.5 | $0.00009 | $0.00047 |
Grade A, and why
shipyard-map 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.
What it actually says
Mapping a codebase (Codex inline-sequential)
This is the mapper role from Shipyard's /shipyard:init and /shipyard:map flows, adapted
for Codex. In Claude Code, mapper runs as four parallel subagents (technology,
architecture, quality, concerns). Codex has no parallelism, so you cover the four focus
areas sequentially in this one context.
You are an analysis-only role. You MUST NOT modify any code — you read, analyze, and document. Bash is for discovery only (line counts, dependency checks, git history), never for changing files.
Degradation note: the four focus areas run one after another instead of in parallel, so a full map takes longer. The output quality is the same — only the wall-clock differs.
Focus areas (run each in turn)
- Technology →
STACK.md— languages, frameworks, build tooling, dependencies. - Architecture →
ARCHITECTURE.md— module boundaries, data flow, why the code is structured the way it is (not just a file listing). - Quality →
TESTING.md/CONVENTIONS.md— test posture, coverage gaps, conventions. - Concerns →
CONCERNS.md— where the real risks hide: fragile areas, tech debt, security-sensitive paths.
Rules
- Cite every finding with at least one repo-relative file path (e.g.
scripts/state-read.sh). Never assert without evidence. Never use absolute paths. - Merge, don't overwrite existing docs — update and date them rather than replacing.
- Surface insight, not surface-level inventory: explain why, and where the risks are.
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 · 35 lines · 88 tokens per session scan A 3e60c591db08
shipyard-map is a skill published in the GitHub repository lgbarn/shipyard (65 stars, last pushed 4d ago), licensed MIT. It adds 88 tokens to every session and 468 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
doc-digest
Turn a long document, PDF, transcript, spreadsheet or log into a compact working digest the conversation can continue from. Use when the user shares or pastes something long (several pages or more) and wants to discuss, analyze, compare or use it over more than one message, or asks to summarize a document so they can…
brainstorm
You MUST use this skill before /pm when work is ambiguous, scope is unclear, or multiple approaches exist. Explores problem space, proposes 2-3 approaches with trade-offs, and produces an approved spec document that feeds into both issue creation (/pm) and implementation planning (/cdt). Triggers: brainstorm, explore…
incident
Incident response and postmortem generation from git/deploy context. When something breaks in production, this skill builds a timeline, identifies the probable cause, and generates a structured postmortem document. Flags: --since, --service, --sev, --revert, --comms, --dry-run.
presentation
Generate PowerPoint (PPTX) presentations from a topic, outline, or content file. Creates professional slides using python-pptx with consistent theming and typography. Modes: [topic] (from scratch), from [file] (from markdown), --slides N, --theme dark|light|corporate, --outline-only, --out [path], --lang [code].
Documentation Hygiene ドキュメント衛生
A documentation review check for keeping permanent guides and public documents clean and purposeful. It distinguishes lasting instructions from temporary logs, decisions, and personal work notes, and looks for internal material in documents meant for others.
template-conventions
This skill should be used when the user asks to "plan a feature", "what goes in the phase file", "which file owns this", "what evidence class is this", "how do I verify a claim no test can settle", "where should this doc go", or when writing, reading or updating any zforge feature document under docs/{feature}/.…