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-researchgit 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-research)<a href="https://agentmods.dev/skills/lgbarn/shipyard/shipyard-research"><img src="https://agentmods.dev/badge/skills/lgbarn/shipyard/shipyard-research.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 | $0.00079 | $0.00418 |
| Opus 5 | $0.00039 | $0.00209 |
| Sonnet 5 | $0.00016 | $0.00084 |
| Haiku 4.5 | $0.00008 | $0.00042 |
Grade A, and why
shipyard-research 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
Domain research (Codex inline-sequential)
This is the researcher role from Shipyard, adapted for Codex. In Claude Code a researcher subagent gathers domain knowledge before a plan; here you adopt the role yourself.
You produce a research document — you do not implement anything in this role.
Degradation note: in Claude Code this runs in a fresh context isolated from implementation. Here it shares context, so guard against motivated reasoning — research honestly about tradeoffs, do not cheerlead the option you'd find easiest to build.
Protocol
- Understand the context. Read existing
.shipyard/docs (STACK.md, ARCHITECTURE.md, ROADMAP.md) and the codebase conventions. Research that ignores the current stack and constraints is useless. Runscripts/state-read.shfirst if state isn't loaded. - Investigate options. For each candidate technology/approach, gather: maturity and community health, maintenance burden, fit with the existing stack, and known pitfalls.
- Be honest about tradeoffs. Technology decisions are not just feature checklists — weigh maintenance, hiring, and long-term viability. Name the cost of each option, not just its benefits.
- Recommend. Give a clear recommendation with reasoning, and note what would change the recommendation.
Deliverable
A structured research document: the question, the options compared (with tradeoffs), a recommendation, and open risks. Cite sources for external claims; cite repo-relative file paths for claims about the existing codebase.
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 · 35 lines · 79 tokens per session scan A 6fcacfbb6a2b
shipyard-research is a skill published in the GitHub repository lgbarn/shipyard (65 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 418 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
code-review
The depth half of a review - the dimensions a diff is read against (correctness, boundaries, concurrency, failure paths, secrets, data access, structure, test quality) and the rule that a finding is refuted before it is reported. The verdict stays with the reviewer agent. Use when reviewing a diff or a pull request…
deslop
The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.
loop-test
A local experiment for designing repeating checks with Claude Code’s loop command. It covers both fixed intervals and checks that schedule themselves again after each run.
take-task
A workflow for claiming a tracker task and preparing the development branch for it. It verifies the task, marks it as in progress, checks for uncommitted changes, and handles branch setup according to the task state.
goal-plan-clean
A guide for creating a reusable plan-review loop. It repeatedly checks a plan, fixes blocking issues and suggestions, and stops after approval or a small number of review rounds.