Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/lgbarn/shipyardnpx agentmods add skills/lgbarn/shipyard/shipyard-stateWrote 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-state)<a href="https://agentmods.dev/skills/lgbarn/shipyard/shipyard-state"><img src="https://agentmods.dev/badge/skills/lgbarn/shipyard/shipyard-state.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 | $0.00098 | $0.00622 |
| Opus 5 | $0.00049 | $0.00311 |
| Sonnet 5 | $0.00020 | $0.00124 |
| Haiku 4.5 | $0.00010 | $0.00062 |
Grade A, and why
shipyard-state 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 7d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shipyard state (Codex on-demand)
In Claude Code, Shipyard's SessionStart hook auto-injects project state at the start of
every session. Codex has no such hook, so state is not loaded automatically — you must
read it on demand with the bundled scripts before acting. All state lives under .shipyard/
(STATE.json, HISTORY.md, ROADMAP.md, PROJECT.md, config.json).
Always run the read step first; if .shipyard/STATE.json is absent, tell the user there is
no Shipyard project here (suggest shipyard init) instead of inventing state.
Status — show the dashboard
bash scripts/state-read.sh # prints JSON context (current phase, position, status)
Then also read .shipyard/HISTORY.md and ROADMAP.md for the fuller picture, and present a
clear dashboard: current phase, position, status, and recent history.
Resume — restore context and continue
bash scripts/state-read.sh
Read STATE.json for the current phase/position/status and HISTORY.md for what happened, then continue the workflow from there. If no state exists, there is nothing to resume.
Cancel — graceful pause
Checkpoint first, then mark the work paused so it can be resumed later:
bash scripts/checkpoint.sh "pre-cancel-$(date +%s)" # git tag rollback point
bash scripts/state-write.sh --phase <N> --position "<where you stopped>" --status paused
Only cancel work that is actually in progress (building/in_progress/planning). If it is
already paused or complete, say so rather than writing redundant state.
Roll back — restore a checkpoint
Checkpoints are git tags created by checkpoint.sh. List them and revert with git:
git tag -l 'shipyard-*' # or however the project tags checkpoints
git checkout <checkpoint-tag> # inspect, or reset per the user's intent
This is a destructive git operation — confirm with the user before resetting, and never force-reset their working tree without explicit instruction.
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.
- 7d ago First seen · 63 lines · 98 tokens per session scan A ec10b70c0db6
shipyard-state is a skill published in the GitHub repository lgbarn/shipyard (65 stars, last pushed 1mo ago), licensed MIT. It adds 98 tokens to every session and 622 once invoked, about $0.0005 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.
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.
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.
create-task
This skill should be used when creating a task in the active tracker - "create task", "create issue", "bd create", "new task", "add task", "add issue". Ensures all required fields are provided, enforces English-only task content, and suggests epic labels. Triggers on any task creation in any context - commands…