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-codex-orchestrationgit 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-codex-orchestration)<a href="https://agentmods.dev/skills/lgbarn/shipyard/shipyard-codex-orchestration"><img src="https://agentmods.dev/badge/skills/lgbarn/shipyard/shipyard-codex-orchestration.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 | $0.00104 | $0.00708 |
| Opus 5 | $0.00052 | $0.00354 |
| Sonnet 5 | $0.00021 | $0.00142 |
| Haiku 4.5 | $0.00010 | $0.00071 |
Grade A, and why
shipyard-codex-orchestration 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shipyard orchestration under Codex
Shipyard was built for Claude Code, where workflows dispatch fresh subagents in parallel (builder, reviewer, auditor, architect, verifier, researcher, mapper, …) via the Task tool. Codex has no equivalent — it runs in a single context.
So under Codex, Shipyard workflows run as inline sequential personas: instead of dispatching a separate agent, you adopt each role yourself, one after another, in this same conversation.
Honest degradation — what you lose
- No parallelism. Roles run one at a time, so multi-agent phases are slower.
- No context isolation. In Claude Code a fresh reviewer can't be biased by the builder's reasoning. Here the same context does both, so a review is less independent. Compensate by being deliberately skeptical when you switch into a review/verify role — re-read the actual artifact, don't trust your own prior step.
What you keep: the discipline — the review and verify gates still run, just sequentially.
The inline-sequential pattern
When a workflow calls for "dispatch the X agent", instead:
- State which role you're entering ("Now acting as the reviewer…").
- Adopt that role's mandate fully — including its MUST-NOT constraints (a reviewer makes no code edits; a mapper only documents).
- Produce the role's deliverable.
- Exit the role and continue the workflow.
Routing — which skill for which intent
| Intent | Skill / behavior |
|---|---|
| Implement a plan | shipyard-executing-plans skill, run builder→reviewer→verifier inline |
| Security/compliance audit | security-audit skill, adopting the auditor mandate |
| Create a plan | shipyard-writing-plans skill (+ shipyard-brainstorming first) |
| Code review after a build | shipyard-review skill |
| Domain/technology research | shipyard-research skill |
| Map/onboard a codebase | shipyard-map skill |
| Ship/release a completed phase | shipyard-ship skill |
| TDD a feature | shipyard-tdd skill |
| Debug a failure | shipyard-debugging skill |
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 · 60 lines · 104 tokens per session scan A c43f9352cf6a
shipyard-codex-orchestration is a skill published in the GitHub repository lgbarn/shipyard (65 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 708 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
cco-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.
codex
Run the Codex CLI directly in the user's checkout for code analysis, refactoring, or automated editing without Claude Architect's verified delegation lifecycle.
design
Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…
spike
A time-limited research task for answering an open technical or product question before implementation begins.
deep-research-tiered
Deep research harness: fan-out search, fetch, adversarially verify, synthesize a cited report. Prefer Workflow({name:'deep-research-tiered', args:{question, models?}}) over built-in deep-research — same output, cheap tiered defaults (scope/search=sonnet, fetch=haiku, verify=sonnet, synthesize=inherit). Use for deep…
review
Run a full code review on current changes or specified files. Runs ruff lint, review-code agent, and security scan in sequence.