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-handoffgit 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-handoff)<a href="https://agentmods.dev/skills/lgbarn/shipyard/shipyard-handoff"><img src="https://agentmods.dev/badge/skills/lgbarn/shipyard/shipyard-handoff/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-handoff"><img src="https://agentmods.dev/badge/skills/lgbarn/shipyard/shipyard-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 6 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00027 | $0.00551 |
| Opus 5 | $0.00014 | $0.00275 |
| Sonnet 5 | $0.00005 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
shipyard-handoff 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 5d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Handoff
When to Use
- User says "handoff", "hand off", "transfer session", "save context", or "I'm done for now"
- User is ending a session and wants context preserved for the next session
- A long work session is wrapping up and state should be recorded
Natural Language Triggers
- "handoff", "hand off", "transfer session", "save context", "I'm done for now"
Overview
Capture the current session's progress into .shipyard/HANDOFF.md so the next session can resume immediately with full context. The orchestrator writes the file directly — this is never delegated to a sub-agent.
I'm using the handoff skill to capture session context.
The Process
Write .shipyard/HANDOFF.md with exactly these five sections in order:
1. Current Task
What was being worked on at handoff time. Be specific: which file, which feature, which plan task.
2. Approach
The strategy or design being followed. Include key decisions already made so the next session doesn't re-litigate them.
3. Tried
What has been attempted and the outcomes — both successes and failures. Include error messages or unexpected behaviors observed.
4. Remaining
Concrete next steps not yet done. List as actionable items, ordered by priority.
5. Open Questions
Unresolved decisions or blockers that need human input or further investigation.
File Format
## Current Task
[What was being worked on]
## Approach
[Strategy and key decisions]
## Tried
[What was attempted and results]
## Remaining
[Concrete next steps]
## Open Questions
[Unresolved decisions or blockers]
Key Principles
- Orchestrator writes the file — never delegate to a sub-agent; sub-agents frequently fail to write output files
- File path is always
.shipyard/HANDOFF.mdrelative to the project root - All five sections are required — do not omit any section, even if the content is "none"
- Be concrete — vague handoffs are useless; include file paths, line numbers, error text where relevant
- After writing, confirm to the user: "HANDOFF.md is ready. The next session will automatically pick it up when it starts."
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.
- 5d ago First seen · 82 lines · 27 tokens per session scan A ede7372ee35d
shipyard-handoff is a skill published in the GitHub repository lgbarn/shipyard (65 stars, last pushed 1mo ago), licensed MIT. It adds 27 tokens to every session and 551 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
tasks
A task-breakdown tool that turns a plan, specification, feature brief, bug report, technical-debt item, or chore into small TASK-NNN work items. Technical debt means postponed cleanup or design work in a codebase.
continue
Autonomous work — find and execute ready tasks.
prd
A Product Requirements Document (PRD) writer for large software initiatives. A PRD records the problem, goals, requirements, assumptions, and evidence before implementation begins.
roadmap
An implementation plan made from a technical specification, organized into phases, milestones, and dependencies.
debt
A command for showing and closing unanswered questions attached to project documents such as requirements, specifications, features, and designs. It can show questions for the whole project or for one document.
pr
A command for managing pull requests on GitHub or Bitbucket Server. A pull request is a request for other developers to review and merge changes into a project branch.