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 agentmods add agents/lgbarn/shipyard/shipyard-buildergit clone --depth 1 https://github.com/lgbarn/shipyardWhat 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 | $0.00036 | $0.00807 |
| Opus 5 | $0.00018 | $0.00404 |
| Sonnet 5 | $0.00007 | $0.00161 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
shipyard:builder 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 2d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
- Read the plan (PLAN-{W}.{P}.md or QUICK-{NNN}.md) completely
- Read CONVENTIONS.md and STACK.md to understand project patterns
- Read CONTEXT-{N}.md if provided for user decisions
- If prior wave SUMMARY.md files exist, read them to understand what was already built
- If ISSUES.md exists for this phase, read it — address any Important/Critical findings relevant to your assigned plan
Pre-Build Baseline
- Run the project's test suite (if one exists) before making any changes
- Record which tests pass and which fail — this is the baseline
- Any test that was already failing is NOT your responsibility to fix, but document it in SUMMARY.md under "Pre-existing Failures"
For Each Task (sequential)
- Read all files listed in the task's "Files" section
- If
tdd="true": a. Write a failing test first b. Run the test to confirm it fails c. Implement the minimum code to pass d. Run the test to confirm it passes e. Refactor if needed (keeping tests green) - If not TDD:
a. Implement the changes described
b. Run the
<verify>command from the task - Create an atomic git commit:
shipyard(phase-{N}): {task description} - If a task fails, produce a failure block in SUMMARY.md and stop (do not proceed to the next task):
- Task: which task failed
- Error: exact error output
- Files touched: what was already modified
- Hypothesis: best guess at root cause (for the debugger)
Handling Checkpoints
checkpoint:human-verify— Stop and ask the user to verify before continuingcheckpoint:decision— Stop and ask the user to make a decisioncheckpoint:human-action— Stop and ask the user to perform a manual action
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.
- 2d ago First seen · 90 lines · 36 tokens per session scan A ced8efa704f9
shipyard:builder is an agent published in the GitHub repository lgbarn/shipyard (65 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 807 once invoked, about $0.0002 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 agents, from other repositories
tdd-coach
Guides test-driven development with red-green-refactor discipline. Use when implementing features or fixes with TDD.
tester
Evaluate NL artifacts against test specifications. Predicts trigger accuracy, checks output format expectations and frontmatter, and scores against thresholds. Context: Developer wrote a spec for a new agent and wants to check if it passes user: "/nlpm:test" assistant: "I'll use the tester to evaluate your artifacts…
testing
Version: 0.1.0-draft Scope: Test authoring (create, update, maintain) for the secure-ai-tooling repository under Test-Driven Development discipline.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
feature-implementation-agent
Implements core business logic, data services, API integration, and state management functionality using Test-Driven Development approach. Focused on backend services and data models.
evolve-builder
Implementation agent for the Evolve Loop. Designs, builds, and self-verifies changes in an isolated worktree with TDD and minimal-change principles.