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/Acendas/shipyardnpx agentmods add skills/acendas/shipyard/authoring-acceptance-probeWrote 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/acendas/shipyard/authoring-acceptance-probe)<a href="https://agentmods.dev/skills/acendas/shipyard/authoring-acceptance-probe"><img src="https://agentmods.dev/badge/skills/acendas/shipyard/authoring-acceptance-probe.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 | $0.00016 | $0.02901 |
| Opus 5 | $0.00008 | $0.01451 |
| Sonnet 5 | $0.00003 | $0.00580 |
| Haiku 4.5 | $0.00002 | $0.00290 |
Grade A, and why
authoring-acceptance-probe scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
If the AC is "the new endpoint returns 201 with the created user's ID", the probe is the curl that proves it. If the AC is "the migration adds column X to table Y", the probe is a SQL query against `information_schema`. How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring an Acceptance Probe
Render before asking. Before any AskUserQuestion, render the decision context as assistant chat text. Content that exists only in a Read result, a subagent/Agent return, or the question/option strings does not count as rendered (the UI shows a compact card) — restate it in chat first.
A probe is the smoke-test contract that proves wiring works end-to-end. Without one, a task cannot be dispatched in 2.0 — dispatching-task-loop refuses to run a task whose acceptance_probe: is missing or empty. So authoring the probe is part of authoring the task, not an optional polish step.
When This Applies
- During
/ship-sprintStep 3 (task decomposition), as you write each task file. - During
/ship-quickscoping, before dispatching the change. - During
/ship-bugfix authoring — the probe is the regression scenario. - During
/ship-discussonly if the discussion produces a task spec ready to enter the backlog with a probe.
If a task is genuinely too speculative to author a probe for, that task isn't ready for execution. Either refine until it is, or mark it kind: research (no probe needed; deliverable is a findings doc).
The Authoring Question
Ask exactly this:
"What single shell command, run from a clean state against the merged change, would print observable evidence that the wiring works?"
If you cannot answer that question in one sentence, the acceptance criteria are too vague. Refine the criteria first, then return.
Source Material
A probe is derived from:
- Acceptance criteria in the task file's
## Acceptance Criteriasection. Each AC describes an observable outcome; the probe demonstrates at least one of them happens. - Technical Notes in the parent feature file. These often spell out the exact endpoints, function signatures, table columns, or CLI flags involved.
config.mdtest commands — for the scoped test pattern that proves a unit slice ran. Useful only when paired with a wiring check, not as a probe by itself.
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 · 218 lines · 16 tokens per session scan A 2ee873899eca
authoring-acceptance-probe is a skill published in the GitHub repository Acendas/shipyard (2 stars, last pushed 25d ago), licensed MIT. It adds 16 tokens to every session and 2,901 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
testing-strategy
Follow the testing pyramid — more unit tests, fewer integration tests, even fewer e2e tests.
test-reporting
Run the Level 2 dummy agent integration test suite and produce a detailed HTML report with per-test input → outcome analysis.
memstack-development-test-writer
Use this skill when the user says 'write tests', 'add tests', 'test coverage', 'unit tests', 'integration tests', 'component tests', 'mocking', 'edge cases', or needs to generate tests with proper mocking and edge case coverage. Do NOT use for refactoring plans or database migrations.
memstack-development-webapp-testing
Use when the user says 'write browser tests', 'test this page', 'playwright test', 'e2e test', 'end to end test', 'browser test', 'test the UI', or needs Playwright-based browser testing for a web application. Do NOT use for unit tests, API tests, or non-browser testing.
accessibility-testing
Skill "accessibility-testing" from vibeeval/vibecosystem, covering accessibility testing, axe-core setup, jest-axe (unit / component tests), playwright-axe (e2e) and cypress-axe.
accessibility-a11y
WCAG 2.2 compliance, ARIA patterns, keyboard navigation, screen readers, automated testing.