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 skills/acendas/shipyard/validating-e2e-coveragenpx skills add Acendas/shipyard --skill validating-e2e-coveragegit clone --depth 1 https://github.com/Acendas/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 | $0.00016 | $0.01564 |
| Opus 5 | $0.00008 | $0.00782 |
| Sonnet 5 | $0.00003 | $0.00313 |
| Haiku 4.5 | $0.00002 | $0.00156 |
Grade A, and why
validating-e2e-coverage 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 yesterday.
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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validating E2E Coverage
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.
Post-hoc validation that reads a written feature spec, detects which operational/architectural surfaces the feature touches, maps them to the E2E taxonomy, gap-analyzes against existing acceptance criteria, and returns recommended additions. The goal is to catch the scenarios that live outside the feature's own logic — timeouts, idempotency, degradation, privilege boundaries — before they become production incidents.
When to Invoke
| Caller | Trigger |
|---|---|
/ship-discuss Phase 3.7 |
After spec write, before quality gate |
/ship-discuss REFINE mode |
On re-entry to existing feature (backfill) |
Inputs
The calling skill provides:
- Feature file path (the written spec at
<SHIPYARD_DATA>/spec/features/FNNN-slug.md) - Existing AC list (parsed from the feature file's
## Acceptance Criteriasection) - Domain hints (e.g.,
["payments", "auth"]) from the discussion context
Procedure
Step 1: Detect Touch Surfaces
Read the feature spec: user story, acceptance criteria, interface, data model, technical notes, flows, error handling sections. For each line, match against the touch-surface detection table in ${CLAUDE_PLUGIN_ROOT}/skills/discovering-edge-cases/references/e2e-taxonomy.md.
Collect all activated category slugs. If the feature's domain_tags include domain-specific terms (payments, auth, etc.), also activate categories commonly associated with those domains.
Step 2: Map to Taxonomy Categories
For each activated category, pull the specific types and example GWT scenarios from the taxonomy. This is the "universe" of E2E scenarios that could apply to this feature.
Step 3: Gap Analysis
For each activated type, check whether existing AC already covers it:
- COVERED — an existing AC's Given/When/Then semantically addresses this type (e.g., existing "timeout returns 504" covers the timeout category)
- GAP — no existing AC covers this type; recommend addition
- PARTIAL — an existing AC touches the area but doesn't fully specify the behavior (e.g., "handles errors" without specifying timeout vs. connection refused vs. 5xx)
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.
- yesterday First seen · 120 lines · 16 tokens per session scan A 9deb04174841
validating-e2e-coverage is a skill published in the GitHub repository Acendas/shipyard (2 stars, last pushed 20d ago), licensed MIT. It adds 16 tokens to every session and 1,564 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 2026-08-31.
Other skills, from other repositories
engenharia-de-requisitos
Use when doing requirements engineering, business analysis, or the software-engineering stage of discovering / specifying / validating / managing requirements — the stage BEFORE code (what to build) and AFTER (was the right thing built?), for new projects and for evolutions of existing ones. Triggers (EN)…
engenharia-de-requisitos
Use when doing requirements engineering, business analysis, or the software-engineering stage of discovering / specifying / validating / managing requirements — the stage BEFORE code (what to build) and AFTER (was the right thing built?), for new projects and for evolutions of existing ones. Triggers (EN)…
write-epic
Produces a complete epic definition following Atlassian agile guidance. An epic captures a large initiative that is too big for a single sprint and must be decomposed into user stories.
write-user-story
Produces a complete, ready-to-groom user story following the standard Atlassian/agile format. It applies the INVEST criteria and the 3 Cs framework (Card, Conversation, Confirmation) to ensure each story is well-scoped, valuable, and testable — not just syntactically correct.
agentflow
Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.
backlog-grooming
Review Agiflow Planning tasks for readiness, prioritize approved work, group related tasks into work units, and promote ready tasks to Todo. Use when grooming a backlog, organizing planned tasks, creating work units, or deciding what should be executed next.