dispatching-spec-review

dispatching-spec-review is a skill for Claude Code from Acendas/shipyard. It costs 14 tokens per session (1,738 once invoked), scanned A, original, MIT.

A review step that sends a fresh-context helper to compare a feature specification with the code changes delivered. The helper reports findings but does not edit files or commit changes.

In plain words
What is it for?
Use it after a task or group of tasks is implemented, or when you want to check whether a specific feature was actually delivered.
Why use it?
It checks whether the implementation meets each stated requirement, including requirements that may be easy to overlook. A fresh context helps reduce assumptions carried over from the build process.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions subagents; names the AskUserQuestion tool.

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the shipyard plugin — 32 skills, 7 agents, 4 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/acendas/shipyard/dispatching-spec-review
Any agent
npx skills add Acendas/shipyard --skill dispatching-spec-review
Clone the repo
git clone --depth 1 https://github.com/Acendas/shipyard

Made for: Claude Code.

Or install shipyard, the plugin that ships this one along with the rest of its 32 skills, 7 agents, 4 hooks.

Wrote 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.

agentmods badge for dispatching-spec-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/acendas/shipyard/dispatching-spec-review.svg)](https://agentmods.dev/skills/acendas/shipyard/dispatching-spec-review)
Your own site
<a href="https://agentmods.dev/skills/acendas/shipyard/dispatching-spec-review"><img src="https://agentmods.dev/badge/skills/acendas/shipyard/dispatching-spec-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,738 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00014 $0.01738
Opus 5 $0.00007 $0.00869
Sonnet 5 $0.00003 $0.00348
Haiku 4.5 $0.00001 $0.00174

Measured 5d ago against content hash 8effa1870494, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

dispatching-spec-review 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.

plugins/shipyard/skills/dispatching-spec-review/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dispatching a Spec Review

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.

Sends a fresh-context subagent to compare what the spec requires against what the diff delivers. The subagent reads, reasons, and reports — it does not edit code or commit. The orchestrator uses the structured findings to decide whether to mark a task done, request fixes, or block approval.

When to Invoke

Caller Scope Trigger
/ship-execute post-task gate One task After dispatching-task-loop returns STATUS: COMPLETE and anti-stub-scan is clean — final compliance check before marking task done
/ship-execute wave VERIFY All tasks in a wave After wave-boundary REFACTOR — confirms wave-level acceptance scenarios all hold
/ship-review Sprint or feature Full audit before user approval
Manual / ad-hoc Single feature When the user asks "did we actually deliver F-007?"

Skip this skill for tasks marked effort: S (trivial) — overhead exceeds value. The post-task gate explicitly bypasses for S tasks per /ship-execute's spec-check rule.

Inputs

  • scope"task" | "wave" | "feature" | "sprint". Determines which spec files and which diff range.
  • target_ids — list of task IDs (scope=task), feature IDs (scope=feature), or null for wave/sprint (those are inferred from sprint state).
  • base_ref — git ref the diff started from. For wave: the working branch HEAD before wave kickoff. For sprint: the sprint's base ref.
  • head_ref — current HEAD (or the sprint's working branch HEAD).
  • data_dir — literal <SHIPYARD_DATA> path.

Dispatching the Reviewer

The reviewer methodology (AC classification, the Iron Law, the read-only contract, the Required Return Shape) lives in the registered agent agents/shipyard-spec-reviewer.md — read it once if you need to know exactly what it does; do not re-inline it here.

Read the full file on GitHub · 100 lines

Changes

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.

  1. 5d ago First seen · 100 lines · 14 tokens per session scan A 8effa1870494

Subscribe to this mod's changes

dispatching-spec-review is a skill published in the GitHub repository Acendas/shipyard (2 stars, last pushed 24d ago), licensed MIT. It adds 14 tokens to every session and 1,738 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.

Related

Other skills, from other repositories

break-complex-projects-into-milestones

How to use AI to generate structured Work Breakdown Structures (WBS), 4-week critical path roadmaps, and verifiable milestone deliverables.

alivirgo/Major-AI-Skills · 40 tokens

iterate-step-by-step

How to use the 4-Turn Conversational Scaffolding framework to build complex code, strategy, and content incrementally without token exhaustion or quality degradation.

alivirgo/Major-AI-Skills · 37 tokens

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.

MarieLynneBlock/arcanum-artifex · 40 tokens

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.

MarieLynneBlock/arcanum-artifex · 64 tokens

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)…

seekdevcore/sk-requirements-engineering-theskill · 0 tokens

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)…

seekdevcore/sk-requirements-engineering-theskill · 0 tokens