clarifyprompt-mcp: Skill for Claude Code

.claude/skills/ship-check/SKILL.md

ship-check (clarifyprompt-mcp overrides) is a skill for Claude Code from LumabyteCo/clarifyprompt-mcp. It costs 66 tokens per session (3,870 once invoked), scanned C, original, Apache-2.0.

A repository-specific checklist extension for the clarifyprompt-mcp project. It adds version checks for the MCP Node SDK, including the version declared in src/index.ts.

In plain words
What is it for?
Use it when auditing this repository before release, especially when checking that version numbers match across its source and manifest files.
Why use it?
It helps catch mismatched project versions before shipping, which can cause releases and package metadata to disagree.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is LumabyteCo/clarifyprompt-mcp's own configuration. It tells Claude Code how to work on clarifyprompt-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything clarifyprompt-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to LumabyteCo/clarifyprompt-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/LumabyteCo/clarifyprompt-mcp/main/.claude/skills/ship-check/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/LumabyteCo/clarifyprompt-mcp

Made for: Claude Code.

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 ship-check (clarifyprompt-mcp overrides)

README.md
[![agentmods](https://agentmods.dev/badge/skills/lumabyteco/clarifyprompt-mcp/ship-check/github.svg)](https://agentmods.dev/skills/lumabyteco/clarifyprompt-mcp/ship-check)
Your own site
<a href="https://agentmods.dev/skills/lumabyteco/clarifyprompt-mcp/ship-check"><img src="https://agentmods.dev/badge/skills/lumabyteco/clarifyprompt-mcp/ship-check/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.

agentmods 80×15 button for ship-check (clarifyprompt-mcp overrides)

Your own site · 80×15
<a href="https://agentmods.dev/skills/lumabyteco/clarifyprompt-mcp/ship-check"><img src="https://agentmods.dev/badge/skills/lumabyteco/clarifyprompt-mcp/ship-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,870 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00066 $0.03870
Opus 5 $0.00033 $0.01935
Sonnet 5 $0.00013 $0.00774
Haiku 4.5 $0.00007 $0.00387

Measured 12d ago against content hash 5713cc56b424, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

ship-check (clarifyprompt-mcp overrides) scanned grade C 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 12d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

The single most expensive class of mistake this repo has hit: a `package-lock.json` regeneration that silently changed more than intended. When a release touches the lockfile (dependency bump, SDK upgrade, `npm audit fix
.claude/skills/ship-check/SKILL.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ship-check — clarifyprompt-mcp overrides

Loaded by the user-scoped ship-check skill at ~/.claude/skills/ship-check/SKILL.md when running audits in this repo. Uses the cascade syntax (CSS-like specificity) the parent skill defines:

  • OVERRIDE: <general-check> — replace the general check entirely
  • DISABLE: <general-check> — skip the general check, requires a rationale
  • AUGMENT: <general-check> — keep general + add more
  • ADD: <new-check> — a check with no general equivalent

Each directive is also tagged with a generalization hint — whether the check is purely repo-specific forever, or a candidate to promote back to the user-scoped skill once it proves useful elsewhere.


AUGMENT: Version consistency — extra source for MCP Node SDK

The general check already inspects package.json, package-lock.json, server.json (both top-level and packages[*].version), CHANGELOG.md, and ecosystem-specific manifests. This repo additionally has:

  • src/index.ts → the McpServer({ name, version }) literal must match all of the above.

Run the general check, then verify grep -oE 'version: "[^"]+"' src/index.ts matches package.json#version.

Generalization hint: the src/index.ts McpServer literal is specific to MCP servers built with @modelcontextprotocol/sdk for Node. Promotion candidate once a second such project adopts ship-check, with detection gated on the SDK being a declared dep.


AUGMENT: Secrets sweep — repo-specific guards

Keep all general patterns AND additionally hard-fail on:

  • Any 40+ character hex string following _authToken= (a leaked ~/.npmrc value).
  • The literal token prefix npm_EYF3iBwo we rotated during 1.2.0 prep — defense against someone re-adding it from transcript history.

The second pattern is an artifact of this project's history and expires once the token is safely out of all backscroll. Review quarterly; remove when no longer needed.

Generalization hint: "add project-specific secret patterns" is itself a general capability — the parent skill already supports it via this AUGMENT operator. The specific patterns here are clarifyprompt-only.

Read the full file on GitHub · 216 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. 12d ago First seen · 216 lines · 66 tokens per session scan C 5713cc56b424

Subscribe to this mod's changes

ship-check (clarifyprompt-mcp overrides) is a skill published in the GitHub repository LumabyteCo/clarifyprompt-mcp (12 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 3,870 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens

atmos-validation

Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.

cloudposse/atmos · 31 tokens

skill-benchmark

Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.

HoangNguyen0403/agent-skills-standard · 16 tokens