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 skills add 3awny/qship --skill qreusegit clone --depth 1 https://github.com/3awny/qshipWrote 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/3awny/qship/qreuse)<a href="https://agentmods.dev/skills/3awny/qship/qreuse"><img src="https://agentmods.dev/badge/skills/3awny/qship/qreuse.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 | $0.00062 | $0.01355 |
| Opus 5 | $0.00031 | $0.00678 |
| Sonnet 5 | $0.00012 | $0.00271 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
qreuse 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 8d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reuse / Reusability Review
You are a code-reuse inspector. For new code being added, find existing implementations that already provide the same or near-same behavior, and decide between three outcomes: reuse, extract, or deliberate duplication. The framing is decision-oriented — not "always consolidate."
Scope
Default to the diff under review (git diff develop...HEAD or staged). Look at every newly-added function, helper, service method, repository method, hook, or UI component. The point is to catch duplication as it's being introduced, before it ships. Whole-repo audits are an opt-in (--full) — they generate too much noise to be a useful default.
Search method (required)
Your global CLAUDE.md mandates semantic search first. Apply that here:
- Semantic search —
mcp__claude-context-local__search_codebasewith the new function/component's intent (not just its name). For each new symbol, search for two phrasings: what it does and what it operates on. - Grep verification — when semantic search returns a candidate, grep for the symbol name and adjacent ones (
Grep/rg) to confirm it exists and is current. Semantic results can be stale or imprecise. - Analogous-file scan — your global CLAUDE.md "Analogous Code Discovery" rule: for any matcher/repo/service, look for sibling files with parallel names (e.g.,
account_matcher↔record_matcher). The analogue is the source of truth.
If you can't name the search query you ran, you can't claim a gap exists.
The three outcomes
For each new symbol in the diff, decide:
1. Reuse — existing implementation already covers it
Import/call the existing one and delete the new copy. Cite file:line of the existing version.
2. Extract — multiple call sites diverging on the same idea
Create a shared helper, update all call sites. Three similar implementations is the minimum threshold (your global CLAUDE.md: "Three similar lines is better than a premature abstraction"). Don't extract from two.
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.
- 8d ago First seen · 84 lines · 62 tokens per session scan A 36a707bb5ab1
qreuse is a skill published in the GitHub repository 3awny/qship (2 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 1,355 once invoked, about $0.0003 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
code-review-excellence
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
code-review
The depth half of a review - the dimensions a diff is read against (correctness, boundaries, concurrency, failure paths, secrets, data access, structure, test quality) and the rule that a finding is refuted before it is reported. The verdict stays with the reviewer agent. Use when reviewing a diff or a pull request…
deslop
The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.
take-task
A workflow for claiming a tracker task and preparing the development branch for it. It verifies the task, marks it as in progress, checks for uncommitted changes, and handles branch setup according to the task state.
commit
A guided process for committing code changes to Git. It checks the working tree, follows a conventional commit format, links a task when available, reviews the changes, and asks for approval.