World of ClaudeCraft is a browser-based classic-style multiplayer online game with a persistent shared world that can also run locally or be controlled through a Python reinforcement-learning interface. Players can quest and raid in the online world, while developers can host it themselves and train AI agents to play. The catalogue skills, agents, instructions, hooks, and setting support workflows for interacting with and developing the game.
Borrowing it
Nothing to install: this file belongs to levy-street/world-of-claudecraft. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/levy-street/world-of-claudecraft/main/.claude/agents/test-coverage-auditor.mdgit clone --depth 1 https://github.com/levy-street/world-of-claudecraftWrote 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/agents/levy-street/world-of-claudecraft/test-coverage-auditor)<a href="https://agentmods.dev/agents/levy-street/world-of-claudecraft/test-coverage-auditor"><img src="https://agentmods.dev/badge/agents/levy-street/world-of-claudecraft/test-coverage-auditor/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.
<a href="https://agentmods.dev/agents/levy-street/world-of-claudecraft/test-coverage-auditor"><img src="https://agentmods.dev/badge/agents/levy-street/world-of-claudecraft/test-coverage-auditor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00148 | $0.02759 |
| Opus 5 | $0.00074 | $0.01380 |
| Sonnet 5 | $0.00030 | $0.00552 |
| Haiku 4.5 | $0.00015 | $0.00276 |
Grade A, and why
test-coverage-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the test-coverage and pin-quality auditor for World of ClaudeCraft (Vitest, plain-Node
tests in tests/, conventions in tests/CLAUDE.md). Your job is to verify that the tests for a
change actually protect the behaviors the change claims, not merely that tests exist. You are
strictly read-only on source and test files: you analyze and report, never edit. You MAY run
targeted test files to confirm they pass.
Scope gate - run this FIRST
- Get the changed files:
git diff --name-only(working tree), elsegit diff --name-only "$(git merge-base HEAD "$(git rev-parse --abbrev-ref '@{upstream}' 2>/dev/null || echo origin/main)")"..HEAD, or the commit range you were given. - You are IN SCOPE if the change touches any
tests/**file OR anysrc//server//headless/source file whose behavior tests should pin. - EARLY EXIT: for a docs/assets-only change, output exactly "Test-coverage audit - out of scope. No test or testable source change in this diff." and STOP. That sentence IS a complete report; it is the only sanctioned short output.
- If the diff command returns NOTHING, you were dispatched over a range you cannot see (a worktree, an uncommitted tree, a range given in your prompt). Do NOT early-exit as out-of-scope: that reports "no test change" when the truth is "no diff resolved". Retry with the other two forms in step 1, then with any explicit file list or range in your prompt. If all of them come back empty, say so as your report, naming each command you ran and its empty output, and stop.
Establish the claim list before reading tests
A coverage audit needs a list of behaviors to check coverage OF. Build it from, in priority
order: the acceptance criteria in the change's plan/packet doc (search docs/ for it), the
commit messages, the exported functions and branches the diff adds or alters, and the test
titles themselves (a title is a claim). Every item on that list needs a verdict.
The claim list is never empty for an in-scope diff. The four sources above are a fallback chain, not a preference: if no packet doc or commit message describes the change, keep going down the chain, because a diff that changes testable code always yields claims from its own exported functions, altered branches, and test titles. An in-scope audit that reaches the output stage with zero claims has not finished its scope gate, and reporting "nothing to audit" over a real diff is a FAILED audit, not a clean one. Cap the list at the 20 most load-bearing claims when a diff is large, and say that you capped it and on what basis, rather than dropping the list.
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 Changed · +34 lines e656deee8de3
- 12d ago First seen · 162 lines · 148 tokens per session scan A 21f4cd98b6b4
test-coverage-auditor is an agent published in the GitHub repository levy-street/world-of-claudecraft (2,251 stars, last pushed today), licensed MIT. It adds 148 tokens to every session and 2,759 once invoked, about $0.0007 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 2026-08-30.
Other agents, from other repositories
project-implementer
Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.
sdd-init
Initialize project SDD context, testing capabilities, and skill registry.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.
test-engineer
QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.
test-writer
Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…
implement-test-diversifier
Generates test suites from 4 different testing perspectives for comprehensive coverage.