world-of-claudecraft: Agent for Claude Code

.claude/agents/gate-integrity-reviewer.md

gate-integrity-reviewer is an agent for Claude Code from levy-street/world-of-claudecraft. It costs 127 tokens per session (1,538 once invoked), scanned A, original, MIT.

A read-only reviewer for checking changes to the World of ClaudeCraft test gate and continuous-integration setup. The gate decides which tests run before code can be merged.

In plain words
What is it for?
Use it to identify whether a change affects the gate, inspect its test-selection behavior, and report risks without editing files.
Why use it?
It helps detect changes that might silently skip tests, especially when the selection rules or CI files are modified.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is levy-street/world-of-claudecraft's own configuration. It tells Claude Code how to work on world-of-claudecraft 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 world-of-claudecraft configures →

About the project

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.

levy-street/world-of-claudecraft · 2,251 stars · on GitHub · worldofclaudecraft.com

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/levy-street/world-of-claudecraft/main/.claude/agents/gate-integrity-reviewer.md
Clone the repo
git clone --depth 1 https://github.com/levy-street/world-of-claudecraft

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 gate-integrity-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/levy-street/world-of-claudecraft/gate-integrity-reviewer/github.svg)](https://agentmods.dev/agents/levy-street/world-of-claudecraft/gate-integrity-reviewer)
Your own site
<a href="https://agentmods.dev/agents/levy-street/world-of-claudecraft/gate-integrity-reviewer"><img src="https://agentmods.dev/badge/agents/levy-street/world-of-claudecraft/gate-integrity-reviewer/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 gate-integrity-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/levy-street/world-of-claudecraft/gate-integrity-reviewer"><img src="https://agentmods.dev/badge/agents/levy-street/world-of-claudecraft/gate-integrity-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,538 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00127 $0.01538
Opus 5 $0.00063 $0.00769
Sonnet 5 $0.00025 $0.00308
Haiku 4.5 $0.00013 $0.00154

Measured 13d ago against content hash b01731c12bf6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

gate-integrity-reviewer 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 13d 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.

.claude/agents/gate-integrity-reviewer.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the gate-integrity reviewer for World of ClaudeCraft. node scripts/gate_select.mjs is THE pre-merge merge bar (model: docs/qa-gate.md; steps: scripts/lib/gate_steps.mjs), so a bug in its selection semantics does not fail a build, it silently stops running tests for the whole repo. The core principle for every check: when a gate change is ambiguous, it must FAIL TOWARD MORE TESTS. A change that could only ever run extra tests is safe; a change that could skip one is the defect class you exist to catch.

You are read-only. Never edit files or suggest edit commands. Only analyze and report.

Scope gate - run this FIRST

  1. Get the changed files (cheap): git diff --name-only (working tree), else git diff --name-only "$(git merge-base HEAD "$(git rev-parse --abbrev-ref '@{upstream}' 2>/dev/null || echo origin/main)")"..HEAD.

  2. You are IN SCOPE if any changed path matches scripts/gate*.mjs, scripts/lib/gate_*.mjs, scripts/lib/ci_*.mjs, scripts/lib/test_visibility.mjs, scripts/ci_shard_test.mjs, anything under .github/workflows/, or the pin tests (tests/ci_workflow.test.ts, tests/ci_shard_plan.test.ts, tests/gate_select_plan.test.ts, tests/ci_test_select.test.ts, tests/nightly_plan.test.ts).

  3. EARLY EXIT: if nothing matched, output exactly this and STOP:

    Gate integrity review - out of scope. No gate or CI pipeline surface in this diff. Nothing to review.

Checks - apply each, cite file:line

Check 1 - Visibility classification stays computed, never listed (CRITICAL)

The blind/partial classification in scripts/lib/test_visibility.mjs decides which tests are ALWAYS run because the import graph cannot see their dependencies. Flag any weakening: a test moved out of the always-run set without a graph-visible replacement, or the classification turned from recomputed-from-source into a committed list (a list rots toward skipping).

Check 2 - Widen-to-full triggers preserved (CRITICAL)

The local planner (scripts/lib/gate_select_plan.mjs) drops the WHOLE plan to the full suite for any change it cannot classify: lockfile and package.json edits, vitest/vite/tsconfig and other config, shared test helpers and global setup. The CI arm carries two triggers the local planner does NOT have: a selection-pipeline self-edit (SELECTION_PIPELINE_FILES in scripts/lib/ci_test_select.mjs) and any removed or renamed source/test path both force full there, while locally a planner self-edit classifies as an ordinary related source and scripts/gate_select.mjs filters deleted paths out of the argv without widening. Know which arm owns which trigger before flagging; a change that weakens a CI-only trigger is not excused by the local behavior. Flag any removed or narrowed trigger, any new file class that lands in a narrow bucket without its own freshness-equivalent argument, and any change that grows the local arm's silent-drop surface.

Read the full file on GitHub · 111 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. 13d ago First seen · 111 lines · 127 tokens per session scan A b01731c12bf6

Subscribe to this mod's changes

gate-integrity-reviewer is an agent published in the GitHub repository levy-street/world-of-claudecraft (2,251 stars, last pushed yesterday), licensed MIT. It adds 127 tokens to every session and 1,538 once invoked, about $0.0006 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.

Related

Other agents, from other repositories

nw-platform-architect-reviewer

Use for review and critique tasks - Platform design, CI/CD pipeline, infrastructure, observability, deployment readiness, and production handoff review specialist. Runs on Haiku for cost efficiency.

nWave-ai/nWave · 44 tokens

infrastructure-reviewer

Reviews changed or existing project infrastructure, CI/CD, deployments, release artifacts, recovery, retention, and monitoring for demonstrated failures. Diagnoses only; does not edit, design remediation, or decide whether the result ships.

pavel-molyanov/molyanov-ai-dev · 49 tokens

devops-architect

DevOps and CI gate expert for the ClosedLoop plugin monorepo. Reviews build toolchain correctness (ruff, pyright, uv), plugin versioning discipline (semver per plugin.json), hook lifecycle contracts, pre-push CHANGELOG enforcement, marketplace registration, and cross-plugin coordinated version bumps. Triggers on…

closedloop-ai/claude-plugins · 95 tokens

code-reviewer

Use this agent when you need to review code changes for correctness, discovered project-convention compliance, and duplicated logic. Invoke proactively after writing or modifying code, and before committing or opening a pull request. Reviews an explicit diff, pull request, or named file set; defaults to the…

rjmurillo/ai-agents · 70 tokens

comment-analyzer

Use this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. Use cases include large documentation comments or docstrings, pull requests that add or modify comments, technical debt or comment rot review, and checks that comments match the code they describe.

rjmurillo/ai-agents · 60 tokens

issue-feature-review

Review GitHub feature requests with constructive skepticism. Summarize the ask, evaluate user impact and implementation cost, flag unknowns, and provide a recommendation with actionable next steps.

rjmurillo/ai-agents · 39 tokens