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/skills/ci-triage/SKILL.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/skills/levy-street/world-of-claudecraft/ci-triage)<a href="https://agentmods.dev/skills/levy-street/world-of-claudecraft/ci-triage"><img src="https://agentmods.dev/badge/skills/levy-street/world-of-claudecraft/ci-triage/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/skills/levy-street/world-of-claudecraft/ci-triage"><img src="https://agentmods.dev/badge/skills/levy-street/world-of-claudecraft/ci-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 18 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00041 | $0.00922 |
| Opus 5 | $0.00020 | $0.00461 |
| Sonnet 5 | $0.00008 | $0.00184 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
ci-triage 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CI triage: classify first, then remedy
A blind gh run rerun wastes a full CI cycle and hides the real cause. Every red run
falls into a small set of known classes, each with its own remedy. Classify before
touching anything. The gate architecture (selective PR tier, shards and lanes, known-flake
handling) is documented in docs/qa-gate.md; the merge queue and required-check contract
in docs/merge-queue.md.
Step 0: classify from the logs, not the summary
- Open the FIRST failing step across ALL shards and jobs. A shard's log tail can be green while an earlier leg in the same job failed; never judge a shard from its last lines.
- CANCELLED counts as a failure. A cancelled leg (timeout, concurrency group, a stall kill) reds the run just like a test failure and needs the same classification pass.
- Record the failing step name, the exact error signature, and whether it reproduces on a second shard or job. Then match a class below.
The failure classes and their remedies
-
Checkout stall (a job hangs fetching, then times out or is cancelled). The auto-rerun reactor handles this class once armed:
.github/workflows/ci-stall-rerun.ymlfires on a completed first-attempt failure/cancellation and drivesscripts/ci_stall_rerun.mjs, which re-reads the live run, applies the tested predicate (pure core:scripts/lib/ci_stall_rerun.mjs), and reruns failed jobs at most once, printing its whole decision in the job log. The driver can also be run by hand for a stalled run it did not catch. Do not stack manual reruns on top of the reactor; check whether attempt 2 already exists first. -
Teardown-rpc flake. The exact signature: every test in the leg passed, but the leg exited 1 with
EnvironmentTeardownError: Closing rpc while ...in the tail. PR-tier shard legs auto-retry this ONCE (the one sanctioned known-flake retry, inscripts/lib/ci_leg_runner.mjsviascripts/ci_shard_test.mjs, loud in the log). Anywhere that retry does not run (release-gate shards, nightly), rerun only the red part:gh run rerun <run-id> --failed. If the signature differs at all, it is not this class; keep classifying.
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.
- 13d ago First seen · 65 lines · 41 tokens per session scan A f4dc4b72ddb1
ci-triage is a skill published in the GitHub repository levy-street/world-of-claudecraft (2,251 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 922 once invoked, about $0.0002 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 skills, from other repositories
Verification & Quality Assurance
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
smoke-test
Health smoke tests + auto-fix for gbrain installs (and OpenClaw services when present). Run after machine/container restarts or whenever something seems broken. Tests critical services, auto-fixes bounded local issues, and reports worker topology without starting daemons. Extensible via user-defined test scripts in…
mcore-create-issue
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
debug-task
Diagnose and fix moon tasks that are broken, misconfigured, or behaving unexpectedly. Use this skill when a moon task is failing, not running, skipped, hanging, producing stale or wrong output, cached when it shouldn't be, re-running every time when it should be cached, or when outputs are empty or missing after a…
operating-github-ci-fixer
Use when the user asks OpenSRE to fix failing GitHub CI, GitHub Actions checks, failing pull request checks, a broken PR branch, or CI on a named branch such as main.
ci-triage
Classify CI failures — distinguish clear regressions from infra flakes and security-test failures. Produces structured failure reports.