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/release-merge-audit/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/release-merge-audit)<a href="https://agentmods.dev/skills/levy-street/world-of-claudecraft/release-merge-audit"><img src="https://agentmods.dev/badge/skills/levy-street/world-of-claudecraft/release-merge-audit/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/release-merge-audit"><img src="https://agentmods.dev/badge/skills/levy-street/world-of-claudecraft/release-merge-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium MCP Rug Pull · line 101 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00000 | $0.01506 |
| Opus 5 | $0.00000 | $0.00753 |
| Sonnet 5 | $0.00000 | $0.00301 |
| Haiku 4.5 | $0.00000 | $0.00151 |
Grade A, and why
release-merge-audit 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 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.
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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release-merge audit
A release merge into a long-lived feature branch routinely lands surprises that neither CI nor
the merge conflict markers surface. This audit has paid for itself four times on
feature/api-re-architecture alone:
- A release hotfix changed a LEGACY route arm the branch had already migrated, so the migrated handler silently diverged (parity break with no conflict).
- A release refactor added a parameter to a helper the branch receives BY INJECTION
(
passesTurnstilegained a secret argument); the un-re-bound injection site silently disabled the gate. - A release added 12 routes the branch's surface inventory did not know about, 6 of them invisible to the parity corpus.
- A release hotfix pre-landed half of some planned work (the market realm-scoping) with a different mechanism than the branch's plan assumed, invalidating the plan's premise.
Run every step; each targets one of those failure classes. No em dashes or emojis in anything you write.
Step 1: identify the merge and its delta
The merge commit is the argument if given, else the most recent RELEASE merge. Both subject
forms occur in this history: the plain form (Merge branch 'release/v0.23.0' ...) and the far
more common remote-tracking form (Merge remote-tracking branch 'origin/release/v0.25.0' ...,
also with upstream/ or up/). Match both:
git log --merges -1 --format='%H %s' \
--grep="branch '\(origin/\|upstream/\|up/\)\?release/" HEAD
Print %s and read it: hand-written subjects (e.g. merge: resync with release/v0.23.0) do
not match this grep, and a bare git log --merges -1 can grab an unrelated merge, e.g. a
main-merge, so when in doubt pass the commit explicitly. The audit
assumes a true two-parent merge commit; a squash-merged release has no ^2, so pass the
commit explicitly and treat its own diff as the incoming delta. The incoming delta (what the
release brought, relative to the branch):
git diff --name-only <merge>^1..<merge>
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.
- 12d ago First seen · 116 lines · 0 tokens per session scan A a59ea1ab6aa6
release-merge-audit is a skill published in the GitHub repository levy-street/world-of-claudecraft (2,251 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,506 tokens. 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
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
oss-maintainer
Run an open-source project's issue/PR/release loop like a careful human maintainer — triage to root cause, absorb community PRs before duplicating them, gate every merge, ship honest releases, and thank the people doing your QA for free.