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 agentmods add commands/crain99/cocos-reverse-engineering-skill/reverse-cocosgit clone --depth 1 https://github.com/Crain99/cocos-reverse-engineering-skillWrote 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/commands/crain99/cocos-reverse-engineering-skill/reverse-cocos)<a href="https://agentmods.dev/commands/crain99/cocos-reverse-engineering-skill/reverse-cocos"><img src="https://agentmods.dev/badge/commands/crain99/cocos-reverse-engineering-skill/reverse-cocos.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 | $0.00020 | $0.01102 |
| Opus 5 | $0.00010 | $0.00551 |
| Sonnet 5 | $0.00004 | $0.00220 |
| Haiku 4.5 | $0.00002 | $0.00110 |
Grade A, and why
reverse-cocos 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 3d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/reverse-cocos
Reverse engineer a Cocos Creator game build end-to-end: detect the engine version, decrypt .jsc scripts if needed, and rebuild an editable project.
Instructions
You are starting the Cocos Creator reverse engineering workflow. Follow these steps:
Step 1: Get the target
If the user provided a path as an argument, use that. Otherwise, ask them for the path to the build directory (or archive).
If the path ends in .zip, .7z, .rar, .war, or .apk, extract it first:
.zip/.war→unzip -q <file> -d <tmpdir>.7z/.rar→7z x <file> -o<tmpdir>(requiresp7zip).apk→ a Cocos game inside an APK is usually underassets/in the APK. Unzip and point at that subdirectory.
Step 2: Check and install dependencies
bash ${CLAUDE_PLUGIN_ROOT}/skills/cocos-reverse-engineering/scripts/check-deps.sh
Parse the output for INSTALL_REQUIRED: and INSTALL_OPTIONAL: lines.
If required dependencies are missing, install them:
bash ${CLAUDE_PLUGIN_ROOT}/skills/cocos-reverse-engineering/scripts/install-dep.sh node
bash ${CLAUDE_PLUGIN_ROOT}/skills/cocos-reverse-engineering/scripts/install-dep.sh cc-reverse
If install-dep.sh exits 2, it's printing manual instructions — show them to the user and stop.
Re-run check-deps.sh until it's green.
Step 3: Detect the project layout
bash ${CLAUDE_PLUGIN_ROOT}/skills/cocos-reverse-engineering/scripts/detect-project.sh <path>
Capture the ENGINE= and ENCRYPTED= lines. Report the detected version to the user before proceeding — if it's "unknown", ask them whether to force --version-hint 2.3.x, 2.4.x, or 3.x.
Step 4: Decrypt JSC (if needed)
If ENCRYPTED=yes:
bash ${CLAUDE_PLUGIN_ROOT}/skills/cocos-reverse-engineering/scripts/find-jsc-key.sh <path>
If a KEY= line is produced, pass it through to the next step. If none is found, ask the user:
- Do they have the key from the original developer / a previous reverse pass?
- If not, proceed without decryption —
cc-reversewill still recover assets and scripts from any non-encrypted parts.
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.
- 3d ago First seen · 99 lines · 20 tokens per session scan A 2878c6f39ebb
reverse-cocos is a command published in the GitHub repository Crain99/cocos-reverse-engineering-skill (35 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 1,102 once invoked, about $0.0001 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 commands, from other repositories
sim
Run the EmbodiedGen simulation rendering workflow with sim-cli.
speckit.taskstoissues
Command "speckit.taskstoissues" from akiojin/unity-mcp-server, covering ユーザー入力 and 実行手順.
cert-check
Review the current state against certification and platform compliance expectations.
combat-design
Design or revise combat rules, variables, readability, and tuning direction.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
tech-debt
You are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects. Analyze the codebase to uncover debt, assess its impact, and create actionable remediation plans.