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 skills/mocraimer/mo-cc-plugins/review-towernpx skills add mocraimer/mo-cc-plugins --skill review-towergit clone --depth 1 https://github.com/mocraimer/mo-cc-pluginsWrote 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/mocraimer/mo-cc-plugins/review-tower)<a href="https://agentmods.dev/skills/mocraimer/mo-cc-plugins/review-tower"><img src="https://agentmods.dev/badge/skills/mocraimer/mo-cc-plugins/review-tower.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 | $0.00073 | $0.01943 |
| Opus 5 | $0.00036 | $0.00971 |
| Sonnet 5 | $0.00015 | $0.00389 |
| Haiku 4.5 | $0.00007 | $0.00194 |
Grade A, and why
review-tower 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 4d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Tower
Generate a browser-based gamified code review for a pull request. You are the AI reviewer — analyze the code, package your findings as JSON, inject into an HTML template, and open the result in the browser. The template handles scoring, progression, and stats persistence at runtime; your job ends after opening the HTML.
References (in ./references/):
scoring-tables.md— severity criteria, multiplier values, XP formulasrpg-progression.md— tier thresholds, titles, badges, stats schemafinding-matching-guide.md— how reviewer findings match AI findings
1. Input
Parse $ARGUMENTS to determine input type:
- PR reference (URL, number, or empty for current branch): proceed to step 2.
- JSON comments array (pasted export from Review Tower): skip to step 7 (Post Findings to PR).
If gh is not installed, tell the user: brew install gh && gh auth login.
2. Fetch PR Data
Retrieve the PR metadata and full unified diff needed to populate the JSON schema below. If no PR found, ask for a number/URL. If the diff is empty, inform the user and stop.
3. Construct Tower
Group Files into Floors
- Same directory/module → same floor
- Test files (
.test.,.spec.,__tests__/) → group with their implementation files - Type/interface files → group with implementations
- Config files (package.json, .env*, CI configs, tsconfig, .eslintrc) → dedicated Easy floor
- Cap at 10 floors (template UI constraint); merge by parent directory if needed
- Single-file floors are fine; don't force-merge unrelated files
Assign Difficulty
A "concern" is a distinct logical change area (e.g., "refactoring auth middleware" and "adding rate limiting" are 2 concerns).
Per floor, total lines changed across its files:
- Easy: < 50 lines AND single concern
- Normal: 50-200 lines, OR 2+ concerns
- Boss: > 200 lines, OR security-sensitive paths (auth, payments, data migrations, public API contracts, DB schemas)
If tower has 3+ floors, ensure at least 1 Boss. Promote the floor with the most lines changed among non-Boss floors.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 187 lines · 73 tokens per session scan A 9231fa5d24f5
review-tower is a skill published in the GitHub repository mocraimer/mo-cc-plugins (2 stars, last pushed 5mo ago), licensed MIT. It adds 73 tokens to every session and 1,943 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
playtest-report
Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
unity-manual-component
Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.