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 skills add Sh3rd3n/megazord --skill reviewgit clone --depth 1 https://github.com/Sh3rd3n/megazordWrote 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/sh3rd3n/megazord/review)<a href="https://agentmods.dev/skills/sh3rd3n/megazord/review"><img src="https://agentmods.dev/badge/skills/sh3rd3n/megazord/review/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/sh3rd3n/megazord/review"><img src="https://agentmods.dev/badge/skills/sh3rd3n/megazord/review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00013 | $0.01733 |
| Opus 5 | $0.00006 | $0.00866 |
| Sonnet 5 | $0.00003 | $0.00347 |
| Haiku 4.5 | $0.00001 | $0.00173 |
Grade A, and why
review 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 9d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mz:review
Perform on-demand two-stage code review (spec compliance + code quality) independently of the /mz:go pipeline. Users can trigger this manually at any time, regardless of the quality.review config setting. Spawns a reviewer subagent via the Task tool that checks changes against plan specs and code quality standards.
Reference @skills/init/design-system.md for visual output formatting.
Reference @agents/mz-reviewer.md for the review agent definition.
Step 1: Display Banner
Output the stage banner:
+===============================================+
| MEGAZORD > REVIEW |
+===============================================+
Step 2: Parse Arguments and Determine Scope
Parse the user's message (text after /mz:review) for the review target:
/mz:review(no args) -- review the most recent commit's changes/mz:review --plan {phase}-{plan}-- review all changes from a specific plan (diff from before plan started to after plan completed)/mz:review --files path/to/file.ts path/to/other.ts-- review specific files (diff of uncommitted changes, or latest commit affecting those files)/mz:review --last N-- review the last N commits
Determine the diff to review based on the scope:
No args (default):
git diff HEAD~1 HEAD
--plan {phase}-{plan}: Compute diff range from plan's first to last commit. Read the plan's SUMMARY.md for commit hashes:
- Read SUMMARY.md in the phase directory for the specified plan.
- Extract the first and last commit hashes from the Task Commits section.
- Compute:
git diff {first_commit}~1 {last_commit}
If SUMMARY.md not found, report error: plan has not been executed yet.
--files {file1} {file2} ...: Check for uncommitted changes first:
git diff HEAD -- {files}
If no uncommitted changes, find latest commit affecting those files:
git log -1 --format=%H -- {files}
Then diff: git diff {hash}~1 {hash} -- {files}
--last N:
git diff HEAD~{N} HEAD
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.
- 9d ago First seen · 221 lines · 13 tokens per session scan A 27217fdfa31c
review is a skill published in the GitHub repository Sh3rd3n/megazord (3 stars, last pushed 6mo ago), licensed MIT. It adds 13 tokens to every session and 1,733 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 2026-08-31.
Other skills, from other repositories
finding-duplicate-functions
Use when auditing a codebase for semantic duplication — functions that do the same thing but have different names or implementations, especially common in LLM-generated codebases.
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).
cost-model
Standardized cost-estimation framework for greatcto plans. Forces explicit LLM cost, infra cost, human-supervision time, and the (defensible) human-equivalent comparison. Output format is parsable by the board's /api/cost path — must follow exactly.