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 caravanglory/magehub --skill mage-reviewgit clone --depth 1 https://github.com/caravanglory/magehubWrote 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/caravanglory/magehub/mage-review)<a href="https://agentmods.dev/skills/caravanglory/magehub/mage-review"><img src="https://agentmods.dev/badge/skills/caravanglory/magehub/mage-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/caravanglory/magehub/mage-review"><img src="https://agentmods.dev/badge/skills/caravanglory/magehub/mage-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 | $0.00041 | $0.08341 |
| Opus 5 | $0.00020 | $0.04170 |
| Sonnet 5 | $0.00008 | $0.01668 |
| Haiku 4.5 | $0.00004 | $0.00834 |
Grade A, and why
mage-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 10d 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 — 774 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Activation
Use When
- The task is to review Magento code changes before merge, after conflict resolution, or around security/performance/API/database risk.
- The user asks for review, audit, pre-landing review, PR/MR feedback, or risk triage on a Magento diff.
Do Not Use When
- The user explicitly asks to implement changes instead of review findings.
- There is no diff, branch, patch, or changed-file set to inspect and the user only wants general best practices.
Required Inputs
- Base branch or PR/MR target when it cannot be detected automatically.
- Changed-file set, PR description or task intent, and project-specific verification commands if available.
Workflow
- Load prior project learnings, detect the base branch, and compute a read-only merge-base diff.
- Read the full diff and surrounding code before producing findings.
- Run critical passes for security, data safety, authorization, concurrency, and correctness before style or maintainability comments.
- Attach severity, confidence, file/line evidence, concrete fix, and verification command to every finding.
- Log only reusable, non-obvious learnings after the review.
Guardrails
- Do not modify, stage, commit, push, create PRs, or switch branches as part of review.
- Use read-only git diff paths; do not create temporary merge branches to isolate review scope.
- Flag security-sensitive uncertainty explicitly instead of suppressing it as low-confidence noise.
Verification
- Verify every safety claim by citing the exact code or test that proves it.
- Suggest concrete project commands for PHPCS, tests, static analysis, or smoke coverage relevant to each finding.
- If no issues are found, state the review scope and remaining test gaps.
Output Contract
- Lead with findings ordered by severity, then open questions, then test gaps or residual risk.
- Use file:line references, confidence scores, concrete fixes, and specific verification commands.
Magento 2 Code Review Workflow
What ships with it
2 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.
- 10d ago First seen · 774 lines · 41 tokens per session scan A 29127c690f81
mage-review is a skill published in the GitHub repository caravanglory/magehub (2 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 8,341 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 2026-08-31.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…