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 EntityProcess/agentv --skill agent-plugin-reviewgit clone --depth 1 https://github.com/EntityProcess/agentvWrote 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/entityprocess/agentv/agent-plugin-review)<a href="https://agentmods.dev/skills/entityprocess/agentv/agent-plugin-review"><img src="https://agentmods.dev/badge/skills/entityprocess/agentv/agent-plugin-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/entityprocess/agentv/agent-plugin-review"><img src="https://agentmods.dev/badge/skills/entityprocess/agentv/agent-plugin-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 | $0.00060 | $0.01424 |
| Opus 5.5 | $0.00024 | $0.00570 |
| Sonnet 5.5 | $0.00012 | $0.00285 |
| Haiku 4.5 | $0.00006 | $0.00142 |
Grade A, and why
agent-plugin-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 1mo 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Review
Overview
Review AI plugin PRs by running deterministic structural checks first, then applying LLM judgment for skill quality and workflow architecture. Post findings as inline PR comments.
Process
Step 1: Structural lint
Run scripts/lint_plugin.py against the plugin directory:
python scripts/lint_plugin.py <plugin-dir> --evals-dir <evals-dir> --json
The script checks:
- Every
skills/*/SKILL.mdhas a corresponding eval file - SKILL.md frontmatter has
nameanddescription - No hardcoded local paths (drive letters, absolute OS paths)
- No version printing instructions
- Referenced files (
references/*.md) exist - Commands reference existing skills
- Path style consistency across commands
Report findings grouped by severity (error > warning > info).
Step 2: Eval lint
If the PR includes eval files, invoke agentv-eval-review for AgentV-specific eval quality checks.
Additionally, check each eval YAML for these structural patterns:
- File path format: Every
type: fileinput value MUST start with a leading/(workspace-root-relative). Paths likeplugins/foo/SKILL.mdare wrong — correct form is/plugins/foo/SKILL.md. Scan everytype: fileentry and flag any missing leading slash, showing the corrected path. - Repeated inputs: If the same file input (same
type: file+value) appears identically in every test case, recommend extracting it to the top-levelinputfield. AgentV eval files support a top-levelinputsection that applies to all tests, eliminating per-test duplication.
Step 3: Skill quality review (LLM judgment)
For each SKILL.md, check against references/skill-quality-checklist.md:
- Description starts with "Use when..." and describes triggering conditions only (not workflow)
- Description does NOT summarize the skill's process — this causes agents to follow the description instead of reading the SKILL.md body
- Body is concise — only include what the agent doesn't already know
- Content is domain-specific (internal conventions, business patterns, context for WHY) — universal concepts AI agents already know are excluded
- Imperative/infinitive form, not second person
- Heavy reference (100+ lines) moved to
references/files - One excellent code example beats many mediocre ones
- Flowcharts only for non-obvious decisions
- Keywords throughout for search discovery
- Cross-references use skill name with requirement markers, not
@force-load syntax - Discipline-enforcing skills have rationalization tables, red flags lists, and explicit loophole closures
- Consistency — no contradictions within or across files (tool names, filenames, commands, rules)
- No manual routing workarounds — if AGENTS.md or instruction files contain heavy TRIGGER/ACTION routing tables or skill-chain logic, the skill descriptions are likely too weak. Good descriptions enable auto-discovery without manual routing.
What ships with it
3 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.
- 1mo ago First seen · 114 lines · 60 tokens per session scan A 94c3d53726a5
agent-plugin-review is a skill published in the GitHub repository EntityProcess/agentv (15 stars, last pushed 6d ago), licensed MIT. It adds 60 tokens to every session and 1,424 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
code-reviewer
Staff-engineer-level code review delivering 10 prioritized actionable findings across architecture, security, performance, and maintainability.
pull-request-review
Review a pull request or branch diff like a staff engineer. Verify it does what the issue asks, find correctness and security defects with file and line evidence, check tests and compatibility, and deliver prioritized, actionable comments. Use for PR review, branch review, and "review my changes".
code-reviewer
Review code for best practices, bugs, and security issues.
pr-review-triage
Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.
learn-from-sage
Detection-gap (miss) analysis for Code Review Sage. Learn from shipped fixes, acted-on human comments, and design outcomes to close reviewer blind spots. Inline during review stages a candidate; a human triggers a one-shot AI consolidation into the live ruleset.
neuron-evaluation
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…