agentmods.dev

a0-review-plugin

a0-review-plugin is a skill for Claude Code, Codex from Gen-Verse/PAST-Bench. It costs 64 tokens per session (2,004 once invoked), scanned A, original, Apache-2.0.

A review checklist for auditing Agent Zero plugins before using or sharing them.

In plain words
What is it for?
Use it to validate a plugin manifest and folder structure, inspect security and code patterns, and compare it with the community index.
Why use it?
It helps find invalid metadata, missing files, unsafe code patterns, and duplicate plugins before they cause problems.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 25repo 1mo ago A scan SkillSpector: warn 64 tokens original Apache-2.0

Good fit Use it to validate a plugin manifest and folder structure, inspect security and code patterns, and compare it with the community index.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gen-verse/past-bench/a0-review-plugin
View source ↗ Gen-Verse/PAST-Bench arxiv.org
Install

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.

Any agent
npx skills add Gen-Verse/PAST-Bench --skill a0-review-plugin
Clone the repo
git clone --depth 1 https://github.com/Gen-Verse/PAST-Bench

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for a0-review-plugin

README.md
[![agentmods](https://agentmods.dev/badge/skills/gen-verse/past-bench/a0-review-plugin/github.svg)](https://agentmods.dev/skills/gen-verse/past-bench/a0-review-plugin)
Your own site
<a href="https://agentmods.dev/skills/gen-verse/past-bench/a0-review-plugin"><img src="https://agentmods.dev/badge/skills/gen-verse/past-bench/a0-review-plugin/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.

agentmods 80×15 button for a0-review-plugin

Your own site · 80×15
<a href="https://agentmods.dev/skills/gen-verse/past-bench/a0-review-plugin"><img src="https://agentmods.dev/badge/skills/gen-verse/past-bench/a0-review-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,004 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 174
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.02004
Opus 5 $0.00032 $0.01002
Sonnet 5 $0.00013 $0.00401
Haiku 4.5 $0.00006 $0.00200

Measured 9d ago against content hash 83a37ce7e8ee, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

a0-review-plugin 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.

agents/agent-zero/skills/a0-review-plugin/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Zero Plugin Review

Full-audit workflow for plugins in /a0/usr/plugins/<name>/. Run all 4 phases in order and report findings grouped by phase. Mark each item PASS, FAIL, or WARN.

For detailed checklists and code pattern references, read checklists.md in this skill directory when needed.

Phase 1: Manifest Validation

Read usr/plugins/<name>/plugin.yaml. Check:

  • File exists at plugin root
  • Valid YAML (parseable, mapping at top level)
  • name field handling matches the intended distribution target: for community / Plugin Index plugins it must be present, non-empty, match ^[a-z0-9_]+$, and match the directory name; for local-only plugins, a missing name is a WARN rather than a FAIL
  • title present and non-empty
  • description present and non-empty
  • version present, follows semver or simple x.y.z format
  • settings_sections is a list; each value is one of: agent, external, mcp, developer, backup
  • per_project_config and per_agent_config are booleans (if present)
  • always_enabled is false or absent (only framework core plugins should use true)
  • No unknown fields (warn on extra keys not in the schema)

Phase 2: Structure Validation

Inspect the plugin directory layout:

  • Directory is under usr/plugins/ (not plugins/ - that is reserved for core)
  • Directory name matches ^[a-z0-9_]+$
  • If api/ exists: contains Python files only; each should subclass ApiHandler
  • If tools/ exists: contains Python files only; each should subclass Tool
  • If extensions/ exists: check subdirs follow python/<point>/, python/_functions/<module>/<qualname>/<start|end>/, or webui/<point>/ patterns; flag the retired flattened python/<module>_<qualname>_<start|end>/ form
  • If helpers/ exists: shared Python logic (standard directory)
  • If prompts/ exists: prompt templates (standard directory)
  • If agents/ exists: agent profiles with <profile>/agent.yaml (standard directory)
  • If conf/ exists: configuration files such as model_providers.yaml (standard directory)
  • If webui/config.html exists: plugin must declare at least one settings_sections entry
  • If hooks.py exists: review whether it defines the lifecycle hook functions the plugin appears to rely on, especially install and pre_update when the plugin needs install-time or update-time behavior
  • If execute.py exists: check it has a main() function and if __name__ == "__main__": sys.exit(main())
  • LICENSE at plugin root: Agent Zero does not require it for local plugins, but it is required at the repo root before submitting to the Plugin Index. If missing → WARN — LICENSE absent — required for community contribution (Plugin Index); optional for local-only use
  • default_config.yaml (if present): valid YAML
  • No unexpected top-level entries (WARN for anything outside the standard layout)

Read the full file on GitHub · 175 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 9d ago First seen · 175 lines · 64 tokens per session scan A 83a37ce7e8ee

Subscribe to this mod's changes

a0-review-plugin is a skill published in the GitHub repository Gen-Verse/PAST-Bench (25 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 64 tokens to every session and 2,004 once invoked, about $0.0003 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.

LLMSecurityagentagent-memoryagent-skillsagentic-workflowauditchecklistllm-agentspluginsreviewvalidate
Related

Other skills, from other repositories

a0-review-plugin

Full audit of Agent Zero plugins in usr/plugins/. Reviews manifest validity, directory structure, code patterns (Store Gating, notifications, imports), security, and duplicate detection against the community index. Use when asked to review, audit, validate, or check an existing plugin before using or contributing it.

agent0ai/agent-zero · 64 tokens

edgeone skill scanner

A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.

Tencent/AI-Infra-Guard · 148 tokens

aig-scanner

A.I.G Scanner — AI security scanning for infrastructure, AI tools / skills, AI Agents, and LLM jailbreak evaluation via Tencent Zhuque Lab AI-Infra-Guard. Uses built-in exec + Python script, no plugin required. Requires AIGBASEURL to be configured. Triggers on: scan AI service, AI vulnerability scan, scan AI infra…

Tencent/AI-Infra-Guard · 142 tokens

agent-review

Critically review a Stencila agent and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve an agent directory or AGENT.md file. Covers frontmatter validation, system instruction quality, configuration correctness, and adherence to the Agent schema.

stencila/stencila · 57 tokens

squirrelscan

Skill "squirrelscan" from squirrelscan/squirrelscan, covering squirrelscan cli, links, install, command overview and quickstart.

squirrelscan/squirrelscan · 101 tokens

audit-website

Audit a website with the squirrelscan CLI and fix the findings in code. Runs SEO, performance, security, technical, content, accessibility, and 15 other rule categories (260+ rules), returns an LLM-optimized report, then drives an iterative fix loop, mapping issues to source files, applying fixes, and re-auditing…

squirrelscan/squirrelscan · 94 tokens