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 Gen-Verse/PAST-Bench --skill a0-debug-plugingit clone --depth 1 https://github.com/Gen-Verse/PAST-BenchWrote 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/gen-verse/past-bench/a0-debug-plugin)<a href="https://agentmods.dev/skills/gen-verse/past-bench/a0-debug-plugin"><img src="https://agentmods.dev/badge/skills/gen-verse/past-bench/a0-debug-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.
<a href="https://agentmods.dev/skills/gen-verse/past-bench/a0-debug-plugin"><img src="https://agentmods.dev/badge/skills/gen-verse/past-bench/a0-debug-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
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 172 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.
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 | $0.00068 | $0.01427 |
| Opus 5.5 | $0.00027 | $0.00571 |
| Sonnet 5.5 | $0.00014 | $0.00285 |
| Haiku 4.5 | $0.00007 | $0.00143 |
Grade A, and why
a0-debug-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 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Zero Plugin Debugger
Work through these checks in order. Stop at the first failure and fix it before continuing.
1. Plugin not appearing in the Plugins list
# Check plugin.yaml exists
ls /a0/usr/plugins/<name>/plugin.yaml
# Validate YAML
python3 -c "import yaml; yaml.safe_load(open('/a0/usr/plugins/<name>/plugin.yaml'))"
# Check directory name doesn't start with '.'
ls /a0/usr/plugins/
Common causes:
- Missing
plugin.yaml- plugin not discovered - Invalid YAML syntax - plugin skipped silently
- Directory name starts with
.- skipped by discovery
2. Plugin appears but won't enable
# Check toggle state
ls -la /a0/usr/plugins/<name>/.toggle-*
# Check for conflicting scoped toggles
ls -la project/.a0proj/plugins/<name>/.toggle-* 2>/dev/null
ls -la /a0/usr/agents/default/plugins/<name>/.toggle-* 2>/dev/null
3. API endpoint not responding
- Verify the handler file is in
api/and subclassesApiHandler - Route format:
POST /api/plugins/<plugin_name>/<handler_filename_without_.py> - Check for Python import errors on startup (check Agent Zero logs)
- Verify correct import paths:
from agent import AgentContextnotfrom helpers.context import AgentContext
# Check for syntax errors in handler
python3 -m py_compile /a0/usr/plugins/<name>/api/my_handler.py
4. Frontend component not rendering / store errors
- Check browser console for Alpine.js errors
- Verify the store file is imported in HTML
<head>via<script type="module"> - Confirm Store Gate pattern is used (missing gate = undefined error if store not yet loaded)
- Verify store name in
createStore(...)matches$store.<name>in templates
5. Extension point not injecting
- Check the HTML file is in
extensions/webui/<correct_breakpoint_name>/ - Verify the breakpoint name exists in core UI (check
webui/index.htmlor component files for<x-extension id="...">) - Common breakpoints:
sidebar-quick-actions-main-start,plugins-list-header-buttons,chat-input-bottom-actions-end - Confirm the HTML file has a root element with
x-dataand anx-move-*directive
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 · 173 lines · 68 tokens per session scan A 30e21d5625ce
a0-debug-plugin is a skill published in the GitHub repository Gen-Verse/PAST-Bench (35 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 68 tokens to every session and 1,427 once invoked, about $0.0003 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
fix
Structured bug fix — reproduce (failing test), diagnose, fix (minimal change), verify, commit. Enforces test-first. Use when a bug needs a methodical fix.
bug-fix-workflow
Structured bug diagnosis and repair workflow using the 5-Whys root cause analysis method. Ensures fixes include tests, documentation, and knowledge capture.
debugging
A debugging-themed dating skill for AI agents on inbed.ai, a platform for agent profiles, matching, and conversations. Here, debugging means finding and fixing problems in connections rather than only in software.
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes — find the root cause first instead of guessing at symptom patches.
reproduce-bug
Reproduce a reported bug in googleapis/mcp-toolbox and decide whether it is real, delivering an evidence-backed verdict: confirmed, already fixed, misconfiguration, client-side, works as intended, not reproducible, or blocked. Use whenever a maintainer asks you to reproduce, verify, confirm, or investigate a bug…