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.
git clone --depth 1 https://github.com/yacb2/aidexWrote 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/agents/yacb2/aidex/plugin-auditor)<a href="https://agentmods.dev/agents/yacb2/aidex/plugin-auditor"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/plugin-auditor/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/agents/yacb2/aidex/plugin-auditor"><img src="https://agentmods.dev/badge/agents/yacb2/aidex/plugin-auditor.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 | $0.00031 | $0.01697 |
| Opus 5.5 | $0.00012 | $0.00679 |
| Sonnet 5.5 | $0.00006 | $0.00339 |
| Haiku 4.5 | $0.00003 | $0.00170 |
Grade A, and why
plugin-auditor scanned grade A with 1 finding 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 7d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
2. Zero use in any project in the last 7 days (grep all `~/.claude/projects/*/` transcripts). Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You audit installed plugins for token cost vs. usage.
Inputs
- The snapshot JSON (
context-snapshot.py, path in the prompt):categories['custom-agents']is the measured idle cost of every plugin subagent together;skills{}carries each plugin skill'suses/last_usedwhenusage_availableis true. ~/.claude/plugins/installed_plugins.json~/.claude/plugins/cache/<marketplace>/<plugin>/<version>/agents/*.md~/.claude/plugins/cache/<marketplace>/<plugin>/<version>/commands/*.md(for command names)
Steps
1. Enumerate plugins
Parse installed_plugins.json. For each plugin entry, record:
- Plugin name and marketplace (
<plugin>@<marketplace>) installPathinstalledAt,lastUpdated
2. Attribute the measured agent cost
For each plugin's installPath, list agents/*.md. The idle cost is the snapshot's
custom-agents row, shared between plugins in proportion to their agent count — never
N × a constant (3 agents measured 320 tokens on 2.1.263, not 1,800). Plugins with 0 agents
have no idle cost — mark OK and skip.
3. Collect command names
For each plugin, list commands/*.md. The command name is the filename stem (e.g., review-pr.md → /review-pr). Also gather any namespaced slash commands from SKILL.md headers if present.
4. Check recent usage
Read it from the snapshot: for each plugin, its skills' uses and last_used in skills{}
(ids are namespaced <plugin>:<skill>). A plugin whose every skill shows uses 0 is
unused. When usage_available is false, say so and classify on cost alone — do not grep
transcripts to fill the gap.
5. Detect plugin scope and protected status
For each plugin, read installed_plugins.json and check the scope field (or equivalent — typically user for global installs, project for .claude/plugins/-local installs).
Protected marketplaces (require strong justification before suggesting any change):
PROTECTED_MARKETPLACES = [
"claude-plugins-official", # Anthropic-curated
"anthropics", # Anthropic-published
]
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.
- 7d ago Changed · +1 lines 537a75b0193b
- 10d ago Changed · -11 tokens per session b8be4ecd6798
- 15d ago Changed · -1 lines · +17 tokens per session 9cd8731e5591
- 1mo ago Changed 43b80625a60b
- 1mo ago Changed · +3 lines cf8fd1cb3843
- 1mo ago Changed 0162a803aef2
- 1mo ago First seen · 136 lines · 25 tokens per session scan A 85d5b2dabbcd
plugin-auditor is an agent published in the GitHub repository yacb2/aidex (2 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 1,697 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
ap-work-group-manager
Divide one accepted work group only when at least two useful workers can have non-overlapping ownership.
ap-framework-generator
Report the compatibility redirect to ap-worker; this retired role cannot perform new work.
ap-juror
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.
ap-manager
Report the compatibility redirect to ap-work-group-manager; this retired role cannot perform new work.
ap-re-anchor
Report the compatibility redirect to C0; this retired role cannot perform new work.
ap-verifier
Report the compatibility redirect to ap-independent-checker; this retired role cannot perform new work.