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 KirKruglov/claude-skills-kit --skill cowork-plugin-auditgit clone --depth 1 https://github.com/KirKruglov/claude-skills-kitWrote 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/kirkruglov/claude-skills-kit/cowork-plugin-audit)<a href="https://agentmods.dev/skills/kirkruglov/claude-skills-kit/cowork-plugin-audit"><img src="https://agentmods.dev/badge/skills/kirkruglov/claude-skills-kit/cowork-plugin-audit/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/kirkruglov/claude-skills-kit/cowork-plugin-audit"><img src="https://agentmods.dev/badge/skills/kirkruglov/claude-skills-kit/cowork-plugin-audit.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 | $0.00081 | $0.01466 |
| Opus 5 | $0.00041 | $0.00733 |
| Sonnet 5 | $0.00016 | $0.00293 |
| Haiku 4.5 | $0.00008 | $0.00147 |
Grade A, and why
cowork-plugin-audit 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cowork Plugin Audit
This skill audits the active plugins in your Claude Cowork setup and produces a keep/disable/disable-until-needed recommendation table. It compares each installed plugin against your described workflow, flags idle or redundant plugins, and provides a qualitative estimate of potential token savings.
Input:
- Your role and workflow description (2–5 sentences)
- List of installed plugins (plain text or markdown list)
- Optional: project context file (
.md)
Output:
- Audit table: plugin → category → recommendation → rationale
- Summary: keep/disable counts + qualitative token-savings estimate
- Optional: ready-made Project Instructions block listing disabled plugins
Language Detection
Detect the user's language from their message:
- If Russian (or contains Cyrillic): respond in Russian
- If English (or other Latin-script language): respond in English
- If ambiguous: respond in the language of the trigger phrase used
Instructions
Step 1: Collect Workflow Context
-
Check if a project context file was provided or is readable from the working directory
- If found: extract role, workflow description, and primary tasks from it
- If not found: proceed to Step 1.2
-
Check if the user provided a workflow description in their message
- If yes: extract role and 2–3 primary tasks; proceed to Step 2
- If no: ask one clarifying question: "Please describe 2–3 main tasks you do in Cowork" — wait for the answer before continuing
-
Confirm understanding of workflow in a 1–2 sentence paraphrase (shown inline before the audit table)
Step 2: Collect Plugin List
-
Check if the user provided a list of installed plugins in their message
- If yes: parse the list and proceed to Step 3
- If no: ask the user to paste the list from Cowork Settings → Plugins
-
If the user does not know plugin names, offer the standard reference list of known Cowork plugins:
- engineering, sales, data, operations, productivity, product-management, finance, skill-planner, skill-builder
- Ask the user to confirm which ones are installed
What ships with it
4 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.
- 9d ago First seen · 149 lines · 81 tokens per session scan A 852a9fbca26d
cowork-plugin-audit is a skill published in the GitHub repository KirKruglov/claude-skills-kit (18 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 1,466 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
tailored-resume-generator
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances.
meeting-insights-analyzer
Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss opportunities to listen. Perfect for professionals seeking to improve their communication and leadership…
dx-optimizer
Developer Experience specialist. Improves tooling, setup, and workflows. Use PROACTIVELY when setting up new projects, after team feedback, or when development friction is noticed.
file-organizer
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
sequence-load
Find leads matching criteria and bulk-add them to an Apollo outreach sequence. Handles enrichment, contact creation, deduplication, and enrollment in one flow.
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.