agentmods.dev

skill-usage

skill-usage is a skill for Claude Code, Codex from paultaki/claude-skill-usage. It costs 122 tokens per session (1,163 once invoked), scanned A, original, MIT.

A reporting tool that examines Claude skill usage and displays activity, token costs, and keep-or-remove recommendations in a local HTML dashboard.

In plain words
What is it for?
Use it to review global, project, or plugin skills and decide which to keep, modernize, turn off, or remove.
Why use it?
It shows which skills are actually used and which add ongoing context or invocation costs without providing much value.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the skill-usage plugin — 1 skill shipped together

not rated 2 2mo ago A scan 122 tokens original MIT
View the source file paultaki/claude-skill-usage
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.

agentmods
npx agentmods add skills/paultaki/claude-skill-usage/skill-usage
Any agent
npx skills add paultaki/claude-skill-usage --skill skill-usage
Clone the repo
git clone --depth 1 https://github.com/paultaki/claude-skill-usage

Made for: Claude Code, Codex.

Or install skill-usage, the plugin that ships this one along with the rest of its 1 skill.

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 skill-usage

README.md
[![agentmods](https://agentmods.dev/badge/skills/paultaki/claude-skill-usage/skill-usage.svg)](https://agentmods.dev/skills/paultaki/claude-skill-usage/skill-usage)
Your own site
<a href="https://agentmods.dev/skills/paultaki/claude-skill-usage/skill-usage"><img src="https://agentmods.dev/badge/skills/paultaki/claude-skill-usage/skill-usage.svg" alt="Measured on agentmods" height="20"></a>
Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,163 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00122 $0.01163
Opus 5 $0.00061 $0.00581
Sonnet 5 $0.00024 $0.00233
Haiku 4.5 $0.00012 $0.00116

Measured 4d ago against content hash 16978c3ccd28, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-usage 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 4d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/selftest.py, scripts/skill-usage.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/skill-usage/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skill-usage

Answers: how often is each skill used, what does it cost, and should I keep / modernize / turn off / prune it?

How it works

The real record of skill use is the Skill tool_use events in ~/.claude/projects/**/*.jsonl. The bundled script parses those (no LLM) for usage + token cost + a heuristic baseline verdict. A Claude recommendation pass then adds judgment. Everything renders to one local HTML dashboard. Nothing is uploaded.

Two token costs (what "turn off" saves)

  1. Always-on tax — every enabled skill's name+description sits in context every session, paid even if never invoked. Scales with the number of enabled skills.
  2. On-invoke cost — when a skill fires, its full body loads once.

So the strongest turn-off candidates are skills you never use.

The script

The collector is bundled with this skill at scripts/skill-usage.py. Resolve its absolute path from this skill's directory:

  • installed as a plugin: "$CLAUDE_PLUGIN_ROOT/skills/skill-usage/scripts/skill-usage.py"
  • dropped into ~/.claude/skills/ manually: ~/.claude/skills/skill-usage/scripts/skill-usage.py

Outputs always go to ~/.claude/skill-usage/ (never next to the script), so they survive plugin updates.

Run it (usage only — fast, deterministic)

python3 "<script-path>" --open

Flags: --open open the dashboard · --prune print the never-used prune list · --rescan ignore cache · --demo build a sample-data dashboard (no transcripts; writes demo.html). First run parses all transcripts; later runs only re-parse new/changed files. Token counts use tiktoken if installed, else a chars/4 estimate (pip install tiktoken for a closer number).

This produces usage + token cost + a heuristic baseline verdict. For real recommendations, run the full pass below.

Full recommendation pass (Claude)

Hybrid engine: the script collects deterministic data; this pass adds judgment and writes the persistent verdict store.

  1. Run python3 "<script-path>" — writes ~/.claude/skill-usage/data/skill-usage.json + dashboard.html.
  2. Fetch the current Anthropic skill-authoring docs (search if the URL moved; do not hardcode a stale link). Distill a best-practice checklist → write ~/.claude/skill-usage/data/best-practices.md with a fetched: <date> line.
  3. Read ~/.claude/skill-usage/data/skill-usage.json, the user's ~/.claude/CLAUDE.md + ~/.claude/rules/**, and each candidate SKILL.md (prioritize never-used + lint-flagged; confirm Keep+current in bulk).
  4. Assign per skill {verdict (keep|modernize|turn_off|prune), reason, modernize_note (modernize only), confidence}:
    • off-stack vs the user's stack → prune
    • situational / maybe-later → turn_off
    • valuable but behind docs (weak description, bloated body, stale refs) → modernize
    • good + current → keep
    • genuinely uncertain → keep / low-confidence (never a confident cut)
  5. Write ~/.claude/skill-usage/data/recommendations.json (schema in DESIGN.md §4.2).
  6. Run python3 "<script-path>" --open — re-renders, merging recommendations, and opens the dashboard.

Read the full file on GitHub · 59 lines

Files

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.

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. 4d ago First seen · 59 lines · 122 tokens per session scan A 16978c3ccd28

Subscribe to this mod's changes

skill-usage is a skill published in the GitHub repository paultaki/claude-skill-usage (2 stars, last pushed 2mo ago), licensed MIT. It adds 122 tokens to every session and 1,163 once invoked, about $0.0006 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 2026-08-31.

Analytics and metricsBuilding agents
Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens