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 agentmods add skills/jerry0022/dotclaude/auto-usagenpx skills add Jerry0022/dotclaude --skill auto-usagegit clone --depth 1 https://github.com/Jerry0022/dotclaudeWrote 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/jerry0022/dotclaude/auto-usage)<a href="https://agentmods.dev/skills/jerry0022/dotclaude/auto-usage"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/auto-usage.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.01786 |
| Opus 5 | $0.00032 | $0.00893 |
| Sonnet 5 | $0.00013 | $0.00357 |
| Haiku 4.5 | $0.00006 | $0.00179 |
Grade A, and why
auto-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 3d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refresh Usage Data
Fetch live token usage for the completion card's battery line.
Step 0 — Load Extensions
Check for optional overrides. Use Glob to verify each path exists before reading. Do NOT call Read on files that may not exist — skip missing files silently (no output).
- Global:
~/.claude/skills/auto-usage/SKILL.md+reference.md - Project:
{project}/.claude/skills/auto-usage/SKILL.md+reference.md - Merge: project > global > plugin defaults
Step 1 — Fetch data
1·0. Native source first (no scrape)
~/.claude/usage-live.json is kept minute-fresh by the native statusLine
writer (statusline-usage.js, registered by
ss.statusline.ensure) — it maps Claude Code's rate_limits JSON onto the
usage schema with no browser and no extra Claude turn. If the file's
timestamp is recent (≤ a couple of minutes), just read it — you are done;
skip the Edge scrape entirely. Only when it is stale/absent (pre-first-API
response, an unsupported login, weeklySonnet needed, or a host without
the statusLine writer) fall through to the Edge scraper below. The
dotclaude-completion MCP server applies this same warm-read-first logic
automatically in get_usage / render_completion_card.
Automatic path is zero-interaction. The MCP fallback always runs the scraper
with --no-login, so the completion card never opens a login window — a
logged-out profile just serves statusLine/cached data. A one-time login is
offered only when you run this skill manually (the command in 1a omits
--no-login). The card itself renders only the 5h + weekly numbers, which the
native statusLine source already provides token-free; weeklySonnet is a
manual-summary extra, not a card field.
1·1. Edge CDP fetcher (fallback)
The script spawns a dedicated, isolated Edge instance with its own
user-data-dir under ~/.claude/edge-usage-profile. It is completely
independent from the user's main Edge — separate cookies, separate
processes, no tabs touched. It fetches usage via a cookie-authed in-page
call to the internal API (GET /api/organizations/{id}/usage +
/rate_limits) — the settings page became an SPA overlay (2026-05) that
never renders headless, so DOM parsing is only a single-grab last resort.
Runs headless; the hidden instance is reused across runs.
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.
- 3d ago First seen · 131 lines · 64 tokens per session scan A 86bf819a7ccf
auto-usage is a skill published in the GitHub repository Jerry0022/dotclaude (4 stars, last pushed 4d ago), licensed MIT. It adds 64 tokens to every session and 1,786 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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.
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.
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.
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.
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…