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/dburkart/auto-engineer/usagenpx skills add dburkart/auto-engineer --skill usagegit clone --depth 1 https://github.com/dburkart/auto-engineerWhat 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 | $0.00070 | $0.00732 |
| Opus 5 | $0.00035 | $0.00366 |
| Sonnet 5 | $0.00014 | $0.00146 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
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 2d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
usage
The authoritative source for session-quota state is the set of anthropic-ratelimit-unified-* response headers Anthropic attaches to every /v1/messages call. Claude Code reads them into memory and feeds them to its statusline — they are the real numbers, not an estimate.
Since that state lives only in the running Claude Code process, this skill fetches it by making a minimal 1-token probe call and parsing the headers. Result is cached for 60s at ~/.claude/cache/usage-probe.json so repeat invocations are free.
Primary command
bash .claude/skills/usage/probe.sh
(Add --force to bypass the 60s cache.)
Output is a single-line JSON like:
{"http":200,"fetched_at":1776054016,
"5h":{"utilization":0.38,"resets_at":1776056400,"status":"allowed"},
"7d":{"utilization":0.33,"resets_at":1776567600,"status":"allowed"},
"overage":{"utilization":0.0,"resets_at":1777593600,"status":"allowed"}}
Fields: utilization is 0..1+ (can exceed 1 when the window is over-consumed), resets_at is Unix epoch seconds, status is allowed / allowed_warning / rejected.
Output format
Always emit these two machine-readable lines first (auto-engineer step 9 parses them):
remaining_pct: <max(0, 100 - 5h.utilization*100), rounded to 1 decimal>
reset_ts: <ISO-8601 of 5h.resets_at>
Then a short human summary: 5h %, 7d %, overage %, each window's status, time-until-reset, and a note if status=rejected (Claude Code is currently blocked on that limit until reset).
Fallback
If the probe returns an error (no credentials, non-200, missing headers), fall back to ccusage:
npx -y ccusage blocks --active --token-limit max --json
Label fallback output clearly as estimated — ccusage benchmarks against the user's all-time largest block, not the plan's real cap, so its percentage is routinely off vs. the probe. Use projection.remainingMinutes and endTime from .blocks[0].
Caveats
- The probe costs one tiny Haiku call (~22 in / 1 out, well under $0.001). The 60s cache keeps this negligible.
overageappears only on plans where extra-usage is enabled; absent otherwise.- If the user is fully rate-limited (
5h.status == "rejected"), the probe itself still succeeds — Anthropic returns headers on 200s and rejects only subsequent inference calls. If it ever fails with 429, reportremaining_pct: 0and surface the cachedreset_tsfrom a prior probe if one exists.
What ships with it
1 file 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.
- 2d ago First seen · 57 lines · 70 tokens per session scan A ca449fc24c94
usage is a skill published in the GitHub repository dburkart/auto-engineer (5 stars, last pushed 4mo ago), licensed BSD-3-Clause. It adds 70 tokens to every session and 732 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.