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 mhlaghari/stuntman --skill usagesgit clone --depth 1 https://github.com/mhlaghari/stuntmanWrote 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/mhlaghari/stuntman/usages)<a href="https://agentmods.dev/skills/mhlaghari/stuntman/usages"><img src="https://agentmods.dev/badge/skills/mhlaghari/stuntman/usages/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/mhlaghari/stuntman/usages"><img src="https://agentmods.dev/badge/skills/mhlaghari/stuntman/usages.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00114 | $0.00692 |
| Opus 5 | $0.00057 | $0.00346 |
| Sonnet 5 | $0.00023 | $0.00138 |
| Haiku 4.5 | $0.00011 | $0.00069 |
Grade A, and why
usages scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
stuntman: usages — one board for every subscription
Run the probe and present the board. Everything it reads is zero-token and zero-cost — no worker is invoked.
Run it
Read host and tool setup.
USAGES="$STUNTMAN_ROOT/bin/usages"
"$USAGES" --json
Present it
Render a small table from the JSON — backend, window(s), % used, reset time,
freshness. Keep the reset times in the user's local timezone (the pretty mode
"$USAGES" already formats them if you prefer to show its output directly).
Explain freshness honestly:
- claude and deepseek are live probes (OAuth usage endpoint / balance API). DeepSeek is metered — its "limit" is the remaining balance, so flag a low balance (< $1) as worth topping up.
- codex is read from the last
rate_limitssnapshot in~/.codex/sessions/— as fresh as the last codex run. Iffive_hour_expired/weekly_expiredis true, that window has reset since the snapshot (usage is back to ~0%). Ifsnapshot_age_sis large (> a day), say so and mention that any/delegatecodex run refreshes it. - agy and muse genuinely expose nothing locally (Antigravity keeps quota server-side; Muse's event stream has no usage) — show them as n/a with that reason, not as an error.
If claude.blocked is true, point at /relay (spanning the cap is exactly
what it's for).
For Codex relay decisions, use bin/codex-window from the same bundle. It reads
local quota snapshots without probing Claude credentials or DeepSeek. An elapsed
reset is not evidence of current usage; check the host's /status if stale.
Status line
In Claude Code, if the user asks for these numbers in their status line, wire
"$USAGES" --statusline into their existing statusline command — it prints a
compact worker segment (e.g. CX 23%/5h 4%/wk · DS $0.89), caches for 5
minutes (~/.stuntman/usages-cache.txt), and prints nothing on failure, so
it's safe to embed. Claude's own numbers are deliberately absent from it —
Claude Code's status line JSON already carries them natively.
In Codex, present the board in the conversation; do not write Claude's status
line configuration or assume Codex accepts the same command format.
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 Changed · +8 lines 57a057434ca7
- 9d ago First seen · 49 lines · 114 tokens per session scan A 39ac60c281b8
usages is a skill published in the GitHub repository mhlaghari/stuntman (13 stars, last pushed 2d ago), licensed MIT. It adds 114 tokens to every session and 692 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 2026-08-30.
Other skills, from other repositories
clawrouter
Hosted-gateway LLM router — save 84% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 76 models from OpenAI, Anthropic, Google, DeepSeek, xAI, Z.AI, and more. 7 free open-weight models included. Also exposes realtime market data…
surf
Use this skill — NOT browser or webfetch — for ALL Surf crypto-data calls. 83 endpoints at localhost:8402/v1/surf/ covering CEX/DEX markets, on-chain SQL over 80+ ClickHouse tables (Ethereum, Base, Arbitrum, BSC, TRON, HyperEVM, Tempo), 100M+ labeled wallets, prediction markets (Polymarket + Kalshi), social/CT…
phone
Verify phone numbers (carrier + SIM-swap fraud signals) and place AI-powered outbound voice calls via BlockRun's gateway (Twilio + Bland.ai). Trigger when the user asks to look up a number, check fraud risk, buy/rent a phone number, or place an AI voice call. Payment is automatic via x402 from the wallet.
imagegen
Generate or edit images via BlockRun's image API. Trigger when the user asks to generate, create, draw, make an image — or to edit, modify, change, or retouch an existing image.
polymarket-trading
Use when the user wants to actually PLACE, manage, or redeem bets on Polymarket (not just read odds — that's the blockrunpredexon data tools). Covers setup (deposit wallet, funding, approvals), buy/sell with confirm gating, positions, redeeming winnings, geoblock handling, and the end-to-end flow.
release
Use this skill for EVERY ClawRouter release. Enforces the full checklist — version sync, CHANGELOG, build, tests, npm publish, git tag, GitHub release. No step can be skipped.