Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/leopu00/job-hunter-teamnpx agentmods add skills/leopu00/job-hunter-team/check-usage-httpWrote 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/leopu00/job-hunter-team/check-usage-http)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/check-usage-http"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/check-usage-http.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.00773 |
| Opus 5 | $0.00024 | $0.00387 |
| Sonnet 5 | $0.00010 | $0.00155 |
| Haiku 4.5 | $0.00005 | $0.00077 |
Grade A, and why
check-usage-http 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.
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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill — Check usage via HTTP (rapido, ~2s, ZERO token)
QUANDO USARLA
Primario quando ricevi [BRIDGE FAILURE] (= il bridge non riesce a leggere usage). HTTP è veloce, gratis (no spawn TUI), e quasi sempre funziona — solo Anthropic rate-limita aggressivamente con tick rapidi.
Ordine di fallback: HTTP → TUI → FATAL.
Step 1 — Leggi provider attivo
python3 -c "import json; print(json.load(open('/jht_home/jht.config.json'))['active_provider'])"
Output: claude / kimi / codex.
Step 2 — Chiama HTTP via libreria del bridge
Usa le funzioni fetch_*_api esposte da sentinel-bridge.py come libreria:
python3 -c "
import importlib.util
spec = importlib.util.spec_from_file_location('br', '/app/.launcher/sentinel-bridge.py')
br = importlib.util.module_from_spec(spec); spec.loader.exec_module(br)
print(br.fetch_claude_api()) # claude → /api/oauth/usage
# OPPURE: br.fetch_kimi_api() # kimi → /coding/v1/usages
# OPPURE: br.fetch_codex_rollout() # codex → file rollout JSONL locale
"
Output Python dict:
{'usage': 42, 'reset_at': '20:10', 'weekly_usage': 25}
Step 3 — Gestisci edge cases
Anthropic 429 (rate-limit)
fetch_claude_api() ritorna la stringa "RATE_LIMIT" invece del dict. Cooldown interno 5 min: prima di quello tornerà ancora "RATE_LIMIT". Significa: HTTP non disponibile per 5 min → cadi su L2 (TUI worker).
None / empty
API down, credenziali scadute, file rollout codex assente. Cadi su L2.
Step 4 — Scrivi sample nel JSONL
python3 /app/shared/skills/usage_record.py --manual \
--usage <X> \
--reset-at <HH:MM> \
--weekly <W> \
--provider <claude|kimi|openai> \
--source sentinella-api
Lo script chiama internamente compute_metrics → calcola velocità, projection, status, throttle. Stampa il sample completo come JSON.
Step 5 — Procedi con la decisione
Hai ora un sample fresco con usage, proj, status. Aggiorna la tua memoria interna (vedi skill memory-state) e decidi se mandare ordine al Capitano (vedi skill order-formats).
What ships with it
6 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.
- 4d ago First seen · 76 lines · 48 tokens per session scan A db8cc06a799e
check-usage-http is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 773 once invoked, about $0.0002 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
gws-events
Subscribe to Google Workspace events.
gws-events-renew
Google Workspace Events: Renew/reactivate Workspace Events subscriptions.
gws-script-push
Google Apps Script: Upload local files to an Apps Script project.
voiden
Create and edit Voiden .void files for API testing. Covers the .void file format and all enabled extension block types.
agent-desktop-ffi
C-ABI bindings over agent-desktop's PlatformAdapter. Consumers (Python ctypes, Swift, Node ffi-napi, Go cgo, C++, Ruby fiddle) link libagentdesktopffi.{dylib,so,dll} and call ad functions directly instead of spawning the CLI binary per call. The canonical observe-act workflow is: adinit → adadaptercreate[withsession]…
api-debugging
Systematic approach to debugging REST APIs, HTTP errors, authentication issues, and network problems. Use when the user has API errors, status code issues, timeout problems, or needs help troubleshooting HTTP requests.