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 gtapps/claude-code-hermit --skill pricing-refreshgit clone --depth 1 https://github.com/gtapps/claude-code-hermitWrote 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/gtapps/claude-code-hermit/pricing-refresh)<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/pricing-refresh"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/pricing-refresh.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 | $0.00076 | $0.00605 |
| Opus 5 | $0.00038 | $0.00302 |
| Sonnet 5 | $0.00015 | $0.00121 |
| Haiku 4.5 | $0.00008 | $0.00060 |
Grade A, and why
pricing-refresh 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 today.
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.
What it actually says
Pricing refresh
Compare plugins/Codex-hermit/scripts/lib/pricing.ts to Anthropic's live
docs and, only after explicit confirmation, edit the table. Do not run this
on a schedule. Do not write anything under an operator's .Codex-hermit/.
Step 1 — Read the table
Read plugins/Codex-hermit/scripts/lib/pricing.ts. Record every PRICING
key, its { input, output, cacheRead?, fast? } rates, the CACHE_WRITE_5M /
CACHE_WRITE_1H / CACHE_READ multipliers, and PRICING_VERIFIED.
Step 2 — Fetch live sources
Load the bundled Codex-api skill. From its shared/live-sources.md, WebFetch
these three URLs:
- Models Overview
- Pricing
- Prompt Caching
Extract current model ids, per-MTok input/output, cache write (5m and 1h) and
read multipliers, any per-model cacheRead absolute rate, and fast-mode rates.
Step 3 — Unknown ids in the log
From .Codex-hermit/cost-log.jsonl (this repo's own hermit dir, last 30
days of timestamp), list distinct model values that are not exact
PRICING keys (dated <key>-YYYYMMDD snapshots of an existing key count as
exact). Print them. Do not edit operator installs.
Step 4 — Diff
Print a rate-diff table: id, live input/output/cache/fast vs the file. Flag
missing ids, stale rates, and a PRICING_VERIFIED date that is not today.
Stop here unless the operator confirms an edit.
Step 5 — Edit on confirmation only
If the operator explicitly confirms:
- Edit
plugins/Codex-hermit/scripts/lib/pricing.tsrates and keys to match the live table. SetPRICING_VERIFIEDto today's date (YYYY-MM-DD). - Add a
### Fixedbullet underplugins/Codex-hermit/CHANGELOG.md[Unreleased]: rate table refreshed for the current generations. - Run
cd plugins/Codex-hermit && bun test tests/pricing.test.ts.
Do not commit. Do not bump min_claude_code_version. Do not add a hook, a
routine, or a config.json entry.
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.
- today Changed · +1 tokens per session 251fcdbede59
- yesterday First seen · 56 lines · 75 tokens per session scan A cb84526a338f
pricing-refresh is a skill published in the GitHub repository gtapps/claude-code-hermit (74 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 605 once invoked, about $0.0004 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 2026-09-06.
Other skills, from other repositories
monitor
Autonomous monitoring loop. Checks open trades against SL/TP levels, closes trades that hit targets, evaluates expired predictions, and generates periodic summaries. Run via cron for full autonomy. Usage: /monitor.
validate-predictions
Review and validate pending predictions against current market data. Usage: /validate-predictions.
analyze
Run a comprehensive multi-agent crypto analysis with phased execution. Usage: /analyze BTC or /analyze ETH SOL.
close-trade
Close an open trade and run post-mortem analysis. Usage: /close-trade trade001 or /close-trade trade001 at 98500.
portfolio
View current portfolio status, open trades, and performance stats. Usage: /portfolio.
quick
Quick single-agent market check. Usage: /quick BTC or /quick ETH.