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 stevengonsalvez/agents-in-a-box --skill costgit clone --depth 1 https://github.com/stevengonsalvez/agents-in-a-boxWrote 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/stevengonsalvez/agents-in-a-box/cost)<a href="https://agentmods.dev/skills/stevengonsalvez/agents-in-a-box/cost"><img src="https://agentmods.dev/badge/skills/stevengonsalvez/agents-in-a-box/cost/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/stevengonsalvez/agents-in-a-box/cost"><img src="https://agentmods.dev/badge/skills/stevengonsalvez/agents-in-a-box/cost.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 | $0.00120 | $0.01094 |
| Opus 5.5 | $0.00048 | $0.00438 |
| Sonnet 5.5 | $0.00024 | $0.00219 |
| Haiku 4.5 | $0.00012 | $0.00109 |
Grade A, and why
ainb-fleet:cost 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 1mo 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ainb fleet:cost
Fleet-shaped spend rollups. ainb already tracks cost_usd per provider call
(the burndown plugin aggregates it); this verb reshapes that data into
per-session / per-model / per-day / per-group USD totals joined to the live
fleet, and evaluates configured budget caps.
Run
ainb fleet cost # text tables (default)
ainb --format json fleet cost # JSON for piping
ainb --format json fleet cost --period week # window: today|week|30days|month|all
--format is a global flag — it goes before fleet, not after cost.
The --period window scopes the data (default month): burndown date-bounds
its call set and re-aggregates, so a narrower period returns less spend; all
reports lifetime totals.
Output fields (JSON)
| field | meaning |
|---|---|
totals |
fleet-wide {cost_usd, bucket, session_count, model_count} |
sessions[] |
per-session {session_id, provider, project, cwd?, group?, cost_usd, bucket}, sorted by descending cost |
models[] |
per-model {model, cost_usd, bucket}, sorted by descending cost |
daily[] |
per-day {date, cost_usd, bucket} |
groups[] |
per-workspace {group, cost_usd, session_count, bucket} (only sessions that match a live fleet cwd) |
budget_breaches[] |
{scope, subject, cwd?, cost_usd, limit_usd} — caps crossed this run (also delivered to notifyd) |
bucket is the token breakdown: input_tokens, cache_creation_tokens,
cache_read_tokens, output_tokens, reasoning_tokens, call_count,
cost_usd.
Budget caps
Configure spend ceilings in config.toml (project config overrides user
config). A breach fires a notifyd alert (Notification:budget_exceeded,
surfacing as WaitingOnUser) and lands in notifications.db.
[fleet.cost]
session_usd = 5.0 # warn when any single session crosses $5
group_usd = 25.0 # warn when any workspace group crosses $25
[fleet.cost.session_overrides]
"abc123" = 50.0 # a long-running session gets its own ceiling
[fleet.cost.group_overrides]
"infra" = 100.0 # the infra workspace gets a higher ceiling
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.
- 1mo ago First seen · 110 lines · 120 tokens per session scan A eaacf784bbdc
ainb-fleet:cost is a skill published in the GitHub repository stevengonsalvez/agents-in-a-box (28 stars, last pushed 4d ago), licensed MIT. It adds 120 tokens to every session and 1,094 once invoked, about $0.0005 per session on Opus 5.5. 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
defi-protocol-templates
Implement DeFi protocols with production-ready templates for staking, AMMs, governance, and flash loans. Use when building decentralized finance applications or smart contract protocols.
metronome
Guides Metronome usage-based billing integration decisions — event ingestion (single and batch, idempotency, billable metrics), contract design (rate cards, overrides, dimensional pricing, products), invoicing lifecycle (grace periods, finalization, Stripe sync), credit and commit management (prepaid, postpaid…
lov-skill-pricing
A pricing workflow for creating an explanation-backed pricing card for an AI agent skill. It considers creation and maintenance effort, user value, scarcity, buyer confidence, and distribution potential.
lov-expense-report
A tool that reads invoice photos, scanned receipts, or expense descriptions and turns them into a categorized Excel reimbursement report. It extracts details such as date, vendor, item, amount, and notes.
chinese-git-workflow
A Git workflow guide tailored to Chinese-hosted platforms such as Gitee, Coding.net, and GitLab, including their code-review and build systems.
chinese-commit-conventions
A Chinese-language convention for writing Git commit messages, based on Conventional Commits, a standard format that tools can use to classify changes and build changelogs.