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/iblai/api/iblai-api-spend-capsnpx skills add iblai/api --skill iblai-api-spend-capsgit clone --depth 1 https://github.com/iblai/apiWrote 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/iblai/api/iblai-api-spend-caps)<a href="https://agentmods.dev/skills/iblai/api/iblai-api-spend-caps"><img src="https://agentmods.dev/badge/skills/iblai/api/iblai-api-spend-caps.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00137 | $0.03288 |
| Opus 5 | $0.00068 | $0.01644 |
| Sonnet 5 | $0.00027 | $0.00658 |
| Haiku 4.5 | $0.00014 | $0.00329 |
Grade A, and why
iblai-api-spend-caps scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -X PUT "$dm/api/ai-mentor/orgs/$IBLAI_ORG/spend-caps/tenant/" \ How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iblai-api-spend-caps
Configure and read LLM spend caps for an organization. A spend cap is an admin-imposed maximum LLM cost enforced at one of three scopes:
- tenant — the whole org (one cap per platform).
- agent — one agent/mentor (one cap per agent).
- user_agent — one user on one agent (an explicit per-user cap).
Each cap has a rolling interval (day/week/month/year, calendar
aligned), a dollar limit (max_cost_usd), an enforcement mode
(block refuses further chats once exceeded; alert_only only notifies), and
alert thresholds (fractions of the limit that fire a near-limit alert). When
a chat is blocked, the request is refused with HTTP 429 and a body naming the
interval that was hit (dollar amounts are deliberately omitted). Spend counters
are reconciled from ClickHouse on a schedule and surfaced read-only so a UI
can render a progress bar.
Auth & conventions
- Base URL:
https://api.iblai.app/dm— these are Data Manager (DM) endpoints, so the/dmprefix is required; the/api/ai-mentor/...paths below are appended to it (e.g.https://api.iblai.app/dm/api/ai-mentor/orgs/$IBLAI_ORG/spend-caps/tenant/). Omitting/dmwill not resolve. - Header:
Authorization: Api-Token $IBLAI_API_KEYon every request. - Path vars:
{org}=$IBLAI_ORG(the org key).{mentor}= an agent'sunique_id(a UUID).{user_id}/{username}= the target learner. - Endpoint prefix twin: every path under
api/ai-mentor/also resolves underapi/ai-agent/(alias); either works, pick one and be consistent. - Permission tiers: all cap configuration endpoints (tenant / agent /
user-agent read+write) require a platform admin (RBAC action prefix
Ibl.Mentor/SpendCaps/*). The status endpoint is learner-safe: any authenticated member may read their own status, and admins may read any user's — it returns only a coarse zone + percent, never raw dollars. - PUT is upsert: writing a cap that doesn't exist yet returns 201 Created; writing over an existing one returns 200 OK.
- DELETE and PUT (destructive / budget-changing) calls say "Confirm with the user first."
- Not connected yet? Run
/iblai-api-loginfirst to populateIBLAI_ORG,IBLAI_USERNAME, andIBLAI_API_KEY.
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.
- 5d ago First seen · 236 lines · 137 tokens per session scan A f88350a8155c
iblai-api-spend-caps is a skill published in the GitHub repository iblai/api (15 stars, last pushed 4d ago), licensed MIT. It adds 137 tokens to every session and 3,288 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
llm-cost-advisor
WHAT — Recommend the most cost-effective LLM provider for a given task type. Shows estimated cost per run across available providers and integrates with devcompanion llm-status to show what is actually available.
threnody-cost
View cost/spend dashboard with role, tier, and provider breakdowns from Threnody's local cost telemetry. Use when asked about cost, spend, budget, tokens used, savings, or how much a task/period cost.
adobe-express-monetization
Monetize Adobe Express add-ons with subscriptions and payments. Use when designing checkout flows, defining subscription tiers, implementing webhook verification, managing entitlements, or securing backend billing logic.
pricing-update
Sync OpenUsage's pricing supplement with Cursor's published model pricing. Pulls https://cursor.com/docs/models-and-pricing.md, diffs it against pricingsupplement.json, updates entries/aliases/multipliers, validates, and opens a PR. Use when Cursor adds or re-prices models, a spend tile shows a warning triangle for an…
lov-skill-pricing
为一个或多个 Agent Skill 生成可解释的 Skill Pricing Card：结合创作者时间与维护成本、用户价值、稀缺性、购买信心和生态潜力，输出建议价、价格区间、渠道策略及证据缺口；触发语包括“给这个 Skill 定价”和 “price this Skill”。.
vindicate
Use when the user wants to write, add, fix, stabilize (flaky), refactor, run, or audit Playwright browser tests, draft requirements/stories from a recording (no tests), find test-coverage gaps, scaffold a Playwright project, or set up Playwright CI. Vindicate's guided workflow for grounded, conformant Playwright test…