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 ericrisco/rsc-harness --skill cost-trackinggit clone --depth 1 https://github.com/ericrisco/rsc-harnessWrote 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/ericrisco/rsc-harness/cost-tracking)<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/cost-tracking"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/cost-tracking.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 | $0.00091 | $0.03238 |
| Opus 5 | $0.00046 | $0.01619 |
| Sonnet 5 | $0.00018 | $0.00648 |
| Haiku 4.5 | $0.00009 | $0.00324 |
Grade A, and why
cost-tracking 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 8d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cost tracking
You are building the money meter for an AI or cloud app: every model call gets a token count, a price, a ledger row, and a budget check — so a cap fires before the invoice, not when finance forwards it in a panic. Model-API spend roughly doubled from $3.5B to $8.4B between late 2024 and mid 2025 (firecrawl.dev best-llm-observability-tools, accessed 2026-06-02); the bill is now big enough to need a guardrail, not a spreadsheet at month-end.
The chain you build, in order — each step feeds the next:
- Capture — read tokens from the response, not from a pre-send guess.
- Price — multiply tokens by a versioned, dated rate table.
- Ledger — append one idempotent row per request, tagged for attribution.
- Budget — roll the ledger up against a soft and a hard threshold.
- Guard — alert, degrade, or refuse before the threshold becomes an invoice.
The one rule that organizes everything: bill against the response usage object. Anything you compute before the call is an estimate — good only for the pre-flight cap check, never for the ledger.
What this skill produces
A checkable cost setup: a pricing table (each model row carries effective_date + source), an append-only ledger schema (idempotency key + attribution keys), and a budget with both a soft and a hard threshold. scripts/verify.sh lints those artifacts (last section). Prose alone is not a deliverable — emit the config.
Capture: read usage, do not estimate
Pre-send token counts (tiktoken, Anthropic client.messages.count_tokens()) are estimates. They exist for the pre-flight cap check — "will this request likely breach the budget?" — and nothing else. The truth lands in the response: input, output, cached, and reasoning tokens, plus audio/image tokens where the modality applies. Bill the ledger off that object.
Two provider facts that bite if you assume otherwise:
- Anthropic
count_tokens()returns input tokens only, is free, has its own rate limit, and is still an estimate. Anthropic is not tiktoken-compatible — do not reuse an OpenAI tokenizer to price Claude (platform.claude.com token-counting; github.com/anthropics/anthropic-tokenizer-typescript, accessed 2026-06-02). - Output and reasoning tokens are the expensive half — output runs 4-5x the input rate. A meter that only counts input is wrong by most of the bill.
What ships with it
5 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.
- 8d ago First seen · 176 lines · 91 tokens per session scan A 72a8c57a9a2c
cost-tracking is a skill published in the GitHub repository ericrisco/rsc-harness (70 stars, last pushed today), licensed MIT. It adds 91 tokens to every session and 3,238 once invoked, about $0.0005 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
cost-optimization
Cloud cost analysis and optimization (FinOps).
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
integritypulse
Cloud cost forecasting via the integritypulse MCP server. Use when a user is planning cloud infrastructure, writing Terraform/Pulumi/CDK, comparing cloud providers, or asking "how much will this cost?" Provides verified pricing for AWS, GCP, and Azure — do not estimate cloud costs from training data when this skill is…
agent-trading-predictor
Agent skill for trading-predictor - invoke with $agent-trading-predictor.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
dd-synthesis
Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.