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 aiappsgbb/awesome-gbb --skill token-economicsgit clone --depth 1 https://github.com/aiappsgbb/awesome-gbbWrote 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/aiappsgbb/awesome-gbb/token-economics)<a href="https://agentmods.dev/skills/aiappsgbb/awesome-gbb/token-economics"><img src="https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/token-economics/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/aiappsgbb/awesome-gbb/token-economics"><img src="https://agentmods.dev/badge/skills/aiappsgbb/awesome-gbb/token-economics.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00230 | $0.05965 |
| Opus 5.5 | $0.00092 | $0.02386 |
| Sonnet 5.5 | $0.00046 | $0.01193 |
| Haiku 4.5 | $0.00023 | $0.00596 |
Grade A, and why
token-economics 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 6d 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 — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Token economics
Optimize cost per successful task, not tokens per request. One user task can include several inferences (tool search, tool calls, follow-ups, retries); a lever that shrinks the first request but adds a second inference, more reasoning, or a lower success rate can lose money. Measure, change one lever, measure again.
The cost model
For every inference in a task:
cost = U·p_in + C·p_cached (+ W·p_write on GPT-5.6+) + O·p_out (× tier multiplier)
U = uncached input tokens C = cached input tokens W = cache-write tokens
O = output tokens, INCLUDING hidden reasoning tokens
Three independent budgets are in play, and levers trade them against each other:
| Budget | Driven by | Notes |
|---|---|---|
| Money | U, C, W, O × current rates |
Cached input is discounted, not free. Output is several times the input price on most models. |
| Throughput (TPM/429s) | Total tokens per minute | Treat TPM headroom as driven by total input, cached or not, plus the output reservation. Azure's admission estimate counts max_tokens/max_output_tokens in full, even if fewer tokens are generated ([source][az429]). |
| Context window / latency | Total input + reasoning | Large tool catalogs and histories raise time-to-first-token and can reduce tool-selection accuracy. |
Never hardcode prices. Use the current [Azure OpenAI pricing][pricing] for the exact model, deployment type and region.
Measure first (usage fields)
| Field (Responses API) | Meaning |
|---|---|
usage.input_tokens |
All input tokens of this inference |
usage.input_tokens_details.cached_tokens |
Cache reads (discounted) |
usage.input_tokens_details.cache_write_tokens |
Cache writes (GPT-5.6+ Standard); a subset of input_tokens, billed at the write rate (1.25× input on current price sheets). Missing ≠ zero |
usage.output_tokens |
Output including reasoning |
usage.output_tokens_details.reasoning_tokens |
Hidden reasoning share of output |
What ships with it
4 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.
- 6d ago First seen · 370 lines · 230 tokens per session scan A 5a08c4c0368c
token-economics is a skill published in the GitHub repository aiappsgbb/awesome-gbb (8 stars, last pushed yesterday), licensed MIT. It adds 230 tokens to every session and 5,965 once invoked, about $0.0009 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 2026-10-15.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
omh-model-optimization
This is a Hermes-native model-optimization workflow skill.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.