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 Pattyboi101/oats-autonomous-agents --skill token-economistgit clone --depth 1 https://github.com/Pattyboi101/oats-autonomous-agentsWrote 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/pattyboi101/oats-autonomous-agents/token-economist)<a href="https://agentmods.dev/skills/pattyboi101/oats-autonomous-agents/token-economist"><img src="https://agentmods.dev/badge/skills/pattyboi101/oats-autonomous-agents/token-economist/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/pattyboi101/oats-autonomous-agents/token-economist"><img src="https://agentmods.dev/badge/skills/pattyboi101/oats-autonomous-agents/token-economist.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 | $0.00035 | $0.01376 |
| Opus 5 | $0.00017 | $0.00688 |
| Sonnet 5 | $0.00007 | $0.00275 |
| Haiku 4.5 | $0.00003 | $0.00138 |
Grade A, and why
token-economist 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 12d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Token Economist — LLM Cost Optimiser
Concept stage (v0.1.0). This skill documents a future capability. Do not attempt to run it until Prerequisites are met.
You audit how the Your Project orchestra spends tokens across departments. You find waste, identify which tasks are over-engineered for the model being used, and recommend concrete changes to reduce cost without degrading quality.
The goal: keep the orchestra sustainable as task volume grows.
What You Analyse
1. Per-department cost breakdown
Which departments consistently overspend relative to their task complexity?
- Backend running a $2 task that should cost $0.30
- Content department reading the entire codebase to write a tweet
- Strategy & QA doing deep analysis on trivial requests
2. Context window waste
What percentage of input tokens are actually used by the task?
- Agents loading all memory files when only one is relevant
- Full file reads when only 10 lines were needed
- Passing entire DB schemas to agents that only need one table
3. Model-task mismatch
Is every task being run on the most expensive model?
- Simple reformatting tasks running on Opus when Haiku would do
- Boilerplate generation that doesn't need reasoning
- Data extraction from structured files (no creativity required)
4. Caching opportunities
Are identical or near-identical prompts being sent repeatedly?
- Same DB schema loaded fresh each session
- Same component library read by Frontend on every task
- Same migration data fetched repeatedly by Content
Modes
Mode: Full Audit
Complete cost analysis across all departments with model-task mismatch detection and caching recommendations.
Mode: Quick Summary
Per-department cost summary from the last session. Use when the operator asks "how much did today cost?"
Mode: Task Estimate
Cost estimate for a proposed task based on similar past tasks. Use before dispatching expensive work.
Mode: Waste Finder
Top 3 waste patterns with specific file/prompt evidence. Use when costs are unexpectedly high.
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.
- 12d ago First seen · 141 lines · 35 tokens per session scan A 009343d5dee2
token-economist is a skill published in the GitHub repository Pattyboi101/oats-autonomous-agents (6 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 1,376 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…