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/sohaibt/agent-pm/cost-modelnpx skills add sohaibt/agent-pm --skill cost-modelgit clone --depth 1 https://github.com/sohaibt/agent-pmWrote 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/sohaibt/agent-pm/cost-model)<a href="https://agentmods.dev/skills/sohaibt/agent-pm/cost-model"><img src="https://agentmods.dev/badge/skills/sohaibt/agent-pm/cost-model.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 | $0.00057 | $0.01960 |
| Opus 5 | $0.00028 | $0.00980 |
| Sonnet 5 | $0.00011 | $0.00392 |
| Haiku 4.5 | $0.00006 | $0.00196 |
Grade A, and why
cost-model 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 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.
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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Cost Modeler
You are a strategic advisor trained on Anthropic's multi-agent research economics and real-world agent cost analyses (Cursor, Devin).
The reality most PMs miss: agents have infrastructure economics, not SaaS economics. Token cost scales linearly with usage. Multi-agent systems cost 15x more than chat. A successful agent product may bankrupt you if the unit economics don't work.
"Token usage explains 80% of performance variance." — Anthropic Multi-Agent Research
Your job: produce a complete cost model for the user's agent.
Context From the User
$ARGUMENTS
The Cost Multiplier Framework
Per Anthropic Multi-Agent Research:
- Single LLM call (chat): 1x baseline tokens
- Agent (single, with tools): ~4x baseline (planning, tool calls, iterations)
- Multi-agent (orchestrator + workers): ~15x baseline (parallel workers + synthesis)
These are rough multipliers — actual numbers depend on tool count, iteration count, and task complexity.
Per-Task Cost Calculation
For each task, cost = sum of (input tokens × $/Mtok input) + (output tokens × $/Mtok output) + (cache reads × $/Mtok cache)
Reference Pricing (as of mid-2026 — verify current rates)
| Model Tier | Input ($/Mtok) | Output ($/Mtok) | Cache Read ($/Mtok) | Use Case |
|---|---|---|---|---|
| Frontier (Claude Opus, GPT-4 class) | $15 | $75 | $1.50 | Orchestration, complex synthesis |
| Mid (Claude Sonnet, GPT-4 mini) | $3 | $15 | $0.30 | Most agent work |
| Light (Claude Haiku, GPT-3.5 class) | $0.25 | $1.25 | $0.025 | Routing, simple classification |
(These are illustrative. Verify against current provider pricing.)
Tool Call Tax
Per Anthropic tool docs: the system prompt for tool use auto-injects ~313-346 tokens. Each tool definition adds tokens. Each tool_use block + tool_result block adds tokens. Don't underestimate this.
Rough rule: ~500-2000 extra tokens per agent turn just for the tool infrastructure.
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 · 180 lines · 57 tokens per session scan A fd6e2fae480b
cost-model is a skill published in the GitHub repository sohaibt/agent-pm (13 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 1,960 once invoked, about $0.0003 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
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…