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 ChintanTurakhia/cost-analysis --skill analyzegit clone --depth 1 https://github.com/ChintanTurakhia/cost-analysisWrote 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/chintanturakhia/cost-analysis/analyze)<a href="https://agentmods.dev/skills/chintanturakhia/cost-analysis/analyze"><img src="https://agentmods.dev/badge/skills/chintanturakhia/cost-analysis/analyze/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/chintanturakhia/cost-analysis/analyze"><img src="https://agentmods.dev/badge/skills/chintanturakhia/cost-analysis/analyze.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 | $0.00093 | $0.03930 |
| Opus 5 | $0.00046 | $0.01965 |
| Sonnet 5 | $0.00019 | $0.00786 |
| Haiku 4.5 | $0.00009 | $0.00393 |
Grade A, and why
analyze 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 9d 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 — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cost Analysis
Analyzes Claude Code token usage and cost from local session data stored in ~/.claude/projects/. Reads raw conversation files to extract per-turn model and token data, then computes costs using Anthropic's current pricing — including prompt caching tokens. Outputs a clean summary with totals, trends, and model recommendations. With --mcp, provides deep analysis of MCP server overhead including tool result sizes, schema bloat, and optimization recommendations.
Arguments
$ARGUMENTS is an optional filter string. Supported flags:
--project <name>— Filter to sessions whose working directory matches<name>(case-insensitive substring match on the project path)--days <N>— Only include sessions from the last N days (shorthand for--since (today - N days)). Default: all time--since <YYYY-MM-DD>— Include only sessions on or after this date--until <YYYY-MM-DD>— Include only sessions on or before this date. Note:--days Nremains a shorthand for--since (today - N days). All three can be combined.--model <name>— Filter to sessions that used a specific model (e.g.,opus,sonnet,haiku)--top <N>— Show only the top N most expensive sessions (default: 10)--mcp— Focus analysis on MCP (Model Context Protocol) server overhead: tool result sizes, schema bloat, cost impact, and optimization recommendations--mcp-server <name>— Filter MCP analysis to a specific server (e.g.,glean-hosted,pencil). Implies--mcp--max-sessions <N>— Hard cap on session count. If session count after date filtering exceeds N, truncates the oldest sessions. Use with caution — truncation may skew aggregates.--save [path]— Write the HTML report to a file. Default path:~/claude-cost-YYYY-MM-DD.html.--budget <N>— Set a monthly spending threshold in dollars. Adds a budget status line (pace vs. limit) to the report header.
If no arguments are given, analyze all sessions and show a full breakdown.
Examples
What ships with it
9 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.
- 9d ago First seen · 277 lines · 93 tokens per session scan A b6613b08fedc
analyze is a skill published in the GitHub repository ChintanTurakhia/cost-analysis (9 stars, last pushed 5mo ago), licensed MIT. It adds 93 tokens to every session and 3,930 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 2026-08-31.
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…
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…
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…