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/aarora79/claude-code-usage-analyzer/tokenomics-dashboardnpx skills add aarora79/claude-code-usage-analyzer --skill tokenomics-dashboardgit clone --depth 1 https://github.com/aarora79/claude-code-usage-analyzerWrote 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/aarora79/claude-code-usage-analyzer/tokenomics-dashboard)<a href="https://agentmods.dev/skills/aarora79/claude-code-usage-analyzer/tokenomics-dashboard"><img src="https://agentmods.dev/badge/skills/aarora79/claude-code-usage-analyzer/tokenomics-dashboard.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 | $0.00114 | $0.01145 |
| Opus 5 | $0.00057 | $0.00573 |
| Sonnet 5 | $0.00023 | $0.00229 |
| Haiku 4.5 | $0.00011 | $0.00114 |
Grade A, and why
tokenomics-dashboard 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 4d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tokenomics Dashboard Skill
Produce the self-contained HTML tokenomics dashboard for a chosen window of Claude Code usage, then present it to the user with a director-of-tokenomics commentary. This wraps the claude-usage-analyzer CLI, which fetches usage via ccusage, prices it from LiteLLM, and writes the dashboard to data/output/tokenomics-dashboard.html.
The one input: number of days
The skill takes exactly one input from the user: how many days of history to analyze.
- If the user already gave a number ("last 30 days", "past 2 weeks"), use it and skip the question.
- Otherwise ask, and only this: "How many days of history should I analyze?" Offer sensible options (7, 30, 90) and note they can enter another number.
- State plainly, before fetching: "I will get this data using the ccusage tool." ccusage reads Claude Code's local usage files; nothing is uploaded.
Do not ask about output paths, formats, or models. Those are fixed: the analyzer always writes to data/output/ and prices every model dynamically.
Workflow
Step 1: Confirm the window and compute the start date
Convert the number of days into a --since date in YYYYMMDD format. The analyzer's --since is an inclusive start date, so for "last N days" use today minus (N - 1) days. Get today's date from the environment context; do not guess it. Tell the user the resulting date range you will analyze.
Step 2: Run the analyzer (it fetches via ccusage)
From the repository root, run the CLI with a refresh so the window is re-fetched, not served from a stale cache:
uv run claude-usage-analyzer --since <YYYYMMDD> --refresh
- Announce that this uses
npx ccusage@latestunder the hood to read local usage data, then prices it from LiteLLM. - If
npx/ccusageis unavailable, the tool prints an actionable error; relay it and stop rather than inventing numbers. - The run writes
data/output/tokenomics-dashboard.html,claude-usage-report.md, andclaude-usage-analysis.json.
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.
- 4d ago First seen · 69 lines · 114 tokens per session scan A 0c54c48ab7c7
tokenomics-dashboard is a skill published in the GitHub repository aarora79/claude-code-usage-analyzer (5 stars, last pushed 1mo ago), licensed MIT. It adds 114 tokens to every session and 1,145 once invoked, about $0.0006 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
token-tracker
Track and analyze LLM token usage across projects. Monitor costs, generate reports, set budgets, and visualize usage patterns. Use when users want to: check token usage, estimate costs, set budgets, export reports, or understand AI spending patterns.
workflow
Professional AI programming assistant with structured workflow (Research -> Ideate -> Plan -> Execute -> Optimize -> Review) for developers.
r3f-animation
React Three Fiber animation - useFrame, useAnimations, spring physics, keyframes. Use when animating objects, playing GLTF animations, creating procedural motion, or implementing physics-based movement.
golden-rss
Use when testing the rss golden build.
r3f-best-practices
React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…