Token Monitor is a local-first desktop widget that tracks token usage, costs, account limits, and session details across many AI coding tools. It is for developers who use tools such as Claude Code, Codex, Cursor, and OpenCode across multiple devices, with synchronized usage history and breakdowns.
Borrowing it
Nothing to install: this file belongs to Javis603/token-monitor. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Javis603/token-monitor/main/AGENTS.mdgit clone --depth 1 https://github.com/Javis603/token-monitorWrote 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/instructions/javis603/token-monitor/agents-md)<a href="https://agentmods.dev/instructions/javis603/token-monitor/agents-md"><img src="https://agentmods.dev/badge/instructions/javis603/token-monitor/agents-md/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/instructions/javis603/token-monitor/agents-md"><img src="https://agentmods.dev/badge/instructions/javis603/token-monitor/agents-md.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 | $0.02191 | $0.02191 |
| Opus 5.5 | $0.00876 | $0.00876 |
| Sonnet 5.5 | $0.00438 | $0.00438 |
| Haiku 4.5 | $0.00219 | $0.00219 |
Grade A, and why
token-monitor AGENTS.md 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This is the entry point for project guidance shared by every coding agent (Claude Code, Codex, Cursor, …). It is loaded automatically; the documents it routes to are not, so anything an unrelated change can break is listed under Tripwires here, with the full reasoning in the linked document.
Commands
npm start # launch the Electron widget (= npm run widget / npm run dev)
npm run hub # start the Node hub on port 17321
npm run agent # start the headless collector→hub agent
npm run agent:once # one-shot collect+post, then exit (useful for cron/launchd)
npm test # run the node:test suite (node --test "tests/**/*.test.js")
npm run lint # ESLint flat config (eslint.config.js)
npm run verify # lint + test (single local entry point)
Automated verification is npm run verify; CI (.github/workflows/ci.yml) runs lint + test on push/PR across Node 22 & 24. The toolchain (ESLint 10 + the node:test glob) needs Node 22.13+ and DSH session decoding needs zlib.zstdDecompressSync (Node 22.15+), which is why engines.node is >=22.15.0.
To dry-run the agent without posting: npm run agent:once -- --dry-run.
Where guidance lives
| Changing… | Read first |
|---|---|
| a boundary shared by the widget, agent, Hub or Worker; the collector, limits runtime, credentials or wire record | docs/architecture.md |
an existing provider under src/shared/providers/<id>/ or src/electron/providers/<id>/ |
The note whose ids: front matter lists that id — grep -lE '^ids:.*[[, ]<id>[],]' docs/providers/*.md; use its read_when to select relevant guidance. If none exists, use the code/tests and shared code layout |
| adding or renaming a tracked client | Tracked-client checklist, including its partition invariants |
| adding or renaming a limits provider | Limits-provider checklist |
| watch roots, event handling or targeted refreshes | Watching, partition invariants, and the matching provider note's source rules |
| the device wire shape or Hub endpoints | docs/API.md |
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 Changed · +5 lines · +198 tokens per session f7143f0c4b88
- 1mo ago Changed · +54 tokens per session 974b19cabc5c
- 1mo ago Changed · -97 lines · -7,164 tokens per session 4fcf74e785ba
- 1mo ago Changed · -1 tokens per session 60ff1f642e1a
- 1mo ago Changed · +77 tokens per session af2568808ea6
- 1mo ago Changed · +415 tokens per session 57d000a17d99
- 1mo ago Changed · +1 lines · +102 tokens per session 149231e0ae38
- 1mo ago Changed · +187 tokens per session ee897c62d5ed
- 1mo ago Changed · +25 lines · +1,475 tokens per session 8a499f8ca2cf
- 1mo ago First seen · 156 lines · 6,848 tokens per session scan A 40f1d9cbd596
token-monitor AGENTS.md is an instructions file published in the GitHub repository Javis603/token-monitor (3,386 stars, last pushed today), licensed MIT. It adds 2,191 tokens to every session, about $0.0088 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.