Token Tracker is a local-first dashboard and desktop application that records AI token usage and costs across coding tools. It is for developers who want to monitor their coding-tool consumption, model usage, rate limits, and spending without relying on a cloud account.
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 instructions/xiufengsun/tokentracker/agents-mdgit clone --depth 1 https://github.com/xiufengsun/TokenTrackerWrote 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/xiufengsun/tokentracker/agents-md)<a href="https://agentmods.dev/instructions/xiufengsun/tokentracker/agents-md"><img src="https://agentmods.dev/badge/instructions/xiufengsun/tokentracker/agents-md.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 | $0.00450 | $0.00450 |
| Opus 5 | $0.00225 | $0.00225 |
| Sonnet 5 | $0.00090 | $0.00090 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
TokenTracker 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 6d 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.
What it actually says
Agent Instructions
Use CLAUDE.md as the single source of truth for this repository's project guidance, architecture notes, release workflow, and conventions.
If any project-specific instructions appear to conflict across files, follow CLAUDE.md and update this file only to keep that pointer intact.
InsForge backend
This project uses InsForge: an all-in-one, open-source Postgres-based backend (BaaS) that gives this app a database, authentication, file storage, edge functions, realtime, an AI model gateway, and payments through one platform.
- Project: tokentracker (API base
https://srctyff5.us-east.insforge.app) - Skills: these InsForge skills are installed for supported coding agents. Reach for them before implementing any InsForge feature instead of guessing the API:
insforge: app code with the@insforge/sdkclient (database CRUD, auth, storage, edge functions, realtime, AI, email, and Stripe payments).insforge-cli: backend and infrastructure via theinsforgeCLI (projects, SQL, migrations, RLS policies, storage buckets, functions, secrets, payment setup, schedules, deploys).insforge-debug: diagnosing failures (SDK/HTTP errors, RLS denials, auth and OAuth issues) and running security or performance audits.insforge-integrations: wiring external auth providers (Clerk, Auth0, WorkOS, Better Auth, etc.) for JWT-based RLS, or the OKX x402 payment facilitator.find-skills: discovering additional skills on demand.
- Credentials: app code reads keys from
.env.local; the CLI reads.insforge/project.json. Never hardcode or commit keys.
Key patterns:
- Database inserts take an array:
insert([{ ... }]). - Reference users with
auth.users(id); useauth.uid()in RLS policies. - For storage uploads, persist both the returned
urlandkey.
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.
- 6d ago First seen · 27 lines · 450 tokens per session scan A 413ababe6318
TokenTracker AGENTS.md is an instructions file published in the GitHub repository xiufengsun/TokenTracker (1,523 stars, last pushed yesterday), licensed MIT. It adds 450 tokens to every session, about $0.0022 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 instructions, from other repositories
sync-agents-settings CLAUDE.md
Instructions for Leoyang183/sync-agents-settings, covering claude.md, commands, architecture, testing and publishing.
sync-agents-settings AGENTS.md
Instructions for Leoyang183/sync-agents-settings, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
IDE-Adapter CLAUDE.md
Instructions for godstale/IDE-Adapter, covering claude.md, commands, architecture, adding a new handler and protocol rules.
IDE-Adapter GEMINI.md
Instructions for godstale/IDE-Adapter, covering gemini.md, project overview, building and running and development conventions.
agent-recall CLAUDE.md
Claude Code instructions for d-wwei/agent-recall, covering agent recall: ai development instructions, architecture, privacy tags, build commands and configuration.
obsidian-mind CLAUDE.md
Claude Code instructions for breferrari/obsidian-mind, covering obsidian mind, skills & capabilities, custom slash commands, vault structure and obsidian cli.