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/durandom/token-burn/agents-mdgit clone --depth 1 https://github.com/durandom/token-burnWhat 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 | $0.00550 | $0.00550 |
| Opus 5 | $0.00275 | $0.00275 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
token-burn 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 2d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - token-burn
Guidance for coding agents working in this repository.
Project Intent
Build a small, reliable daemon and CLI for monitoring live subscription quota usage for AI coding tools.
The primary use case is live quota visibility:
- percentage used
- reset time
- window duration
- plan/account metadata
- forecasted exhaustion time
- OpenTelemetry export
Do not infer subscription usage from local session files, transcripts, token logs, or pricing estimates unless explicitly requested later. This project is about provider live usage signals.
Language Direction
The implementation is Go.
Rationale:
- Simple daemon/CLI story.
- Strong OpenTelemetry support.
- Easy SQLite integration.
- A CGO-free binary is possible with
modernc.org/sqlite.
Layout
cmd/token-burn/ CLI entrypoint
internal/cli/ command wiring
internal/config/ XDG config load and defaults
internal/provider/ provider interface and shared models
internal/provider/codex/ live Codex usage client
internal/provider/claude/ live Claude usage client
internal/provider/copilot/ Copilot quota via the logged-in GitHub CLI
internal/provider/antigravity/ Antigravity quota via existing OAuth state
internal/store/ SQLite schema, migrations, queries
internal/forecast/ burn-rate and exhaustion forecast logic
internal/otel/ OTLP metric exporter
internal/daemon/ poll loop, backoff, graceful shutdown
internal/service/ macOS LaunchAgent and Linux systemd user unit
internal/tui/ read-only dashboard over SQLite
internal/upgrade/ self-upgrade from GitHub Releases
Code Style
- Keep the provider interface small and shaped around live usage windows.
- Prefer table-driven tests with the standard
testingpackage. - HTTP provider tests should use
httptest.NewServer. - SQLite tests should use
t.TempDir. - Never log raw access tokens, refresh tokens, cookies, or authorization headers.
- Store raw provider JSON only after redacting obvious token/cookie fields.
- Use UTC timestamps in storage; format in local time only in CLI/TUI output.
- Keep the TUI a read-only view over SQLite; it must not poll providers.
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.
- 2d ago First seen · 77 lines · 550 tokens per session scan A 6afbb6b01adb
token-burn AGENTS.md is an instructions file published in the GitHub repository durandom/token-burn (2 stars, last pushed 8d ago), licensed MIT. It adds 550 tokens to every session, about $0.0028 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 instructions, from other repositories
ai-viewer AGENTS.md
Instructions for netdata/ai-viewer, covering ai-viewer, goals, phase: development (active — started 2026-06-14), what's overridden during development and what stays in force during development.
tuitube AGENTS.md
Instructions for gitcoder89431/tuitube, covering agents.md, project intent, checklist for adding a new feature, key packages and logging.
ai-viewer CLAUDE.md
Instructions for netdata/ai-viewer, a project described as: Read-only real-time explorer for AI coding-agent session snapshots (ai-agent v2/v3, claude-code, codex, opencode). Workstation-only, single static binary.
ai-viewer GEMINI.md
Instructions for netdata/ai-viewer, a project described as: Read-only real-time explorer for AI coding-agent session snapshots (ai-agent v2/v3, claude-code, codex, opencode). Workstation-only, single static binary.
awesome-go AGENTS.md
AGENTS.md instructions for avelino/awesome-go, covering awesome-go · llm contribution guide, project snapshot, when modifying the awesome list, coding guidelines and testing & validation.
azure-sdk-for-go go-code.instructions.md
Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.