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/janekbaraniewski/openusage/claude-mdgit clone --depth 1 https://github.com/janekbaraniewski/openusageWrote 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/janekbaraniewski/openusage/claude-md)<a href="https://agentmods.dev/instructions/janekbaraniewski/openusage/claude-md"><img src="https://agentmods.dev/badge/instructions/janekbaraniewski/openusage/claude-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 | $0.02303 | $0.02303 |
| Opus 5 | $0.01151 | $0.01151 |
| Sonnet 5 | $0.00461 | $0.00461 |
| Haiku 4.5 | $0.00230 | $0.00230 |
Grade A, and why
openusage CLAUDE.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 yesterday.
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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What is this project?
OpenUsage is a terminal dashboard (TUI) for monitoring AI coding tool usage and spend. It auto-detects AI tools and API keys on the workstation and displays live data using Bubble Tea. Written in Go, requires CGO enabled (for mattn/go-sqlite3 used by the Cursor provider).
Commands
make build # build binary to ./bin/openusage (includes version ldflags)
make test # run all tests with -race and coverage
make test-verbose # verbose test output
make lint # golangci-lint (skips gracefully if not installed)
make fmt # go fmt ./...
make vet # go vet ./...
make run # go run cmd/openusage/main.go
make demo # build and run demo with dummy data (for screenshots)
make sync-tools # regenerate all AI tool configs from canonical template
# Run a single test
go test ./internal/providers/openai/ -run TestFetch -v
# Run provider tests only
go test ./internal/providers/...
Code style
- Standard
gofmtwithgoimports. Tabs for indentation. - Import groups (separated by blank lines): stdlib, third-party, internal.
- Bubble Tea aliased as
tea. - Errors wrapped with provider prefix:
fmt.Errorf("openai: creating request: %w", err). - Pointer fields for optional numerics:
Limit *float64. - JSON tags use
snake_casewithomitemptyfor optional fields.
Architecture
Data flow
There are two runtime modes:
Direct mode (default):
main.go → config.Load() → runDashboard()
→ detect.AutoDetect() → registers providers from providers.AllProviders()
→ polls providers concurrently on a ticker
→ snapshots sent to TUI via tea.Program.Send(SnapshotsMsg)
Daemon mode (openusage telemetry):
daemon.Server polls providers → ingests into SQLite (telemetry.Store)
→ TUI connects via daemon.ViewRuntime over unix socket
→ daemon.ReadModel hydrates snapshots from stored events
→ telemetry events deduplicated, mapped to providers via ProviderLinks
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.
- yesterday Changed · +5 lines · +120 tokens per session ee20f27e70b1
- 5d ago First seen · 188 lines · 2,183 tokens per session scan A f935166e9f34
openusage CLAUDE.md is an instructions file published in the GitHub repository janekbaraniewski/openusage (185 stars, last pushed yesterday), licensed MIT. It adds 2,303 tokens to every session, about $0.0115 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
toktrack AGENTS.md
AGENTS.md instructions for mag123c/toktrack, covering agents.md, non-obvious rules, before you finish and commits.
toktrack CLAUDE.md
Claude Code instructions for mag123c/toktrack, covering toktrack, quick start, context, workflow and 코드 구현 작업.
TokenBar AGENTS.md
AGENTS.md instructions for Nanako0129/TokenBar, covering tokenbar agent routing, read order, invariants, authorization boundary and handoff.
TokenBar CLAUDE.md
Claude Code instructions for Nanako0129/TokenBar: Read AGENTS.md first, then docs/knowledge/README.md and the task-specific canonical document it routes to. If .agent-local/CLAUDE.md exists, read it after the canonical documents as additive machine-local guidance only; it must not override the canonical architecture…
ai-usage-widget AGENTS.md
Instructions for odrasile/ai-usage-widget, covering agents.md, goal, working principles, workflow and technical constraints.
UsageAtlas AGENTS.md
Instructions for SRX9/UsageAtlas, covering repository guidelines and coding approach.