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/agents-mdgit clone --depth 1 https://github.com/janekbaraniewski/openusageWhat 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 | $0.01484 | $0.01484 |
| Opus 5 | $0.00742 | $0.00742 |
| Sonnet 5 | $0.00297 | $0.00297 |
| Haiku 4.5 | $0.00148 | $0.00148 |
Grade A, and why
openusage 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 3d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — OpenUsage
Guidelines for coding agents working in this repository.
Project Overview
OpenUsage is a Go terminal dashboard (Bubble Tea) for monitoring AI coding tool usage and spend. It supports two runtime paths:
- Dashboard mode (
openusage) reads usage snapshots through the local telemetry daemon runtime. - Daemon mode (
openusage telemetry ...) collects provider data + hook events into SQLite.
CGO is required (CGO_ENABLED=1) due to mattn/go-sqlite3 usage (Cursor + telemetry store).
Build, Run, Test, Lint
# Build
make build # binary -> ./bin/openusage (with version ldflags)
go build ./cmd/openusage # quick build without ldflags
# Run
make run # go run cmd/openusage/main.go
OPENUSAGE_DEBUG=1 make run # enable debug logging to stderr
make demo # run demo binary with simulated data
# Telemetry daemon
go run ./cmd/openusage telemetry daemon
go run ./cmd/openusage telemetry daemon status
go run ./cmd/openusage telemetry hook codex < /tmp/codex-hook.json
# Test
make test # go test -race -coverprofile=coverage.out -covermode=atomic ./...
make test-verbose # go test -v -race ./...
go test ./internal/providers/... -v
go test ./internal/telemetry/... -v
go test ./internal/tui/... -v
# Lint/format
make lint # golangci-lint run ./... (skips if binary missing)
make vet # go vet ./...
make fmt # go fmt ./...
# Dependencies
make deps # go mod download && go mod verify
make tidy # go mod tidy
Current Structure
cmd/openusage/ cobra CLI entrypoint
main.go root command
dashboard.go Bubble Tea runtime wiring
telemetry.go telemetry daemon / hook subcommands
cmd/demo/ demo dashboard runner with synthetic snapshots
internal/
config/ settings + credentials JSON persistence
core/ shared types (UsageSnapshot, Metric, ProviderSpec, widgets, time windows)
daemon/ daemon server/client, socket runtime, service install/status
detect/ local tool + env key auto-detection
integrations/ Codex/OpenCode/Claude hook/plugin install + version checks
parsers/ shared HTTP header parsing helpers
providers/ provider implementations + registry (16 providers)
telemetry/ SQLite store, ingest pipeline, dedup, read model
tui/ Bubble Tea views/components/settings UX
version/ build metadata injected by ldflags
plugins/ integration install scripts/templates
configs/ example settings
docs/skills/ feature and provider implementation workflows
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.
- 3d ago First seen · 161 lines · 1,484 tokens per session scan A 70173e09e3c1
openusage AGENTS.md is an instructions file published in the GitHub repository janekbaraniewski/openusage (180 stars, last pushed 9d ago), licensed MIT. It adds 1,484 tokens to every session, about $0.0074 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
Instructions for mag123c/toktrack, covering agents.md, non-obvious rules, before you finish and commits.
toktrack CLAUDE.md
Instructions for mag123c/toktrack, covering toktrack, quick start, context, workflow and 코드 구현 작업.
TokenBar AGENTS.md
Instructions for Nanako0129/TokenBar, covering tokenbar agent routing, read order, invariants, authorization boundary and handoff.
TokenBar CLAUDE.md
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.