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/rygel/aiusagetracker/claude-mdgit clone --depth 1 https://github.com/rygel/AIUsageTrackerWrote 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/rygel/aiusagetracker/claude-md)<a href="https://agentmods.dev/instructions/rygel/aiusagetracker/claude-md"><img src="https://agentmods.dev/badge/instructions/rygel/aiusagetracker/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 | $0.05592 | $0.05592 |
| Opus 5 | $0.02796 | $0.02796 |
| Sonnet 5 | $0.01118 | $0.01118 |
| Haiku 4.5 | $0.00559 | $0.00559 |
Grade A, and why
AIUsageTracker 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 5d 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 — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Build & Test
Before building, kill any running app/monitor instances that lock DLLs:
pwsh -File scripts/kill-all.ps1
Run tests (capped at 4 cores per global CLAUDE.md):
dotnet test AIUsageTracker.Tests/AIUsageTracker.Tests.csproj -T 4
Analyzer Rules — Do Not Weaken
The following .editorconfig rules are enforced at error severity with zero violations.
Never lower their severity, add suppressions, or work around them.
Fix the underlying code instead.
| Rule | Severity | What it enforces |
|---|---|---|
| CA1031 | warning | No catching general Exception — use specific types |
| CA1062 | error | Validate public method parameters for null |
| CA1307 | error | Explicit StringComparison on all string operations |
| CA2016 | error | Forward CancellationToken to async methods |
| CA2254 | error | Use structured logging templates, not interpolation |
If a new violation appears, fix it before pushing. Do not:
- Change severity to
suggestionornone - Add
#pragma warning disable - Add
[SuppressMessage]attributes - Raise analyzer thresholds to make CI pass
Architecture
- AIUsageTracker.UI.Slim — WPF main window + settings dialog (net10.0-windows)
- AIUsageTracker.Monitor — Background agent that polls providers and serves usage data over HTTP
- AIUsageTracker.Core — Shared models, interfaces, monitor client
- AIUsageTracker.Infrastructure — Provider implementations (Synthetic, Codex, OpenAI, etc.)
Data flow: Monitor → Main Window
- Monitor polls each configured provider via
IProvider.GetUsageAsync(config) - Results are grouped into
AgentGroupedUsageSnapshotand served via HTTP with ETag caching - Main window polls
MonitorService.GetGroupedUsageAsync()every 2-60 seconds GroupedUsageDisplayAdapter.Expand()flattens the snapshot intoList<ProviderUsage>MainWindowRuntimeLogic.PrepareForMainWindow()filters by visibility and stateRenderProviders()builds the card UI
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.
- 5d ago First seen · 421 lines · 5,592 tokens per session scan A 26bef0549ec6
AIUsageTracker CLAUDE.md is an instructions file published in the GitHub repository rygel/AIUsageTracker (44 stars, last pushed 2d ago), licensed MIT. It adds 5,592 tokens to every session, about $0.0280 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
oh-my-opencode-slim AGENTS.md
AGENTS.md instructions for alvinunreal/oh-my-opencode-slim, covering agent coding guidelines, project overview, commands, code style and general rules.
copilot-api AGENTS.md
AGENTS.md instructions for caozhiyuan/copilot-api, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
opencode-bar AGENTS.md
Instructions for opgginc/opencode-bar, covering important restriction, coding rules, branding guides, ui styling rules and explicit 'used' or 'left'.
gmail-mcp AGENTS.md
AGENTS.md instructions for Evyatar108/gmail-mcp, covering gmail mcp agent guidance, repository purpose, non-negotiable invariants, live-account policy and code map.
copilot-api CLAUDE.md
Claude Code instructions for caozhiyuan/copilot-api, a project described as: GitHub Copilot, OpenAI Codex, OpenCode Go, and third-party AI provider gateway with OpenAI and Anthropic API compatibility.
gmail-mcp copilot-instructions.md
Copilot instructions for Evyatar108/gmail-mcp: Follow AGENTS.md and preserve every security invariant documented there.