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/ognjeeen/codex-usage-widget/agents-mdgit clone --depth 1 https://github.com/ognjeeen/codex-usage-widgetWhat 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 | $0.01218 | $0.01218 |
| Opus 5 | $0.00609 | $0.00609 |
| Sonnet 5 | $0.00244 | $0.00244 |
| Haiku 4.5 | $0.00122 | $0.00122 |
Grade A, and why
codex-usage-widget 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
Project
Codex Usage Widget is a local-only Windows desktop utility that displays Codex usage in a movable WPF widget and beside the Windows notification area. It targets .NET 10 and obtains rate-limit data through the locally installed Codex CLI and its official app-server protocol.
Before changing code, read README.md, docs/ARCHITECTURE.md, and the files directly involved in the requested behavior. For release work, also read docs/RELEASING.md.
Scope and decision discipline
- Implement the smallest complete change that satisfies the explicit request.
- Preserve behavior outside the requested scope.
- Do not add speculative features, configuration, compatibility layers, dependencies, or refactors for possible future needs.
- Prefer a direct implementation over a generalized system. Introduce an abstraction only when it solves a concrete current problem, protects an existing architectural boundary, or creates a necessary test seam.
- Do not turn an isolated change into a repository-wide cleanup. Mention worthwhile out-of-scope improvements separately instead of implementing them.
- Refactor only when the existing structure directly prevents a safe change. Keep the refactor proportional to the request.
- Keep one cohesive responsibility per type and file, but do not split trivial logic into extra files merely to reduce file size.
- Follow established project patterns unless the task explicitly requires changing them.
- Resolve discoverable, reversible, in-scope implementation details by inspecting the repository and following its existing patterns. Do not stop for minor choices that do not materially affect the result.
- Ask before making a choice that materially changes UX, architecture, public behavior, data handling, packaging, supported platforms, or dependencies.
Authorization and repository safety
- Treat existing uncommitted changes as user-owned. Do not overwrite, revert, reformat, stage, or include them unless they are explicitly part of the task.
- Do not commit, push, create or update a pull request, tag, publish a release, rewrite history, or otherwise change remote state unless the user explicitly requests that action.
- When the user asks for a local implementation or preview, stop after local validation and wait for approval before any Git or GitHub publishing action.
- Never use destructive Git or filesystem commands to resolve an unrelated workspace problem.
- Keep personal machine paths, usernames, credentials, tokens, and environment-specific values out of tracked files. Use repository-relative paths in documentation and configuration.
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 · 1,218 tokens per session scan A ce31d5dc22d8
codex-usage-widget AGENTS.md is an instructions file published in the GitHub repository ognjeeen/codex-usage-widget (9 stars, last pushed 4d ago), licensed MIT. It adds 1,218 tokens to every session, about $0.0061 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
CodexCliPlus AGENTS.md
Instructions for C4AL/CodexCliPlus, covering agents.md and repository rules.
ai-code-interface.el AGENTS.md
Instructions for tninja/ai-code-interface.el, covering agents.md, common development commands, byte compilation, running tests and run a specific test file.
ai-code-interface.el copilot-instructions.md
Instructions for tninja/ai-code-interface.el, covering github copilot instructions for ai-code-interface.el, project overview, language and technology, code style and conventions and file naming.
codexU AGENTS.md
Instructions for shanggqm/codexU, covering agents.md, 项目边界, 关键文档, 代码结构 and 项目级 skills.
codex-usage-desktop AGENTS.md
Instructions for itvincent-git/codex-usage-desktop, covering agents.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.
codex-multi-profile AGENTS.md
Instructions for Hung2124/codex-multi-profile: This repository is a Windows-only Codex Desktop multi-account helper.