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/yuriipalam/codex-status-bar/agents-mdgit clone --depth 1 https://github.com/yuriipalam/codex-status-barWrote 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/yuriipalam/codex-status-bar/agents-md)<a href="https://agentmods.dev/instructions/yuriipalam/codex-status-bar/agents-md"><img src="https://agentmods.dev/badge/instructions/yuriipalam/codex-status-bar/agents-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 5.1 | $0.00862 | $0.00862 |
| Opus 5 | $0.00431 | $0.00431 |
| Sonnet 5 | $0.00172 | $0.00172 |
| Haiku 4.5 | $0.00086 | $0.00086 |
Grade A, and why
codex-status-bar 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 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Instructions
Read README.md before making changes. Follow the product behavior, privacy boundaries, build commands, distribution notes, and local-state assumptions documented there.
Engineering Expectations
- Prefer the existing SwiftPM layout: keep platform-independent parsing, state, formatting, and presentation logic in
Sources/CodexBarCore, and keep AppKit/menu-bar wiring inSources/CodexBar. - Use Swift and macOS best practices for a small native menu-bar app: value types for pure model/presentation state, dependency injection for filesystem/environment readers, main-thread AppKit updates, and no unnecessary global state.
- Keep Codex Status Bar local-first and read-only for Codex activity data. Do not add network calls, telemetry, hooks, or writes to session JSONL/global state.
- Treat Codex local files as implementation details, not a stable public API. Add or update focused tests when parsing new JSONL events, state files, metadata fields, or status labels.
- Use
originatoronly for visibleAPP/CLI/IDEclient badges. Do not fall back to noisysourcemetadata for badge display. - For shell scripts, fail fast on errors, quote paths, avoid destructive commands, and keep release packaging reproducible from
./build.sh --dmg. - For release packaging, assemble, sign, and verify the app in a clean staging directory, then publish final artifacts into
build/. In-place local app copies are fine for development, but the DMG should come from the verified staged app.
Verification
Run the narrowest relevant checks for the change:
swift test
./build.sh --release
For packaging changes, also run:
./build.sh --dmg
hdiutil verify build/CodexStatusBar.dmg
For launch or AppKit behavior changes, run:
./script/build_and_run.sh --verify
Generated build artifacts under .build/, build/, dist/, .swiftpm/, and DerivedData/ should stay untracked.
Release Procedure
Only the maintainer publishes releases. App bundle versions are controlled by VERSION and BUILD_NUMBER:
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 · 91 lines · 862 tokens per session scan A 32139747ee0f
codex-status-bar AGENTS.md is an instructions file published in the GitHub repository yuriipalam/codex-status-bar (8 stars, last pushed 1mo ago), licensed MIT. It adds 862 tokens to every session, about $0.0043 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
codex-usage-sidebar AGENTS.md
AGENTS.md instructions for JaceHwang/codex-usage-sidebar, a project described as: Live Codex quota, reset time, Credits, and Bank details in the macOS desktop UI.
codex-status-menubar AGENTS.md
AGENTS.md instructions for Gatsby007max/codex-status-menubar, covering codex status menubar agent guide, project overview, repository layout, development rules and verification.
codex-mission-control AGENTS.md
Instructions for dicnunz/codex-mission-control: Keep this repo small, local-first, and dependency-light.
CodexAgentMonitor AGENTS.md
AGENTS.md instructions for Saba-Burduli/CodexAgentMonitor, covering repository guidelines, context rules, semantic repo map workflow, project shape and commands.
codex-provider-sync AGENTS.md
AGENTS.md instructions for Dailin521/codex-provider-sync, covering ai / agent operator guide, vnext architecture baseline, goal, choose the interface and safe operating flow.
codexia AGENTS.md
AGENTS.md instructions for milisp/codexia, covering agents.md, project info, project tech, common commands and project structure.