Borrowing it
Nothing to install: this file belongs to JaceHwang/codex-usage-sidebar. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/JaceHwang/codex-usage-sidebar/main/AGENTS.mdgit clone --depth 1 https://github.com/JaceHwang/codex-usage-sidebarWrote 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/jacehwang/codex-usage-sidebar/agents-md)<a href="https://agentmods.dev/instructions/jacehwang/codex-usage-sidebar/agents-md"><img src="https://agentmods.dev/badge/instructions/jacehwang/codex-usage-sidebar/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/jacehwang/codex-usage-sidebar/agents-md"><img src="https://agentmods.dev/badge/instructions/jacehwang/codex-usage-sidebar/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00401 | $0.00401 |
| Opus 5.5 | $0.00160 | $0.00160 |
| Sonnet 5.5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
codex-usage-sidebar 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 24d 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 — 20 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository governance
- Run
./governance doctorbefore the first code-changing action in a task. If hooks are inactive, run./governance bootstrapand repeat doctor. - Never develop or commit directly on
main; usecodex/<type>/<kebab-case>. - Use English Conventional Commit headers and Conventional Commit PR titles. PR background and verification may be written in Chinese.
- Never use
--no-verify, weaken checks, overwrite a published release asset, or edit product versions in ordinary commits. - Run
./governance check allbefore pushing. Release product versions only through the generated Release Please PR.
Development progress
- Before every development, continuation, fix, validation or release task, read
docs/PROJECT_PROGRESS-standalone-app.mdand resume.project-board/using the installed tracking-project-progress skill utility when available. If it is unavailable, read.project-board/board.mddirectly and report the limitation; never hand-edit its generated files. - Reconcile the progress with live code, Git status and verification evidence before selecting work. The standalone-app document is the detailed roadmap; the board is the current recovery snapshot. Historical tasks on the board do not certify standalone-app completion.
- Update the roadmap task status, evidence, decisions, blockers and next action after each meaningful milestone, before interruption/handoff and before ending a development session. Update the board through its utility and validate it when available.
- Distinguish planned, implemented, tested on CI, tested on a device and released states. Record tests that were not run and do not mark a platform complete based on another platform's result.
- Follow the user's latest authorization for implementation, installation and release. The current objective authorizes Windows standalone implementation, macOS feature parity and candidate packaging/installation testing. Public release requires explicit release authorization; record current platform scope in the standalone roadmap.
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.
- 24d ago Changed · +9 tokens per session 5a6c81c02c5c
- 25d ago Changed · +8 lines · +244 tokens per session 49207db65774
- 2mo ago First seen · 12 lines · 148 tokens per session scan A 57d9c8d3d69e
codex-usage-sidebar AGENTS.md is an instructions file published in the GitHub repository JaceHwang/codex-usage-sidebar (4 stars, last pushed 23d ago), licensed MIT. It adds 401 tokens to every session, about $0.0016 per session on Opus 5.5. 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.
codex-usage-sidebar AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| codex-usage-sidebar AGENTS.mdJaceHwang/codex-usage-sidebar | Instructions file | 4 | 23d ago | MIT | A | 401 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |