Borrowing it
Nothing to install: this file belongs to yueyifei0716/codex-async-wait-rules. 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/yueyifei0716/codex-async-wait-rules/main/AGENTS.mdgit clone --depth 1 https://github.com/yueyifei0716/codex-async-wait-rulesWrote 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/yueyifei0716/codex-async-wait-rules/agents-md)<a href="https://agentmods.dev/instructions/yueyifei0716/codex-async-wait-rules/agents-md"><img src="https://agentmods.dev/badge/instructions/yueyifei0716/codex-async-wait-rules/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/yueyifei0716/codex-async-wait-rules/agents-md"><img src="https://agentmods.dev/badge/instructions/yueyifei0716/codex-async-wait-rules/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 | $0.00322 | $0.00322 |
| Opus 5.5 | $0.00129 | $0.00129 |
| Sonnet 5.5 | $0.00064 | $0.00064 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
codex-async-wait-rules 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 2mo 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.
What it actually says
Async waits (long-running work)
Scope note: this section overrides the general preference for short waits. It applies only to tools that (a) return as soon as the underlying work finishes and (b) can be cut short by user input. Under those two conditions a long yield has no downside — finishing early is the normal case, not the exception.
-
Status-check
write_stdincalls (empty payload) Floor: 180000 ms. Use 300000 ms unless you specifically need to read partial output as it streams. -
functions.waitFloor: 180000 ms. Same reasoning as above. -
functions.execwrapping any of the above The outer cell's yield must exceed the largest inner wait by 30000 ms or more. Getting this wrong makes the inner floors pointless — the wrapper times out first and the whole nesting yields early anyway. -
Backing off Two polls in a row with nothing new means the task is slow, not stuck. Move to 300000 ms and stay there until output actually appears.
-
After an early return An early return is not a cue to poll again. Re-enter the wait only if what came back demands a decision. "Still working" is not a reason to surface anything to the model.
-
Out of scope Interactive
write_stdincalls — anything carrying real input — keep their normal short timeouts. Latency matters there.
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.
- 2mo ago First seen · 35 lines · 322 tokens per session scan A ff1db3458611
codex-async-wait-rules AGENTS.md is an instructions file published in the GitHub repository yueyifei0716/codex-async-wait-rules (5 stars, last pushed 2mo ago), licensed MIT. It adds 322 tokens to every session, about $0.0013 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-async-wait-rules AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| codex-async-wait-rules AGENTS.mdyueyifei0716/codex-async-wait-rules | Instructions file | 5 | 2mo ago | MIT | A | 322 | 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 |