Borrowing it
Nothing to install: this file belongs to alieismy/codex-three-layer-delivery. 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/alieismy/codex-three-layer-delivery/main/AGENTS.mdgit clone --depth 1 https://github.com/alieismy/codex-three-layer-deliveryWrote 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/alieismy/codex-three-layer-delivery/agents-md)<a href="https://agentmods.dev/instructions/alieismy/codex-three-layer-delivery/agents-md"><img src="https://agentmods.dev/badge/instructions/alieismy/codex-three-layer-delivery/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/alieismy/codex-three-layer-delivery/agents-md"><img src="https://agentmods.dev/badge/instructions/alieismy/codex-three-layer-delivery/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 | $0.01538 | $0.01538 |
| Opus 5.5 | $0.00615 | $0.00615 |
| Sonnet 5.5 | $0.00308 | $0.00308 |
| Haiku 4.5 | $0.00154 | $0.00154 |
Grade A, and why
codex-three-layer-delivery 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 27d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Repository Maintainer Instructions
Purpose and Authority
This file governs maintenance of the codex-three-layer-delivery source repository itself. It is not a distributable project template and must not become a current-task status record.
README.mdis the authority for repository purpose, the three-layer model, supported adapters, and published layout.- The English root is the canonical baseline.
zh-CN/is a translation pack; Claude and Cursor files are platform adapters that preserve documented platform differences. codex/global/AGENTS.md.templateandrules/project/AGENTS.md.templateare distributable templates. Do not make this maintainer file a byte-for-byte copy of either template.- Detailed RD methods belong in the owning
skills/rd-*/SKILL.md; this file keeps only repository-wide maintenance controls and pointers.
Before Editing
- Inspect the user request, effective instructions, target file, authoritative English source, maintained mirrors, nearby references, and relevant validator entry points before changing content.
- Reuse previously inspected stable project context only when its authoritative source, revision, and applicability remain known. Use applicable low-cost change detectors such as branch and HEAD, worktree status, changed paths, and relevant source revisions to scope refreshes.
- Re-read affected or decision-critical sources after revision changes, external edits, new evidence, context compaction, task redirection, or conflicting observations. Do not rescan the entire repository by default, and do not claim prior context remains current without checking applicable change detectors.
- For complex or high-impact maintenance, briefly identify the reused baseline and newly refreshed dynamic evidence at the first meaningful checkpoint when that improves reviewability; do not impose a fixed context-accounting format on simple tasks.
- Treat versions, installed tools, external releases, generated configuration, runtime state, and test results as dynamic evidence. Recheck them when they affect a conclusion; keep version snapshots in
docs/compatibility.md, not in this file. - This root
AGENTS.mdis the sole repository-maintainer authority. Files underrules/,codex/,zh-CN/,cursor/, andclaude/are distributable templates or adapters, not maintainer guidance. Keep instruction sources under non-discoverable.templatefilenames and Skills only in the sharedskills/andzh-CN/skills/source trees. If an editor surfaces distributable sources as effective instructions, treat that as an unresolved adapter-isolation conflict: do not assume this root file overrides a more specific instruction, and record reproduced platform behavior indocs/compatibility.mdrather than turning a single observation into a repository-wide runtime claim.
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.
- 27d ago Changed · +57 tokens per session e3b68b505a08
- 1mo ago Changed · +2 lines · +53 tokens per session 07bbf6809c35
- 1mo ago Changed · +2 lines · +67 tokens per session e61111e9b7c3
- 1mo ago Changed · +9 lines · +196 tokens per session 681d9cbce152
- 2mo ago Changed · +7 lines · +192 tokens per session 0a9f495f1b24
- 2mo ago First seen · 56 lines · 973 tokens per session scan A 699de5f3c45f
codex-three-layer-delivery AGENTS.md is an instructions file published in the GitHub repository alieismy/codex-three-layer-delivery (12 stars, last pushed 27d ago), licensed MIT. It adds 1,538 tokens to every session, about $0.0062 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-three-layer-delivery AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| codex-three-layer-delivery AGENTS.mdalieismy/codex-three-layer-delivery | Instructions file | 12 | 27d ago | MIT | A | 1,538 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 1,907 | GitHub Copilot |