LazyCodex is an agent harness for working on complex codebases, combining project memory, planning, execution, and completion checks inside Codex. It is for developers who want structured, repeatable assistance when handling substantial software projects. The catalogue contains the skills, hook, and MCP integration that provide its workflow inside Codex.
Borrowing it
Nothing to install: this file belongs to code-yeongyu/lazycodex. 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/code-yeongyu/lazycodex/main/AGENTS.mdgit clone --depth 1 https://github.com/code-yeongyu/lazycodexWrote 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/code-yeongyu/lazycodex/agents-md)<a href="https://agentmods.dev/instructions/code-yeongyu/lazycodex/agents-md"><img src="https://agentmods.dev/badge/instructions/code-yeongyu/lazycodex/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/code-yeongyu/lazycodex/agents-md"><img src="https://agentmods.dev/badge/instructions/code-yeongyu/lazycodex/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 | $0.00622 | $0.00622 |
| Opus 5.5 | $0.00249 | $0.00249 |
| Sonnet 5.5 | $0.00124 | $0.00124 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
lazycodex 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 15d 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 — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent notes: lazycodex
What you may edit
plugins/omo/**,.agents/plugins/marketplace.json,marketplace.jsonand.github/workflows/pr-source-guidance.ymlare synced from the oh-my-openagent repository and are rewritten on every sync. Never hand-edit them: change their source in oh-my-openagent (the plugin's test rules live inpackages/omo-codex/plugin/test/AGENTS.mdthere).src/is a git submodule of oh-my-openagent.- The hand-owned parts are the root
test/,bin/andpackages/web/.
Tests
- Root:
npm test, which runsnode --test test/*.test.mjs. - Plugin:
npm testfrom the plugin directory (the suite is owned upstream, see above). - Web:
pnpm run lint,pnpm run type-checkand the Playwright suite (seepackages/web/AGENTS.md).
Test authoring gate
Before adding or changing a test, answer all four; a missing answer means do not add it yet:
- What observable behavior, invariant, or independent contract does it protect?
- What credible regression makes it fail?
- Why does existing coverage not already catch that failure? Each contract has one primary test owner at the strongest boundary; extend a table case or shared fixture instead of adding a near-duplicate.
- Does it need a production seam (export, flag, wrapper, injection hook) no production caller needs? If yes, test at the real boundary instead. Junk patterns (reject unless the retention bar below applies): assertion-free probes; self-comparisons and identity copiers; copied fixtures, inventories, manifests or export lists; exact source, import or string greps; private call-shape tests duplicated at a real boundary; duplicate invocations of one contract; replays of a shared helper through a wrapper; tests that exist to keep a test-only export or wrapper alive; production code whose only callers are tests; expected values produced by the code under test; mocks that implement the asserted behavior; fixture-supplied receipts or postconditions the code under test should produce; assertions against a store nothing writes; capability or flag restatements without a delivery proof; negative controls that pass for an unrelated reason; names that promise more than the input exercises. Retention bar: keep a pattern match only when it independently guards a public API, protocol, config, migration, storage, security, platform, default, prompt-byte, generated or cross-language, package, release, or architecture contract, and say which one in the test. Static or slow is never a deletion reason. A retained test that fails on the base is a product bug to fix at its owner, never a test to delete. A bug regression test must fail on the pre-fix code for the intended reason; an existing owner test that already fails may serve as that proof. Method source: openclaw test-audit skill.
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.
- 15d ago First seen · 23 lines · 622 tokens per session scan A 0c1dabff4386
lazycodex AGENTS.md is an instructions file published in the GitHub repository code-yeongyu/lazycodex (3,782 stars, last pushed 2d ago), licensed MIT. It adds 622 tokens to every session, about $0.0025 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 2026-10-01.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).