Borrowing it
Nothing to install: this file belongs to Ghqqqq/codex-overleaf-link. 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/Ghqqqq/codex-overleaf-link/main/AGENTS.mdgit clone --depth 1 https://github.com/Ghqqqq/codex-overleaf-linkWrote 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/ghqqqq/codex-overleaf-link/agents-md)<a href="https://agentmods.dev/instructions/ghqqqq/codex-overleaf-link/agents-md"><img src="https://agentmods.dev/badge/instructions/ghqqqq/codex-overleaf-link/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/ghqqqq/codex-overleaf-link/agents-md"><img src="https://agentmods.dev/badge/instructions/ghqqqq/codex-overleaf-link/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 | $0.01866 | $0.01866 |
| Opus 5.5 | $0.00746 | $0.00746 |
| Sonnet 5.5 | $0.00373 | $0.00373 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
codex-overleaf-link 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 7d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Overleaf Link Maintenance Entry Point
This repository provides local Codex conversations, project understanding, editing, and recovery for Overleaf. Start maintenance work by locating the feature's actual entry point, state owner, and protocols.
Keeping Code and the Guide in Sync
Defect fixes preserve the existing feature scope and primary interactions by default. Distinguish confirmed defects from capability limitations first; do not automatically turn a capability limitation into feature development, or substitute new buttons, manual workflows, or extra confirmation steps for a fix. New capabilities must fall within the task scope explicitly requested by the user. Necessary error messages must follow the existing presentation, language setting, and style. When withdrawing incidental feature additions, preserve the underlying protections and recovery compatibility for operations already performed.
All new features, behavior changes, debugging, refactoring, and configuration/tool changes follow the Feature Development and Bug-Fix SOP. At the start, use the guide to verify the actual entry points, owners, call chains, and validation methods. Before delivery, update the affected domain pages, feature index, and obsolete limitations to match the final code. Both the code and the necessary guide revisions are part of the task's completion criteria.
Every code task must assess its impact on the guide. If the existing description remains complete and accurate, the body may stay unchanged, but the final reply or existing PR/task description must name the sections checked and give specific reasons. Changes to actual behavior, navigation paths, or limitations require the corresponding revisions. Delivery notes include behavior changes, guide synchronization, validation actually performed, and remaining items. Review proceedings and separate issue records stay outside the guide.
Once a local fix involving runtime code passes the relevant automated checks, build, back up, and update the existing Managed installation directly by default; do not ask for installation permission again. After verifying the extension, Native, and build digests, ask the user to click Reload on the existing Chrome extension entry. After the user confirms the reload, refresh the project and continue CUA acceptance testing. Documentation-only changes do not trigger installation; publishing and writes to real projects still follow their respective authorization scopes. The SOP's local acceptance procedure specifies the delivery order.
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.
- 7d ago First seen · 70 lines · 1,866 tokens per session scan A ca67e284f408
codex-overleaf-link AGENTS.md is an instructions file published in the GitHub repository Ghqqqq/codex-overleaf-link (95 stars, last pushed yesterday), licensed MIT. It adds 1,866 tokens to every session, about $0.0075 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 2026-10-11.
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.
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).
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.