AgentLoop AGENTS.md

Repository instructions for coding agents working on AgentLoop, a software project whose releases use a version file. They require updating that version before pushing changes.

In plain words
What is it for?
Use them when making changes, choosing a semantic-version bump, checking the release checklist, and preparing a push to GitHub.
Why use it?
They prevent changes from being pushed without a matching release version, which would break the project's update checks.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/ciroaurelio22/agentloop/agents-md
Clone the repo
git clone --depth 1 https://github.com/ciroaurelio22/AgentLoop

Made for: Codex, OpenCode.

Per session 421 This file is loaded in full into every session.
When invoked 421 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00421 $0.00421
Opus 5 $0.00211 $0.00211
Sonnet 5 $0.00084 $0.00084
Haiku 4.5 $0.00042 $0.00042

Measured 2d ago against content hash 63fc8ebdd2be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AgentLoop 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 2d 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.

AGENTS.md · 35 lines

What it actually says

Agent Loop — instructions for coding agents

This file applies to any agent working in this repository (Cursor, Claude Code, Codex, etc.).

Before every push

You must bump the root VERSION file before pushing to GitHub.

The kit uses VERSION as the release identifier: installs copy it to .agent-loop/kit-version, and agent-update-check compares it with the remote file on GitHub.

How to bump

  1. Read the current value in VERSION (single line, semver, e.g. 0.1.0).
  2. Increment it before git push:
    • Patch (0.1.00.1.1): default for bug fixes, GUI tweaks, docs, and most kit changes.
    • Minor (0.1.00.2.0): new features or behavior changes that are backward compatible.
    • Major (0.1.01.0.0): breaking changes to install layout, CLI contract, or queue/task format.
  3. Write only the new version string in VERSION (no v prefix, no extra lines).
  4. Include VERSION in the same commit you push, or in a dedicated release commit immediately before push.

Do not push without a version bump

If the branch has user-facing or kit changes that will land on master, do not push until VERSION is updated. Skipping this breaks update notifications for downstream repos.

Quick checklist

  • Changes committed
  • VERSION incremented
  • git push (only when the user asked to push)
Changes

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.

  1. 2d ago First seen · 35 lines · 421 tokens per session scan A 63fc8ebdd2be

Subscribe to this mod's changes

AgentLoop AGENTS.md is an instructions file published in the GitHub repository ciroaurelio22/AgentLoop (10 stars, last pushed 2mo ago), licensed MIT. It adds 421 tokens to every session, about $0.0021 per session on Opus 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

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).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,040 tokens

langchain 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.

langchain-ai/langchain · 4,345 tokens