agents-skeleton AGENTS.md

An `AGENTS.md` project guide that serves as a starting map for coding agents. It points to architecture, design, frontend, planning, product, quality, and reliability documentation.

In plain words
What is it for?
Use it to orient agents in the repository and document build, test, lint, and formatting commands as those details become available.
Why use it?
It gives an agent a quick overview and clear places to look for deeper project rules instead of putting all instructions in one file.

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/mcqua007/agents-skeleton/agents-md
Clone the repo
git clone --depth 1 https://github.com/mcqua007/agents-skeleton

Made for: Codex, OpenCode.

Per session 812 This file is loaded in full into every session.
When invoked 812 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 $0.00812 $0.00812
Opus 5 $0.00406 $0.00406
Sonnet 5 $0.00162 $0.00162
Haiku 4.5 $0.00081 $0.00081

Measured 2d ago against content hash c945b9af8d33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agents-skeleton 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 · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file is the universal entry point for all AI coding agents. It serves as a table of contents — not an encyclopedia. Keep it under ~100 lines. Point to deeper docs for detail.

Project Overview

This repository uses an agent-first development workflow. All coding agents should treat this file as their starting map and navigate to specific docs as needed for deeper context.

Quick Reference

# Build
# TODO: Add build command

# Test
# TODO: Add test command

# Lint
# TODO: Add lint command

# Format
# TODO: Add format command

Architecture

See ARCHITECTURE.md for the full codemap, module layout, dependency directions, and architectural invariants.

Documentation Map

All deep knowledge lives in docs/. Navigate by topic:

Document Purpose
docs/DESIGN.md UI/UX design conventions and patterns
docs/FRONTEND.md Frontend-specific guidance and component patterns
docs/PLANS.md Current priorities and high-level roadmap
docs/PRODUCT_SENSE.md Product principles, user empathy, domain context
docs/QUALITY_SCORE.md Quality grades by domain and architectural layer
docs/RELIABILITY.md Reliability requirements, SLOs, error handling
docs/SECURITY.md Security guidelines, auth patterns, threat model

Deeper Resources

Directory Purpose
docs/design-docs/ Design documents with verification status
docs/exec-plans/ Execution plans (active, completed, tech debt)
docs/product-specs/ Product specifications and requirements
docs/references/ External reference docs, llms.txt files
docs/generated/ Auto-generated documentation (schemas, etc.)

Read the full file on GitHub · 88 lines

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 · 88 lines · 812 tokens per session scan A c945b9af8d33

Subscribe to this mod's changes

agents-skeleton AGENTS.md is an instructions file published in the GitHub repository mcqua007/agents-skeleton (2 stars, last pushed 6mo ago), licensed MIT. It adds 812 tokens to every session, about $0.0041 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.