agentmods.dev

expert-ai-developer-skills: Instructions file for Codex

AGENTS.md

expert-ai-developer-skills AGENTS.md is an instructions file for Codex, OpenCode from jggomez/expert-ai-developer-skills. It costs 6,560 tokens per session, scanned A, original, Apache-2.0.

Repository rules for AI coding agents, including planning before code changes, defined coordinator roles, and test-driven development. Test-driven development means writing or updating tests as part of the process of changing code.

In plain words
What is it for?
Use them to guide agent work from planning through implementation and testing, including keeping PLAN.md current and following the repository's workflow.
Why use it?
They set required steps and boundaries so agents do not make unplanned changes or lose track of the system's state.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions .claude-plugin; mentions subagents; mentions Claude Code.

This is jggomez/expert-ai-developer-skills's own configuration. It tells Codex and OpenCode how to work on expert-ai-developer-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything expert-ai-developer-skills configures →

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

not rated 30repo today A scan 6,560 tokens original Apache-2.0
View source ↗ jggomez/expert-ai-developer-skills
Reuse

Borrowing it

Nothing to install: this file belongs to jggomez/expert-ai-developer-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jggomez/expert-ai-developer-skills/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/jggomez/expert-ai-developer-skills

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for expert-ai-developer-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jggomez/expert-ai-developer-skills/agents-md/github.svg)](https://agentmods.dev/instructions/jggomez/expert-ai-developer-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jggomez/expert-ai-developer-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/jggomez/expert-ai-developer-skills/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.

agentmods 80×15 button for expert-ai-developer-skills AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jggomez/expert-ai-developer-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/jggomez/expert-ai-developer-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,560 This file is loaded in full into every session.
When invoked 6,560 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.06560 $0.06560
Opus 5.5 $0.02624 $0.02624
Sonnet 5.5 $0.01312 $0.01312
Haiku 4.5 $0.00656 $0.00656

Measured yesterday against content hash 3768321fba9d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

expert-ai-developer-skills AGENTS.md scanned grade A with 1 finding 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 yesterday.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

...require("child_process").execSync("find plugins -name \"*.json\"").toString().trim().split("\n")
AGENTS.md · 288 lines

How it starts

The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Universal AI Coding Agent Constitution & Instructions

Target Audience: All AI Coding Agents operating within this repository, including Google Antigravity, Anthropic Claude Code, Cursor, Codex, Gemini CLI, and related autonomous coding engines.

Authority: This document serves as the supreme operational constitution and governance framework. All agents must comply with the rules, boundaries, and lifecycles defined herein without exception.

1. Inviolable Core Principles

1.1. Plan-First Mandatory Gate

  • No Unplanned Code Changes: Before any application code modification, refactoring, or implementation begins, an up-to-date PLAN.md file MUST be authored or updated and committed/saved to disk in the repository root.
  • Granular Task Breakdown: The plan must detail exact tracks, phases, actionable verification criteria, and affected components.
  • Lifecycle Synchronization: As milestones progress, agents must keep PLAN.md strictly synchronized with the true system state.

1.2. Orchestrator Role Boundary

  • Technical Director & Coordinator: Orchestrator agents (e.g., senior-dev-orchestrator, flutter-feature-orchestrator) are coordinators and systems directors.
  • Strict Non-Execution Constraint: Orchestrators are STRICTLY PROHIBITED from directly editing application code, libraries, or tests (src/, lib/, tests/, etc.).
  • Tool Permissions: File editing and writing tools (write_to_file, replace_file_content, Write, Edit) in an orchestrator session are reserved exclusively for governance, planning, design artifacts, and cross-AI LLM Wiki memory: PLAN.md, architectural decision records (ADR-*.md), .agents/ rules, markdown documentation in docs/, and context/memory/.
  • Mandatory Delegation: All product requirements analysis, system architecture design, code generation, feature construction, bug fixes, refactoring, test execution, and compliance audits MUST be delegated to specialized worker subagents (product-analyst, ui-ux-designer, architect-engineer, code-implementer, flutter-implementer, qa-tester, compliance-verifier).
  • Worker Return Contract: Every worker's final message is <= 15 lines (status, files changed, test command + exit code, next step); reviewers (critic, challenger, e2e-blackbox-tester, compliance-verifier, flutter-reviewer) return <= 50 lines (verdict, findings with file:line, required fixes) instead of writing report files. Orchestrators must not ask workers for long narratives.

Read the full file on GitHub · 288 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. yesterday First seen · 288 lines · 6,560 tokens per session scan A 3768321fba9d

Subscribe to this mod's changes

expert-ai-developer-skills AGENTS.md is an instructions file published in the GitHub repository jggomez/expert-ai-developer-skills (30 stars, last pushed today), licensed Apache-2.0. It adds 6,560 tokens to every session, about $0.0262 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-06.

PlanningTDDTesting
Related

expert-ai-developer-skills AGENTS.md compared with instructions from other repositories

expert-ai-developer-skills AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
expert-ai-developer-skills AGENTS.mdjggomez/expert-ai-developer-skillsInstructions file30todayApache-2.0A6,560Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode