ai-dev-team AGENTS.md

ai-dev-team AGENTS.md is an instructions file for Codex, OpenCode from JoeSoep/ai-dev-team. It costs 313 tokens per session, scanned A, original, MIT.

Repository instructions for a local-first workspace that coordinates AI development work and shared project memory. They define the source-of-truth files, runtime rules and how tasks and projects should be registered.

In plain words
What is it for?
Use them when working on the AI development team cockpit or a registered target repository. They explain which project files to read, how to record decisions, how to register tasks and how to choose the configured runtime.
Why use it?
They help agents preserve architecture decisions and task evidence in the repository instead of relying only on temporary database state. They also reduce mistakes from assuming the wrong runtime or project configuration.

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/joesoep/ai-dev-team/agents-md
Clone the repo
git clone --depth 1 https://github.com/JoeSoep/ai-dev-team

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 ai-dev-team AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/joesoep/ai-dev-team/agents-md.svg)](https://agentmods.dev/instructions/joesoep/ai-dev-team/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/joesoep/ai-dev-team/agents-md"><img src="https://agentmods.dev/badge/instructions/joesoep/ai-dev-team/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 313 This file is loaded in full into every session.
When invoked 313 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 $0.00313 $0.00313
Opus 5 $0.00156 $0.00156
Sonnet 5 $0.00063 $0.00063
Haiku 4.5 $0.00031 $0.00031

Measured 3d ago against content hash 03c98616f0f5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ai-dev-team 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 3d 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 · 36 lines

What it actually says

Agent Instructions

Purpose

This workspace builds a local-first AI development team cockpit. Codex is the default implementation agent. Claude Code can review work through the same shared memory MCP server.

Source Of Truth

  • Read .ai/PROJECT.md before changing architecture or workflow.
  • Record durable architecture decisions in .ai/DECISIONS.md.
  • Use the ai-dev-memory MCP tools for task status, progress, evidence, and review findings when the server is available.
  • Register a target repository with memory_project_register before creating application tasks, and link new tasks to its project_id.
  • Keep code changes and durable documentation in Git. Do not treat the SQLite runtime database as the only permanent record.

Runtime Rules

  • This MCP workspace runs on Node, not PHP.
  • Target repository runtimes are machine-specific. Read the registered project profile, local environment file, or target repo instructions before running validation.
  • Do not assume global language runtimes are compatible with a target project. For PHP projects, use the target project's configured PHP executable or set AI_DEV_TEAM_PHP, PHP82_PATH, or PHP_PATH before using scripts/php82.ps1.

Working Rules

  • Keep builder and reviewer roles separate for non-trivial changes.
  • Save actual validation command output as evidence before marking a task done.
  • When parallel file editing is introduced, use separate Git worktrees for writers and merge through reviewed commits.
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. 3d ago First seen · 36 lines · 313 tokens per session scan A 03c98616f0f5

Subscribe to this mod's changes

ai-dev-team AGENTS.md is an instructions file published in the GitHub repository JoeSoep/ai-dev-team (2 stars, last pushed 3mo ago), licensed MIT. It adds 313 tokens to every session, about $0.0016 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

cognirepo CLAUDE.md

Instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).

ashlesh-t/cognirepo · 2,241 tokens

aeon CLAUDE.md

Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).

aeonfun/aeon · 3,720 tokens

inkwell-memory CLAUDE.md

Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.

veronchenko/inkwell-memory · 2,378 tokens

RNR-Enhanced-Cognee AGENTS.md

AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.

vincentspereira/RNR-Enhanced-Cognee · 6,855 tokens

memory-mcp-1file AGENTS.md

Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).

pomazanbohdan/memory-mcp-1file · 7,991 tokens

openexp CLAUDE.md

Instructions for anthroos/openexp, covering openexp — development instructions, memory protocol (mandatory), before starting any task, after completing a task and when the user shares context.

anthroos/openexp · 799 tokens