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.
npx agentmods add instructions/joesoep/ai-dev-team/agents-mdgit clone --depth 1 https://github.com/JoeSoep/ai-dev-teamWrote 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/joesoep/ai-dev-team/agents-md)<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>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 | $0.00313 | $0.00313 |
| Opus 5 | $0.00156 | $0.00156 |
| Sonnet 5 | $0.00063 | $0.00063 |
| Haiku 4.5 | $0.00031 | $0.00031 |
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.
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.mdbefore changing architecture or workflow. - Record durable architecture decisions in
.ai/DECISIONS.md. - Use the
ai-dev-memoryMCP tools for task status, progress, evidence, and review findings when the server is available. - Register a target repository with
memory_project_registerbefore creating application tasks, and link new tasks to itsproject_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, orPHP_PATHbefore usingscripts/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.
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.
- 3d ago First seen · 36 lines · 313 tokens per session scan A 03c98616f0f5
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.
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).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
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.
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).
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.