ai-dev-agent

Rules for a Trello-driven coding workflow in which the user remains responsible for approving development actions.

In plain words
What is it for?
Use them when analysing, implementing, reviewing, committing, or syncing work connected to Trello tickets.
Why use it?
They prevent an AI agent from committing code, pushing changes, or changing Trello tickets without explicit permission.

Cursor rule for Cursor

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 rules/mih-nig-afe/mcp-dev-loop-trello-cursor-github/ai-dev-agent
Clone the repo
git clone --depth 1 https://github.com/Mih-Nig-Afe/MCP-Dev-Loop-Trello-Cursor-GitHub

Made for: Cursor.

Per session 250 This file is loaded in full into every session.
When invoked 250 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 $0.00250 $0.00250
Opus 5 $0.00125 $0.00125
Sonnet 5 $0.00050 $0.00050
Haiku 4.5 $0.00025 $0.00025

Measured yesterday against content hash 5cd9a651b7f8, 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-agent 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 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.

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.

.cursor/rules/ai-dev-agent.mdc · 30 lines

What it actually says

MCP Dev Loop — Human Approval Required

This project uses a Trello-driven dev loop. You are not autonomous. The user is always the controller.

Never without explicit user approval

  • git commit
  • git push (especially to main / master)
  • Trello move_card, mark_in_progress, mark_done
  • Trello add_comment (except when user says "update trello")

Workflow phases

  1. Analyze — read ticket + comments, propose plan, no code edits
  2. Implement — only after user approves the plan
  3. Review — user says fix / improve / commit / update trello
  4. Commit — only when user says commit
  5. Sync — only when user says update trello

Ticket commands

Recognize: analyze ticket, implement ticket, prepare commit, update trello, mark in progress, mark done.

Use the trello MCP server and the trello-dev-loop skill when handling these.

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 · 30 lines · 250 tokens per session scan A 5cd9a651b7f8

Subscribe to this mod's changes

ai-dev-agent is a cursor rule published in the GitHub repository Mih-Nig-Afe/MCP-Dev-Loop-Trello-Cursor-GitHub (0 stars, last pushed 2mo ago), licensed MIT. It adds 250 tokens to every session, about $0.0013 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.