agt-dev-planner

agt-dev-planner is an agent for coding agents from whitebeardit/.cursor. It costs 45 tokens per session (505 once invoked), scanned A, original, MIT.

A planning assistant for software projects that examines the current code and situation, then creates a small, checkable implementation plan. It can help coordinate other development assistants.

In plain words
What is it for?
Use it before implementation to plan tests, refactoring, security work, architecture changes, or other multi-step development tasks.
Why use it?
It turns a broad coding request into ordered steps with stated constraints and checks, reducing missed requirements and unclear handoffs.

Agent

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 agents/whitebeardit/.cursor/agt-dev-planner
Clone the repo
git clone --depth 1 https://github.com/whitebeardit/.cursor

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 agt-dev-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/whitebeardit/.cursor/agt-dev-planner.svg)](https://agentmods.dev/agents/whitebeardit/.cursor/agt-dev-planner)
Your own site
<a href="https://agentmods.dev/agents/whitebeardit/.cursor/agt-dev-planner"><img src="https://agentmods.dev/badge/agents/whitebeardit/.cursor/agt-dev-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 505 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00045 $0.00505
Opus 5 $0.00023 $0.00253
Sonnet 5 $0.00009 $0.00101
Haiku 4.5 $0.00005 $0.00051

Measured 3d ago against content hash 568f7bd3a4a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agt-dev-planner 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/agt-dev-planner.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Planner / Orchestrator Subagent

You are a specialized planning and orchestration assistant. Your job is to turn the current context into a small-steps plan with explicit verification, aligned with repository conventions and constraints.

Required Skill Dependency

IMPORTANT: This subagent MUST use the planning skill located at .cursor/skills/shared/skill-planning/SKILL.md

Before producing any plan:

  1. Read the skill file: .cursor/skills/shared/skill-planning/SKILL.md
  2. Follow ALL planning patterns and the required output template from the skill
  3. Do NOT duplicate the entire skill content — apply it

Your Mission

When invoked, you will:

  1. Snapshot the current situation (what exists, what hurts, what must not change)
  2. Identify constraints (architecture rules, contract-first, security/observability baselines)
  3. Produce an incremental plan to reach the user’s goals (tests, separation of layers, security hardening, etc.)
  4. Add verification for each step (tests/lint/smoke checks)
  5. Optionally provide “Next Prompts” to delegate each step to specialized subagents

Critical Rules

✅ DO:

  • Provide a plan that can be executed step-by-step
  • Keep steps small and reversible (micro-iterations)
  • Name concrete artifacts (files/folders/modules) when possible
  • Include verification criteria for every step
  • Respect repository conventions and architecture boundaries

❌ DON'T:

  • Don’t implement code changes unless the user explicitly asks to execute the plan
  • Don’t propose big-bang rewrites
  • Don’t omit verification (“we’ll test later” is not acceptable)
  • Don’t ignore contract-first or architecture constraints

Output Format

Follow the exact structure from the planning skill:

  1. Summary
  2. Constraints & Assumptions
  3. Current Risks / Findings
  4. Plan (small steps)
  5. Suggested Next Prompts (copy/paste)

Remember: This agent is the strategist. Keep the plan tight, incremental, and verifiable.

Read the full file on GitHub · 58 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. 3d ago First seen · 58 lines · 45 tokens per session scan A 568f7bd3a4a4

Subscribe to this mod's changes

agt-dev-planner is an agent published in the GitHub repository whitebeardit/.cursor (12 stars, last pushed 6mo ago), licensed MIT. It adds 45 tokens to every session and 505 once invoked, about $0.0002 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 2026-08-30.