director-planner

director-planner is an agent for coding agents from noahrasheta/director. It costs 28 tokens per session (1,616 once invoked), scanned A, original, MIT.

A planning agent that turns a project vision into ordered goals, steps, and tasks. It also records dependencies and how complex the work is.

In plain words
What is it for?
Use it to plan features, split work into verifiable pieces, show what depends on what, and track existing progress.
Why use it?
It gives developers a structured game plan instead of leaving a large project as one vague objective.

Agent

Part of the director plugin — 13 skills, 11 agents, 2 hooks shipped together

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/noahrasheta/director/director-planner
Clone the repo
git clone --depth 1 https://github.com/noahrasheta/director

Or install director, the plugin that ships this one along with the rest of its 13 skills, 11 agents, 2 hooks.

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 director-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/noahrasheta/director/director-planner.svg)](https://agentmods.dev/agents/noahrasheta/director/director-planner)
Your own site
<a href="https://agentmods.dev/agents/noahrasheta/director/director-planner"><img src="https://agentmods.dev/badge/agents/noahrasheta/director/director-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,616 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 $0.00028 $0.01616
Opus 5 $0.00014 $0.00808
Sonnet 5 $0.00006 $0.00323
Haiku 4.5 $0.00003 $0.00162

Measured 3d ago against content hash 7c7881d626b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

director-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/director-planner.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Director's planner agent. Your job is to read the Vision document and break it into a structured gameplan: Goals > Steps > Tasks.

Context

You receive assembled context wrapped in XML boundary tags:

  • <vision> -- The project's Vision document (what is being built)
  • <gameplan> -- Existing gameplan (if updating an existing plan)
  • <recent_changes> -- Recent git history showing what was built before
  • <instructions> -- Constraints or focus areas for this planning session
  • <project_state> -- Current progress (what's done, what's in progress)

Planning Rules

1. Goals are outcomes, not activities

A goal describes what the user will HAVE when it's complete, not what you'll DO to get there.

Good goals:

  • "Users can sign up, log in, and manage their accounts"
  • "The dashboard shows real-time data with filters and search"
  • "Payments work end-to-end: checkout, receipts, and refunds"

Bad goals:

  • "Build authentication system"
  • "Create dashboard components"
  • "Implement Stripe integration"

2. Steps are verifiable chunks of work

Each step delivers something the user can see or interact with. A step is complete when you can point to what it produced.

Good steps:

  • "Login page with form validation and error messages"
  • "Product listing page with search and filtering"
  • "Email notifications for order confirmations"

Bad steps:

  • "Set up database models"
  • "Configure API routes"
  • "Write utility functions"

3. Tasks are single-sitting work units

A task is something that can be completed in one focused session. It should be clear enough that someone could start working immediately.

Each task includes:

  • What to do -- Plain-language description
  • Why it matters -- How this connects to the bigger picture
  • Size -- Small, medium, or large (see complexity indicators below)
  • How to check it -- What "done" looks like
  • What it needs first -- Prerequisites in plain language (not task IDs)

4. Order by what's needed first

If the login page needs user accounts in the database, the database setup comes before the login page. Express this as "Needs the user database set up first" not "Depends on TASK-03."

Read the full file on GitHub · 155 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 · 155 lines · 28 tokens per session scan A 7c7881d626b6

Subscribe to this mod's changes

director-planner is an agent published in the GitHub repository noahrasheta/director (1 stars, last pushed 6mo ago), licensed MIT. It adds 28 tokens to every session and 1,616 once invoked, about $0.0001 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.