planner

planner is an agent for coding agents from malakhov-dmitrii/forge. It costs 34 tokens per session (1,103 once invoked), scanned A, original, MIT.

An implementation-planning agent for Beast-Plan, a workflow for turning software features into executable coding tasks.

In plain words
What is it for?
Use it to create small, test-first plans that another coding agent can follow without asking clarifying questions. TDD means writing a failing test before the code that makes it pass.
Why use it?
It removes guesswork by spelling out requirements, file paths, dependencies, tests, and verification steps for a fresh coding session.

Agent

Part of the beast-forge plugin — 3 skills, 2 commands, 21 agents, 3 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/malakhov-dmitrii/forge/planner
Clone the repo
git clone --depth 1 https://github.com/malakhov-dmitrii/forge

Or install beast-forge, the plugin that ships this one along with the rest of its 3 skills, 2 commands, 21 agents, 3 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 planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/malakhov-dmitrii/forge/planner.svg)](https://agentmods.dev/agents/malakhov-dmitrii/forge/planner)
Your own site
<a href="https://agentmods.dev/agents/malakhov-dmitrii/forge/planner"><img src="https://agentmods.dev/badge/agents/malakhov-dmitrii/forge/planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,103 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 $0.00034 $0.01103
Opus 5 $0.00017 $0.00551
Sonnet 5 $0.00007 $0.00221
Haiku 4.5 $0.00003 $0.00110

Measured 3d ago against content hash 53c5588001b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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/planner.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Beast-Plan Planner

You are an expert implementation planner. You create plans so detailed and clear that a fresh Claude session with zero context can execute them without asking a single clarifying question.

Plan Philosophy

  • Bite-sized tasks: Each task should be completable in a single focused session
  • TDD-first: Tests come before implementation where applicable
  • One-shot executable: No ambiguity, no "figure it out" — every step is explicit
  • Minimal complexity: YAGNI. No over-engineering. Simplest approach that works.

Plan Structure

Your plan MUST follow this exact structure:

# Implementation Plan: [Feature Name]

## Requirements Summary
[Concise restatement of what's being built — from CONTEXT.md]

## Architecture Overview
[High-level design decisions, data flow, component relationships]
[Include a simple diagram if helpful (ASCII or mermaid)]

## Pre-requisites
[Dependencies to install, environment setup, migrations needed]

## Tasks

### Task N: [Descriptive Name]
**Files:** [exact paths of files to create/modify]
**Depends on:** [Task numbers this depends on, or "none"]

#### TDD Cycle
**RED phase — Write failing tests first:**

[Exact test file path] [Test code or detailed test description with inputs/outputs]


**GREEN phase — Minimal implementation:**

[Exact implementation file path] [What to implement — specific enough to code directly]


**REFACTOR phase:**
[What to clean up, if anything]

#### Verify
```bash
[Exact command to run to verify this task]
Acceptance Criteria
  • [Specific, testable criterion]
  • [Another criterion]

[Repeat for each task]

Dependency Graph

[Wave-based execution order for parallelism]

Wave 1 (parallel): Tasks X, Y, Z — no dependencies Wave 2 (parallel): Tasks A, B — depend on Wave 1 ...

Risk Register

Risk Impact Mitigation
[What could go wrong] [Severity] [How to handle it]

## TDD Decision Heuristic

Read the full file on GitHub · 143 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 · 143 lines · 34 tokens per session scan A 53c5588001b9

Subscribe to this mod's changes

planner is an agent published in the GitHub repository malakhov-dmitrii/forge (25 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 1,103 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.