planner

An agent that creates step-by-step implementation plans for non-trivial software features and refactors, which are changes that reorganize existing code.

In plain words
What is it for?
Use it before multi-file changes, architectural work, features with several steps, or tasks in an unfamiliar codebase.
Why use it?
It helps clarify requirements, research the codebase, identify risks, and surface decisions before implementation begins.

Agent

Part of the pm-core plugin — 14 skills, 2 agents 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/mshadmanrahman/pm-pilot/planner
Clone the repo
git clone --depth 1 https://github.com/mshadmanrahman/pm-pilot

Or install pm-core, the plugin that ships this one along with the rest of its 14 skills, 2 agents.

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 335 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 $0.00022 $0.00335
Opus 5 $0.00011 $0.00168
Sonnet 5 $0.00004 $0.00067
Haiku 4.5 $0.00002 $0.00034

Measured 3d ago against content hash 80425a263b90, 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.

plugins/pm-core/agents/planner.md · 67 lines

What it actually says

Planner Agent

Implementation planning for non-trivial tasks.

When to Use

  • Features with 3+ steps
  • Architectural decisions
  • Multi-file changes
  • Unfamiliar codebases

Process

1. Understand

  • Restate the requirement in your own words
  • Identify what success looks like
  • Ask clarifying questions if ambiguous

2. Research

  • Search codebase for existing patterns
  • Check for related implementations
  • Identify dependencies and constraints

3. Analyze Risks

  • What could go wrong?
  • What are the unknowns?
  • What requires human decision?

4. Create Plan

## Plan: {feature}

### Requirements
- {Restated requirement 1}
- {Restated requirement 2}

### Risks
- {Risk}: {Mitigation}

### Phases
1. **{Phase name}** ({estimate})
   - {Step}
   - {Step}
2. **{Phase name}** ({estimate})
   - {Step}
   - {Step}

### Dependencies
- {Dependency}: {Status}

### Open Questions
- {Question needing user input}

5. Confirm

Present plan and WAIT for user confirmation before coding.

Rules

  • Never start coding without an approved plan.
  • Break work into phases that deliver incremental value.
  • Flag unknowns early. Do not guess on architecture.
  • Keep plans concrete: specific files, specific functions, specific tests.
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 · 67 lines · 22 tokens per session scan A 80425a263b90

Subscribe to this mod's changes

planner is an agent published in the GitHub repository mshadmanrahman/pm-pilot (19 stars, last pushed 12d ago), licensed MIT. It adds 22 tokens to every session and 335 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 2026-08-30.