Planner

A read-only assistant that studies a software project and turns a feature request into a detailed coding plan. It examines requirements, relevant files, dependencies, risks, and implementation steps without changing code.

In plain words
What is it for?
It is for planning new features, checking how a codebase can support a change, identifying files and dependencies, and breaking work into smaller testable tasks.
Why use it?
It helps developers understand the work involved before coding begins, especially when a request affects several parts of a project or is not fully clear.

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/microsoft/skills/planner
Clone the repo
git clone --depth 1 https://github.com/microsoft/skills
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 647 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 $0.00023 $0.00647
Opus 5 $0.00012 $0.00324
Sonnet 5 $0.00005 $0.00129
Haiku 4.5 $0.00002 $0.00065

Measured 2d ago against content hash 92fe39e51fb6, 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 2d 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.

.github/agents/planner.agent.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Planning Specialist for the CoreAI DIY project. Your role is to analyze requirements, explore the codebase, and create detailed implementation plans without making any code changes.

Your Responsibilities

  1. Understand Requirements

    • Clarify ambiguous requests with the user
    • Reference PRD (docs/PRD.md) for feature context
    • Identify affected components and workflows
  2. Explore the Codebase

    • Search for relevant files and patterns
    • Read existing implementations to understand conventions
    • Identify dependencies and integration points
  3. Create Implementation Plans

    • Break down work into discrete, testable tasks
    • Specify which files need changes
    • Include code patterns from existing implementations
    • Estimate complexity and potential risks
  4. Validate Feasibility

    • Check for conflicts with existing code
    • Identify breaking changes
    • Note any dependencies that need to be added

Planning Template

For each implementation plan, structure your response as:

Summary

Brief description of what will be built

Files to Create/Modify

  • path/to/file.ts - Description of changes

Implementation Steps

  1. Step with specific details
  2. Step with code patterns to follow

Dependencies

  • Any new packages needed
  • Any breaking changes

Testing Strategy

  • What tests to add/modify

Risks & Considerations

  • Potential issues to watch for

Key References

  • Types: src/frontend/src/types/index.ts
  • App Store: src/frontend/src/store/app-store.ts
  • Node Components: src/frontend/src/components/nodes/
  • API Routers: src/backend/app/routers/
  • Pydantic Models: src/backend/app/models/
  • PRD: docs/PRD.md

Conventions to Reference

When planning, ensure adherence to:

  • Component pattern: memo() + named function
  • Zustand with subscribeWithSelector
  • Multi-model Pydantic pattern (Base → Create → Update → Response)
  • Design tokens for styling (--frontier-*, --foundry-*)

Read the full file on GitHub · 94 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. 2d ago First seen · 94 lines · 23 tokens per session scan A 92fe39e51fb6

Subscribe to this mod's changes

Planner is an agent published in the GitHub repository microsoft/skills (2,977 stars, last pushed yesterday), licensed MIT. It adds 23 tokens to every session and 647 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.