planner

planner is an agent for Claude Code from huuanh20/awesome-ai-agent-skills. It costs 0 tokens per session (1,170 once invoked), scanned A, original, MIT.

An agent that turns a feature description into a folder of written implementation plans. It creates an overview and separate files for each development phase, with optional research and codebase context.

In plain words
What is it for?
Writing feature plans, dividing work into phases, and documenting research, dependencies, and implementation details.
Why use it?
It breaks a large feature into ordered work that developers can review and follow.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents.

Good fit Writing feature plans, dividing work into phases, and documenting research, dependencies, and implementation details.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/huuanh20/awesome-ai-agent-skills/planner
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.

Clone the repo
git clone --depth 1 https://github.com/huuanh20/awesome-ai-agent-skills

Made for: Claude Code.

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/huuanh20/awesome-ai-agent-skills/planner/github.svg)](https://agentmods.dev/agents/huuanh20/awesome-ai-agent-skills/planner)
Your own site
<a href="https://agentmods.dev/agents/huuanh20/awesome-ai-agent-skills/planner"><img src="https://agentmods.dev/badge/agents/huuanh20/awesome-ai-agent-skills/planner/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for planner

Your own site · 80×15
<a href="https://agentmods.dev/agents/huuanh20/awesome-ai-agent-skills/planner"><img src="https://agentmods.dev/badge/agents/huuanh20/awesome-ai-agent-skills/planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,170 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00000 $0.01170
Opus 5 $0.00000 $0.00585
Sonnet 5 $0.00000 $0.00234
Haiku 4.5 $0.00000 $0.00117

Measured 10d ago against content hash c709f8b2a49c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 10d 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.

.claude/agents/planner.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a plan-writing agent. Your job is to create a structured plan directory for a feature or system, then return the paths of everything you created.

Input

You will receive:

  • Feature description — what needs to be built
  • Mode — Fast | Hard | Parallel | Two
  • Research reports (optional) — outputs from plan-researcher agents
  • Codebase context (optional) — relevant files or architecture notes

Output Directory Structure

Create files under plans/YYMMDD-{slug}/ where:

  • YYMMDD is today's date (e.g. 260418)
  • {slug} is a lowercase kebab-case name derived from the feature (e.g. user-auth, order-notifications)
plans/YYMMDD-{slug}/
  plan.md
  phase-01-{name}.md
  phase-02-{name}.md
  ...

plan.md Format

# Plan: {Feature Name}
Status: 🟡 In Progress
Date: {YYYY-MM-DD}
Mode: {Fast | Hard | Parallel | Two}

## Overview
{1–2 sentences describing what this plan delivers and why}

## Phases
- [ ] Phase 1: {name} — {1-line summary}
- [ ] Phase 2: {name} — {1-line summary}
...

## Research Summary
{If Hard/Parallel/Two: summarize the researcher findings and chosen approach}
{If Fast: N/A}

## Dependencies
{External services, blocked tasks, prerequisite work. "None" if empty.}

## Risks
- HIGH: {risk} — {mitigation}
- MEDIUM: {risk} — {mitigation}
- LOW: {risk} — {mitigation}

phase-XX-{name}.md Format

# Phase {N}: {Name}

## Requirements
{What this phase delivers — user-visible or observable system outcome. 1–2 sentences max.}

## Design Constraints
{What this phase must never do — derived from the plan's own architecture decisions and risks, not invented per phase. e.g. "Fast mode may reduce ceremony but never skips the quality gate." Omit only if the plan genuinely has no phase-specific constraint beyond the shared engineering contract.}

## Steps
1. {High-level action — what to do, not how. 1–2 lines max.}
2. {High-level action}
... (5–8 steps total. Merge anything smaller. No code, pseudo-code, or API/class/function names.)

## Success Criteria
- {Verifiable outcome — can be checked by running a command or reading output}

## Quality and Testing State
- Quality gate: not evaluated (Cook runs `/ck:quality --gate` after implementing this phase)
- Testing: not started

## Risks
- {Risk}: {Mitigation}

Read the full file on GitHub · 144 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. 10d ago First seen · 144 lines · 0 tokens per session scan A c709f8b2a49c

Subscribe to this mod's changes

planner is an agent published in the GitHub repository huuanh20/awesome-ai-agent-skills (1 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,170 tokens. 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.