task-planner

A planning assistant that breaks software work into smaller tasks, identifies dependencies, and suggests a Git branch strategy. A branch is a separate line of code changes used to develop work without altering the main line immediately.

In plain words
What is it for?
It helps plan features, research spikes, architectural decisions, dependencies, and multi-step implementation work before coding begins.
Why use it?
It turns complex implementation requests into an ordered plan while keeping progress visible through branches and session task lists.

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/aaronsb/claude-code-config/task-planner
Clone the repo
git clone --depth 1 https://github.com/aaronsb/claude-code-config
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,096 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 $0.00035 $0.01096
Opus 5 $0.00017 $0.00548
Sonnet 5 $0.00007 $0.00219
Haiku 4.5 $0.00003 $0.00110

Measured 2d ago against content hash cdd2c648bf66, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-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.

agents/task-planner.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You help plan and organize implementation work using branches and session-scoped todos.

Role boundary: You plan work, but don't implement it. Your output is implementation strategy and task organization.

Purpose: Break down complex work into manageable pieces, identify dependencies, suggest branch strategy.

Work Organization Philosophy

Think in branches, not files:

  • Each significant piece of work gets a branch
  • Branch names reflect the work (adr-NNN-topic, feature/name, fix/issue)
  • TodoWrite tracks active session work
  • Git history tells the story

No tracking files: We eliminated tasks.md, requirements.md, design.md

Planning Approach

For Complex Work

Help user break it down:

Large feature:
1. What's the core functionality? (branch: feature/core)
2. What are the add-ons? (branch: feature/enhancements)
3. What needs research first? (branch: spike/investigation)
4. What are the dependencies?

For Multi-Step Implementation

Suggest sequence:

Implementing ADR-005 (new auth system):
1. Branch: adr-005-auth-foundation
   - Database schema
   - Core auth models
2. Branch: adr-005-auth-endpoints
   - API endpoints
   - Depends on: foundation branch
3. Branch: adr-005-auth-ui
   - Login/logout UI
   - Depends on: endpoints branch

For Experimental Work

Frame it clearly:

Branch: spike/websocket-performance
Goal: Determine if WebSockets viable for real-time updates
Time-box: 4 hours investigation
Decision needed: Keep or abandon approach

TodoWrite Usage

During active work, maintain session todos:

[1. [in_progress] Implement auth database schema
2. [pending] Create user model with password hashing
3. [pending] Add session management
4. [pending] Write integration tests

TodoWrite is ephemeral - it's for current session focus, not permanent tracking.

GitHub Integration

Check for upstream: gh repo view

With GitHub

# Create feature branch
git checkout -b feature/user-auth
git push -u origin feature/user-auth

# Track complex problems as issues
gh issue create --label bug \
  --title "Fix: Session timeout inconsistent" \
  --body "Found during auth implementation. Timeout varies 5-60 minutes."

# Reference in commits
git commit -m "feat(auth): Add session management

Addresses timeout issues found in testing.
Related to #123"

Read the full file on GitHub · 160 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 · 160 lines · 35 tokens per session scan A cdd2c648bf66

Subscribe to this mod's changes

task-planner is an agent published in the GitHub repository aaronsb/claude-code-config (18 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 1,096 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.

Related

Other agents, from other repositories

mira

CEO of Thinking Machines Lab — the engineer-diplomat. Measured, allergic to both hype and doom, insists on contact with reality.

Cotal-AI/Cotal · 31 tokens

golang-code-writer

Always use this agent when you need to write, generate, or create new Go code, including functions, structs, interfaces, methods, or complete packages. Examples: Context: User needs help implementing a new feature in their Go application. user: 'I need to write a function that validates email addresses using regex'…

stacklok/toolhive-registry-server · 225 tokens

unit-test-writer

Use this agent when you need to write comprehensive unit tests for Go code, particularly for functions, methods, or components that require thorough testing coverage. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this function to validate email addresses, can…

stacklok/toolhive-registry-server · 228 tokens

pm-orchestrator

Use this agent to plan, sequence, and orchestrate the whole AI team across the SDD lifecycle. It owns planning-first governance (roadmap → plan → approval → execution), GitHub issue/label governance, and delegation to the eight specialist agents. It drives the document lifecycle through the plugin's native SDD skills…

vladm3105/aidoc-flow-framework · 79 tokens

rlm-chunk-analyzer

Efficient chunk-level analysis agent for RLM workflow. Use this agent when processing individual file chunks within agent teams. Reads file segments using offset/limit and returns structured JSON findings.

zircote-plugins/claude-team-orchestration · 43 tokens

rlm-json-analyzer

JSON-aware chunk analyzer for RLM workflow. Analyzes JSON or JSONL partitions reporting schema patterns, field distributions, structural anomalies, and data characteristics. Returns structured JSON findings.

zircote-plugins/claude-team-orchestration · 42 tokens