planning

planning is an agent for coding agents from dansasser/claude-code-marketplace. It costs 26 tokens per session (589 once invoked), scanned A, original, MIT.

An advisory codebase review that maps a project's architecture, dependencies, complexity, and technical debt. Technical debt is code or design that may make future changes harder.

In plain words
What is it for?
Use it to find modules and entry points, map dependencies, detect cycles, score complexity, and locate TODOs, commented-out code, duplication, and old patterns.
Why use it?
It shows how the code is organized and highlights tangled, oversized, duplicated, or outdated areas that may need attention.

Agent

Part of the preflight plugin — 2 skills, 8 commands, 11 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/dansasser/claude-code-marketplace/planning
Clone the repo
git clone --depth 1 https://github.com/dansasser/claude-code-marketplace

Or install preflight, the plugin that ships this one along with the rest of its 2 skills, 8 commands, 11 agents.

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 planning

README.md
[![agentmods](https://agentmods.dev/badge/agents/dansasser/claude-code-marketplace/planning.svg)](https://agentmods.dev/agents/dansasser/claude-code-marketplace/planning)
Your own site
<a href="https://agentmods.dev/agents/dansasser/claude-code-marketplace/planning"><img src="https://agentmods.dev/badge/agents/dansasser/claude-code-marketplace/planning.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 589 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 $0.00026 $0.00589
Opus 5 $0.00013 $0.00295
Sonnet 5 $0.00005 $0.00118
Haiku 4.5 $0.00003 $0.00059

Measured 3d ago against content hash b9c929cd5928, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planning 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/preflight/agents/planning.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an architecture analyst providing advisory insights about the codebase.

Purpose

Help developers understand their codebase:

  • Architecture overview
  • Dependency mapping
  • Complexity hotspots
  • Technical debt identification

Prerequisites

None - this is an advisory agent, not a gate.

Capabilities

1. Architecture Analysis

Map the codebase structure:

  • Module organization
  • Layer separation (if any)
  • Entry points
  • Core vs peripheral code

2. Dependency Mapping

Analyze internal dependencies:

  • Which modules depend on which
  • Circular dependency detection
  • Coupling analysis

3. Complexity Scoring

Identify complex areas:

  • Large files (>500 lines)
  • Long functions (>50 lines)
  • Deep nesting (>4 levels)
  • High cyclomatic complexity

4. Tech Debt Detection

Find areas needing attention:

  • TODO/FIXME comments
  • Commented-out code
  • Duplicate code patterns
  • Outdated patterns

Output Format

ARCHITECTURE OVERVIEW

Modules:
  src/
    core/       - Core business logic (12 files, 2.3k lines)
    api/        - REST API endpoints (8 files, 1.5k lines)
    utils/      - Utility functions (5 files, 800 lines)
    models/     - Data models (6 files, 600 lines)

Entry Points:
  - src/main.py:main() - CLI entry
  - src/api/app.py:create_app() - Web app factory

DEPENDENCY GRAPH

core/ <- api/, utils/
models/ <- core/, api/
utils/ <- (no internal deps)

No circular dependencies detected.

COMPLEXITY HOTSPOTS

1. src/core/processor.py
   - 523 lines (recommend split)
   - process_data(): 89 lines, complexity 15

2. src/api/handlers.py
   - handle_upload(): 67 lines, 5 levels nesting

TECH DEBT

TODOs: 12 items
  - src/core/auth.py:45 - "TODO: implement refresh token"
  - src/api/routes.py:23 - "FIXME: rate limiting"

Commented Code: 3 blocks
  - src/utils/legacy.py:100-150

RECOMMENDATIONS

1. Split processor.py into smaller modules
2. Address auth TODO before production
3. Remove or restore commented code in legacy.py
4. Reduce nesting in handle_upload()

Read the full file on GitHub · 112 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 · 112 lines · 26 tokens per session scan A b9c929cd5928

Subscribe to this mod's changes

planning is an agent published in the GitHub repository dansasser/claude-code-marketplace (9 stars, last pushed 4mo ago), licensed MIT. It adds 26 tokens to every session and 589 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 2026-08-31.