analyze-complexity

A command that evaluates how difficult project tasks are and recommends which ones should be split into smaller tasks.

In plain words
What is it for?
Use it to score pending tasks from 1 to 10, identify tasks above a chosen threshold, and suggest subtasks or ways to reduce implementation risk.
Why use it?
Large or uncertain tasks are harder to estimate and implement safely. The analysis highlights risks, dependencies, testing needs, and unknowns before work begins.

Command for Claude Code

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 commands/snarktank/code-editing-agent/analyze-complexity
Clone the repo
git clone --depth 1 https://github.com/snarktank/code-editing-agent

Made for: Claude Code.

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 633 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00000 $0.00633
Opus 5 $0.00000 $0.00316
Sonnet 5 $0.00000 $0.00127
Haiku 4.5 $0.00000 $0.00063

Measured yesterday against content hash 7eb8edfcfe21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyze-complexity 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 yesterday.

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.

Origin

This is a copy

100% identical to analyze-complexity — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/tm/analyze-complexity/analyze-complexity.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze task complexity and generate expansion recommendations.

Arguments: $ARGUMENTS

Perform deep analysis of task complexity across the project.

Complexity Analysis

Uses AI to analyze tasks and recommend which ones need breakdown.

Execution Options

task-master analyze-complexity [--research] [--threshold=5]

Analysis Parameters

  • --research → Use research AI for deeper analysis
  • --threshold=5 → Only flag tasks above complexity 5
  • Default: Analyze all pending tasks

Analysis Process

1. Task Evaluation

For each task, AI evaluates:

  • Technical complexity
  • Time requirements
  • Dependency complexity
  • Risk factors
  • Knowledge requirements

2. Complexity Scoring

Assigns score 1-10 based on:

  • Implementation difficulty
  • Integration challenges
  • Testing requirements
  • Unknown factors
  • Technical debt risk

3. Recommendations

For complex tasks:

  • Suggest expansion approach
  • Recommend subtask breakdown
  • Identify risk areas
  • Propose mitigation strategies

Smart Analysis Features

  1. Pattern Recognition

    • Similar task comparisons
    • Historical complexity accuracy
    • Team velocity consideration
    • Technology stack factors
  2. Contextual Factors

    • Team expertise
    • Available resources
    • Timeline constraints
    • Business criticality
  3. Risk Assessment

    • Technical risks
    • Timeline risks
    • Dependency risks
    • Knowledge gaps

Output Format

Task Complexity Analysis Report
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

High Complexity Tasks (>7):
📍 #5 "Implement real-time sync" - Score: 9/10
   Factors: WebSocket complexity, state management, conflict resolution
   Recommendation: Expand into 5-7 subtasks
   Risks: Performance, data consistency

📍 #12 "Migrate database schema" - Score: 8/10
   Factors: Data migration, zero downtime, rollback strategy
   Recommendation: Expand into 4-5 subtasks
   Risks: Data loss, downtime

Medium Complexity Tasks (5-7):
📍 #23 "Add export functionality" - Score: 6/10
   Consider expansion if timeline tight

Low Complexity Tasks (<5):
✅ 15 tasks - No expansion needed

Summary:
- Expand immediately: 2 tasks
- Consider expanding: 5 tasks
- Keep as-is: 15 tasks

Read the full file on GitHub · 121 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. yesterday First seen · 121 lines · 0 tokens per session scan A 7eb8edfcfe21

Subscribe to this mod's changes

analyze-complexity is a command published in the GitHub repository snarktank/code-editing-agent (24 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 633 tokens. A static security scan graded it A with 0 findings. It is 100% identical to analyze-complexity, differing in 0 lines, and is treated as a copy.