TFE: Command for Claude Code

.claude/commands/phased-plan.md

phased-plan is a command for Claude Code from GGPrompts/TFE. It costs 10 tokens per session (1,818 once invoked), scanned A, original, MIT.

A workflow for carrying out a task in several planned phases, starting each phase with a fresh working context. It saves a summary after each phase so later phases can continue from earlier work.

In plain words
What is it for?
Use it for staged work such as researching a library, choosing an approach, implementing it, integrating it, and testing the result.
Why use it?
Long tasks can become harder to follow as the working context fills up. This approach keeps each phase focused while preserving the decisions and results already made.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is GGPrompts/TFE's own configuration. It tells Claude Code how to work on TFE itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything TFE configures →

Reuse

Borrowing it

Nothing to install: this file belongs to GGPrompts/TFE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/GGPrompts/TFE/main/.claude/commands/phased-plan.md
Clone the repo
git clone --depth 1 https://github.com/GGPrompts/TFE

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 phased-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/ggprompts/tfe/phased-plan.svg)](https://agentmods.dev/commands/ggprompts/tfe/phased-plan)
Your own site
<a href="https://agentmods.dev/commands/ggprompts/tfe/phased-plan"><img src="https://agentmods.dev/badge/commands/ggprompts/tfe/phased-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,818 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 $0.00010 $0.01818
Opus 5 $0.00005 $0.00909
Sonnet 5 $0.00002 $0.00364
Haiku 4.5 $0.00001 $0.00182

Measured 7d ago against content hash 72779c99d2e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

phased-plan 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 7d 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/commands/phased-plan.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phased Plan: Multi-Phase Execution with Auto-Compacting

You are executing a multi-phase plan where each phase runs in fresh context for maximum accuracy.

CRITICAL INSIGHT: Fresh context = better accuracy. Even if context window has room, compacting between phases improves results!

How This Works

After the user provides a phased plan, you will:

  1. Execute Phase 1 - Work on first phase completely
  2. Auto-compact - Create summary using Desktop Commander
  3. Execute Phase 2 - Start fresh with Phase 1 summary
  4. Auto-compact - Cumulative summary of Phases 1-2
  5. Continue - Each phase gets fresh context

Command Format

The user will provide phases in one of these formats:

Format 1: Inline

/phased-plan
Phase 1: Research syntax highlighting libraries for Go
Phase 2: Choose library and implement basic highlighting
Phase 3: Add language detection for code blocks
Phase 4: Integrate with preview rendering
Phase 5: Test and optimize performance

Format 2: With Goal

/phased-plan Implement syntax highlighting in preview

Then you ask for the phases.

Your Execution Process

Phase Execution Pattern:

For each phase:

  1. Announce Phase Start

    ═══════════════════════════════════════════════
    📋 PHASE N/TOTAL: [Phase Description]
    ═══════════════════════════════════════════════
    
    Previous phases summary:
    [Cumulative summary of completed phases]
    
    Now executing: [Current phase]
    
  2. Execute the Phase

    • Work on the phase completely
    • Show progress as you go
    • Complete all tasks for this phase
  3. Phase Completion

    ✅ PHASE N COMPLETE
    
    What was accomplished:
    - [Key achievements]
    - [Files modified]
    - [Important decisions]
    
  4. Git Commit (Optional but Recommended)

    📝 Phase complete! Ready to commit?
    
    Suggested commit message:
    Phase N: [Phase description]
    
    - [Achievement 1]
    - [Achievement 2]
    - [Files modified]
    
    Use: auto-compact --commit -g "Phase [N+1]"
    → This will: commit changes + compact + continue
    

Read the full file on GitHub · 293 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. 7d ago First seen · 293 lines · 10 tokens per session scan A 72779c99d2e9

Subscribe to this mod's changes

phased-plan is a command published in the GitHub repository GGPrompts/TFE (20 stars, last pushed 2mo ago), licensed MIT. It adds 10 tokens to every session and 1,818 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.