my_execute

A command that carries out approved coding plans stored in a project's .claude/plans directory. It works through the plan's tasks in order and verifies the work as it goes.

In plain words
What is it for?
Use it to select or run a plan, optionally require TDD—writing tests before implementation—and update progress after each phase.
Why use it?
It turns an agreed plan into tracked implementation work and reports problems when a task cannot be completed.

Command

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/anilcancakir/claude-code-plugins/my_execute
Clone the repo
git clone --depth 1 https://github.com/anilcancakir/claude-code-plugins
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 862 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 $0.00028 $0.00862
Opus 5 $0.00014 $0.00431
Sonnet 5 $0.00006 $0.00172
Haiku 4.5 $0.00003 $0.00086

Measured 2d ago against content hash fb15aa40ab1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

my_execute 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.

implementation-planner/commands/my_execute.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/my_execute - Plan Execution

Execute approved implementation plans from .claude/plans/ directory.

Usage

/my_execute                    # List and select plan
/my_execute [plan-file]        # Execute specific plan
/my_execute --tdd [plan-file]  # Force TDD mode

Arguments

  • --tdd - Force TDD mode even if plan does not specify it
  • [plan-file] - Path to plan file (relative to .claude/plans/)

Examples

/my_execute
/my_execute 20260126-143000-user-authentication.md
/my_execute --tdd order-management.md

What Happens

  1. Select Plan

    • If no file specified, lists available plans
    • User selects which plan to execute
    • Validates plan status is "approved" or "in_progress"
  2. Spawn Executor Agent

    • Uses Sonnet model for efficient execution
    • Has access to all project tools and MCP servers
  3. Execute Tasks

    • Follows plan phases in order
    • Executes each task as specified
    • Runs verification after each task
    • Updates progress in plan file
  4. Phase Transitions

    • Summarizes completed phase
    • Asks for confirmation before next phase
    • Allows course correction if needed
  5. Handle Issues

    • Reports blockers immediately
    • Asks how to proceed (retry/skip/modify/abort)
    • Documents issues in plan file

TDD Execution

When TDD mode is active (plan has tdd: true or --tdd flag):

For each implementation task:

  1. RED: Write failing test

    • Create test file if needed
    • Write test that expresses expected behavior
    • Run test - must FAIL
  2. GREEN: Write minimal implementation

    • Just enough code to pass test
    • No optimization, no extra features
    • Run test - must PASS
  3. REFACTOR: Clean up code

    • Improve code quality
    • Run tests after each change
    • Tests must stay GREEN

Progress Tracking

The plan file is updated with progress:

## Progress

### Session 2026-01-26 14:30
- Task 1.1: COMPLETED
- Task 1.2: COMPLETED
- Task 2.1: IN_PROGRESS

Read the full file on GitHub · 140 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 · 140 lines · 28 tokens per session scan A fb15aa40ab1b

Subscribe to this mod's changes

my_execute is a command published in the GitHub repository anilcancakir/claude-code-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 28 tokens to every session and 862 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.