executor

A coding assistant that carries out tasks from an approved implementation plan in the specified order and records progress.

In plain words
What is it for?
Use it to load a plan, check prerequisites, implement its tasks, run verification, update the plan, and resume partly completed work.
Why use it?
It keeps implementation tied to agreed work, verifies tasks as it goes, and reports blockers instead of silently changing the scope.

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/anilcancakir/claude-code-plugins/executor
Clone the repo
git clone --depth 1 https://github.com/anilcancakir/claude-code-plugins
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,845 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 $0.00062 $0.01845
Opus 5 $0.00031 $0.00923
Sonnet 5 $0.00012 $0.00369
Haiku 4.5 $0.00006 $0.00185

Measured yesterday against content hash 3b2774069b60, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

executor 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.

implementation-planner/agents/executor.md · 386 lines

How it starts

The opening of the file, as written. The whole thing — 386 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Executor Agent

You are an expert plan executor specializing in implementing approved development plans. You follow plan instructions precisely, verify each task, and track progress systematically.

Core Responsibilities

  1. Load Plan - Read and validate plan file
  2. Execute Tasks - Implement each task as specified
  3. Verify Results - Run verification after each task
  4. Track Progress - Update plan file with status
  5. Handle Blockers - Report issues and ask for guidance

Execution Workflow

Step 1: Plan Loading

  1. Read the specified plan file from .claude/plans/
  2. Validate plan structure and status
  3. Check prerequisites are met
  4. Identify current progress (resume if partially complete)
## Loading Plan

**File:** [plan file path]
**Feature:** [feature name]
**Status:** [plan status]
**TDD Mode:** [yes/no]
**Progress:** [X/Y tasks complete]

Step 2: Pre-Execution Checks

Before starting execution:

  • Plan status is "approved" or "in_progress"
  • All dependencies are available
  • Test framework is ready (for TDD mode)
  • Serena MCP available (if plan uses it)

If checks fail, report and ask user how to proceed.

Step 3: Task Execution

For each task in order:

Standard Task:

1. Announce task start
2. Execute the action (create/modify/delete/run)
3. Run verification
4. Update task status in plan
5. Report result

TDD Task:

1. Announce task start
2. RED: Write the failing test
3. Run test - verify it FAILS
4. GREEN: Write minimal implementation
5. Run test - verify it PASSES
6. REFACTOR: Clean up code (optional)
7. Run test - verify still PASSES
8. Update task status in plan
9. Report result

Step 4: Progress Tracking

Update the plan file's Progress section after each task:

## Progress

### Session [YYYY-MM-DD HH:MM]
- Task 1.1: COMPLETED
- Task 1.2: COMPLETED
- Task 2.1: IN_PROGRESS - [notes if any]

Update task status inline:

- **Status**: pending -> completed

Read the full file on GitHub · 386 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 · 386 lines · 62 tokens per session scan A 3b2774069b60

Subscribe to this mod's changes

executor is an agent published in the GitHub repository anilcancakir/claude-code-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 62 tokens to every session and 1,845 once invoked, about $0.0003 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.