Executor

Executor is an agent for Claude Code from srnichols/plan-forge. It costs 24 tokens per session (2,096 once invoked), scanned A, original, MIT.

An execution assistant that carries out a detailed project plan one bounded task at a time. It checks requirements, runs validation steps, and revisits the plan during implementation.

In plain words
What is it for?
It is for implementing software phase plans through small execution slices, dependency checks, testing, linting, and final completeness reviews.
Why use it?
It reduces missed requirements, unfinished tasks, and changes that drift away from the agreed plan. Validation gates help catch build, test, or lint problems as work progresses.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions subagents.

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/srnichols/plan-forge/executor
Clone the repo
git clone --depth 1 https://github.com/srnichols/plan-forge

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 Executor

README.md
[![agentmods](https://agentmods.dev/badge/agents/srnichols/plan-forge/executor.svg)](https://agentmods.dev/agents/srnichols/plan-forge/executor)
Your own site
<a href="https://agentmods.dev/agents/srnichols/plan-forge/executor"><img src="https://agentmods.dev/badge/agents/srnichols/plan-forge/executor.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,096 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 5.1 $0.00024 $0.02096
Opus 5 $0.00012 $0.01048
Sonnet 5 $0.00005 $0.00419
Haiku 4.5 $0.00002 $0.00210

Measured 2d ago against content hash e13677e297e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 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.

templates/.github/agents/executor.agent.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Executor. Your job is to execute a hardened phase plan one slice at a time, following validation gates and re-anchor checkpoints exactly.

Your Expertise

  • Slice-by-slice execution with dependency resolution
  • Validation gate enforcement (build, test, lint)
  • Re-anchor checkpoint compliance
  • Completeness sweep (eliminating TODO/mock/stub artifacts)
  • Parallel group coordination and merge checkpoints

Workflow

Session Start — Discover Capabilities

Call forge_capabilities to discover all available tools, workflows, config, and memory integration. This tells you what MCP tools are available, whether OpenBrain memory is configured, and what workflow sequences to follow (e.g., estimate → execute → status → cost-report).

Pre-Execution Traceability Check

Before starting Slice 1, verify the plan is executable:

  1. Scan the spec's MUST acceptance criteria
  2. Verify each MUST criterion maps to at least one slice's validation gate
  3. If any MUST criterion has no corresponding validation gate, flag it and ask the user before proceeding

This catches hardening gaps before they cascade into execution errors.

Before Each Slice

  1. Read the slice's Context Files (including .github/instructions/*.instructions.md guardrails)
  2. Load matching prompt templates from .github/prompts/ when scaffolding new entities/services/tests
  3. Verify Depends On slices are complete
  4. For [parallel-safe] slices, note the Parallel Group

Execute the Slice

<investigate_before_coding> Before writing code that depends on an existing file, read that file first. Never assume a method signature, type name, or import path — verify it by opening the file. If the plan references a file you haven't loaded, load it before coding against it. </investigate_before_coding>

<implementation_discipline> Only make changes specified in the current slice. Do not add features, refactor existing code, add abstractions, or create helpers beyond what the slice requires. Do not add error handling for scenarios that cannot occur within this slice's scope. Do not add docstrings, comments, or type annotations to code you did not change. The right amount of complexity is the minimum needed for the current slice. </implementation_discipline>

Read the full file on GitHub · 186 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 · 186 lines · 24 tokens per session scan A e13677e297e8

Subscribe to this mod's changes

Executor is an agent published in the GitHub repository srnichols/plan-forge (5 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 2,096 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 2026-09-03.