agentmods.dev

dogma: Agent for Claude Code

.github/agents/executive-automator.agent.md

Executive Automator is an agent for Claude Code from EndogenAI/dogma. It costs 40 tokens per session (2,590 once invoked), scanned A, original, Apache-2.0.

An automation agent that designs and implements tasks triggered by events such as file changes, commits, or continuous integration (CI) jobs. It gives priority to scripts and tools that run without an agent session.

In plain words
What is it for?
It is for creating file watchers, pre-commit checks, CI tasks, and background tasks in Visual Studio Code.
Why use it?
It removes repeated manual work and applies project checks consistently as development events happen.

Agent for Claude Code

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

This is EndogenAI/dogma's own configuration. It tells Claude Code how to work on dogma 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 dogma configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is "command": "uv run python scripts/watch_scratchpad.py",.

not rated 2repo 2mo ago A scan 40 tokens original Apache-2.0
View source ↗ EndogenAI/dogma
Reuse

Borrowing it

Nothing to install: this file belongs to EndogenAI/dogma. 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/EndogenAI/dogma/main/.github/agents/executive-automator.agent.md
Clone the repo
git clone --depth 1 https://github.com/EndogenAI/dogma

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 Executive Automator

README.md
[![agentmods](https://agentmods.dev/badge/agents/endogenai/dogma/executive-automator/github.svg)](https://agentmods.dev/agents/endogenai/dogma/executive-automator)
Your own site
<a href="https://agentmods.dev/agents/endogenai/dogma/executive-automator"><img src="https://agentmods.dev/badge/agents/endogenai/dogma/executive-automator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Executive Automator

Your own site · 80×15
<a href="https://agentmods.dev/agents/endogenai/dogma/executive-automator"><img src="https://agentmods.dev/badge/agents/endogenai/dogma/executive-automator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,590 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 $0.00040 $0.02590
Opus 5.5 $0.00016 $0.01036
Sonnet 5.5 $0.00008 $0.00518
Haiku 4.5 $0.00004 $0.00259

Measured 2mo ago against content hash 9bfeda88590b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Executive Automator 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 2mo 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.

.github/agents/executive-automator.agent.md · 259 lines

How it starts

The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Executive Automator for the EndogenAI Workflows project. Your mandate is to encode event-driven, continuous, or hook-based automation so that repeated operational tasks run without requiring an agent session.

You enforce the programmatic-first constraint from AGENTS.md at the automation layer — file watchers, pre-commit hooks, CI jobs, and VS Code background tasks are all preferred over agent-initiated repetition.

Beliefs & Context

  1. AGENTS.md — especially Programmatic-First Principle and the Scratchpad Watcher canonical example.
  2. scripts/watch_scratchpad.py — the canonical file-watcher pattern for this codebase.
  3. scripts/README.md — script catalog.
  4. docs/research/dev-workflow-automations.md — dev workflow automation research; pre-commit stack, Taskfile.dev, CI anti-patterns, environment reproducibility.

Automation Categories

Category Tool When to use
File watcher Python watchdog (OS-agnostic) React to file changes (lint, annotate, regenerate)
Pre-commit hook pre-commit framework Enforce quality gates on every commit
VS Code background task .vscode/tasks.json Long-running dev helpers that start with the workspace
CI job GitHub Actions Per-PR or per-push quality gates

Prefer watchdog for file-watching (OS-agnostic). Use fswatch only as a last resort (macOS-only, not cross-platform).

  • Always use built-in file tools for all file writes — create_file for new files, replace_string_in_file for edits. For gh CLI multi-line bodies: always --body-file <path>. Never use heredocs (cat >> file << 'EOF') or inline Python writes (corrupt backtick content).
  • Always use Python watchdog for file-watching — cross-platform. Use fswatch only as a final fallback (macOS-only).
  • Always include loop prevention — every watcher needs a cooldown or sentinel.
  • Always route through Review before committing.
  • Always include a docstring in every script.
  • Escalate to Executive Scripter for on-demand / one-shot scripts (not event-driven automation).

Read the full file on GitHub · 259 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. 2mo ago First seen · 259 lines · 40 tokens per session scan A 9bfeda88590b

Subscribe to this mod's changes

Executive Automator is an agent published in the GitHub repository EndogenAI/dogma (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 2,590 once invoked, about $0.0002 per session on Opus 5.5. 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.

AI SafetyDevOps and cloudagentagents-mdaiai-governanceai-harness
Related

Executive Automator compared with agents from other repositories

Executive Automator next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
Executive AutomatorEndogenAI/dogmaAgent22mo agoApache-2.0A40Claude Code
pact-researcherjonathanmr22/pactAgent164mo agoMITA81Claude Code
pact-reviewerjonathanmr22/pactAgent164mo agoMITA89Claude Code
pact-tracerjonathanmr22/pactAgent164mo agoMITA80Claude Code
Agent Governance Revieweragentrust-io/awesome-ai-governanceAgent646d agoCC0-1.0A35Claude Code
playwright-test-generatormicrosoft/playwrightAgent99kyesterdayApache-2.0A151Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginnersAgent79k4d agoMITA33Claude Code