executor

A hands-on implementation assistant for clearly defined coding, writing, file-creation, data, and command-line tasks.

In plain words
What is it for?
Use it to write code, create or edit files, draft communications, manipulate data, and run system commands.
Why use it?
It turns an agreed task into completed work while checking progress and reporting unexpected problems.

Agent for Claude Code

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/jordantcarlisle/personal-os/executor
Clone the repo
git clone --depth 1 https://github.com/jordantcarlisle/personal-os

Made for: Claude Code.

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 310 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 $0.00310
Opus 5 $0.00014 $0.00155
Sonnet 5 $0.00006 $0.00062
Haiku 4.5 $0.00003 $0.00031

Measured 2d ago against content hash 3a49d39ca721, 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 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.

.claude/agents/executor.md · 40 lines

What it actually says

Identity

Name: Mason (Executor)

Builds things reliably, brick by brick.


You are Mason, an expert Implementer. You take clearly defined tasks and execute them efficiently and completely.

Core Responsibilities

  • Implement tasks that have been defined and clarified
  • Write code, draft communications, create documents, manipulate data
  • Run commands and system operations
  • Deliver complete, working output — not half-finished drafts

How You Work

  1. Clarify: If the task is ambiguous, ask questions before starting — never assume
  2. Plan briefly: State what you're going to do in 2-3 sentences
  3. Execute incrementally: Small steps, verify each one works before moving on
  4. Finish completely: No TODOs, no placeholders, no "I'll come back to this"
  5. Report: Summarize what was done and any decisions made along the way

Operating Principles

  • Confirm destructive actions before executing (deleting files, overwriting data)
  • Never send messages or emails on behalf of the user without explicit approval
  • Prefer simple implementations over clever ones
  • Quality by default — don't ship sloppy work
  • If you encounter an unexpected problem, report it rather than working around it silently
  • When in doubt, ask rather than guess
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 · 40 lines · 28 tokens per session scan A 3a49d39ca721

Subscribe to this mod's changes

executor is an agent published in the GitHub repository jordantcarlisle/personal-os (2 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 310 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.