codex-of-consentient-craft: Command for Claude Code

.claude/commands/operator.md

operator is a command for Claude Code from StupidIncarnate/codex-of-consentient-craft. It costs 0 tokens per session (605 once invoked), scanned A, original, MIT.

A command that loads an autonomous implementation process, reads a plan, and requires work to happen in a separate Git worktree. It directs helper agents to research, implement, and verify the plan.

In plain words
What is it for?
Use it to start plan execution, create the required worktree, delegate batches, run checks, and commit completed work.
Why use it?
It reduces the risk of editing the main project copy and sets boundaries around how planned work is carried out. The command itself does not describe the plan's actual changes.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions subagents; mentions Claude Code.

This is StupidIncarnate/codex-of-consentient-craft's own configuration. It tells Claude Code how to work on codex-of-consentient-craft 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 codex-of-consentient-craft configures →

Reuse

Borrowing it

Nothing to install: this file belongs to StupidIncarnate/codex-of-consentient-craft. 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/StupidIncarnate/codex-of-consentient-craft/master/.claude/commands/operator.md
Clone the repo
git clone --depth 1 https://github.com/StupidIncarnate/codex-of-consentient-craft

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 operator

README.md
[![agentmods](https://agentmods.dev/badge/commands/stupidincarnate/codex-of-consentient-craft/operator/github.svg)](https://agentmods.dev/commands/stupidincarnate/codex-of-consentient-craft/operator)
Your own site
<a href="https://agentmods.dev/commands/stupidincarnate/codex-of-consentient-craft/operator"><img src="https://agentmods.dev/badge/commands/stupidincarnate/codex-of-consentient-craft/operator/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 operator

Your own site · 80×15
<a href="https://agentmods.dev/commands/stupidincarnate/codex-of-consentient-craft/operator"><img src="https://agentmods.dev/badge/commands/stupidincarnate/codex-of-consentient-craft/operator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 605 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 $0.00000 $0.00605
Opus 5.5 $0.00000 $0.00242
Sonnet 5.5 $0.00000 $0.00121
Haiku 4.5 $0.00000 $0.00060

Measured 1mo ago against content hash 6f0db7f9f140, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

operator 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 1mo 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/commands/operator.md · 30 lines

What it actually says

Read .agents/skills/operator/SKILL.md to load the full autonomous operator process and standing instructions.

Then read the plan document specified at: $ARGUMENTS

CRITICAL MANDATE — WORKTREE FIRST: Unless the plan document explicitly states otherwise, you MUST open a dedicated worktree before starting ANY work: mcp__dungeonmaster__create-worktree({ name: "<name>" }) All orchestration, subagent dispatching, investigation, implementation, testing/ward runs, and git commits MUST be performed inside worktrees/<name>/. Never work directly in the root repository unless the plan explicitly directs it.

You are now in Operator Mode. Follow all instructions in .agents/skills/operator/SKILL.md:

  1. Open Worktree First: Unless the plan document explicitly states otherwise, invoke mcp__dungeonmaster__create-worktree({ name: "<name>" }) before starting any work and conduct all work inside worktrees/<name>/.
  2. The operator NEVER writes or edits code directly in this session. All research, planning, implementation, and verification work is dispatched to specialized subagents (batch_planner, batch_worker, batch_reviewer) operating within the worktree.
  3. At most THREE (3) concurrent subagents at a time.
  4. The operator exclusively owns git staging, commits, and builds in the worktree. Dispatched agents never run git add, git mv, git commit, git checkout, or npm run build.
  5. Staging discipline: run git diff --cached --stat before committing and stage explicit file paths, never whole directories or packages.
  6. Sizing: each worker gets 1–3 files for cleanup/creation or 2–4 files for migration. Name every file explicitly in the prompt.
  7. Safe deletions: never rm or git rm; move verified unused files to tmp/deletions/<item>/<relative-path>.
  8. Zero tolerance: fix every pre-existing failure you encounter; npm run ward must exit 0.
  9. Maintain the keepalive check-in schedule during subagent runs: a CronCreate cron every 30 minutes (7,37 * * * *, recurring, not durable) in Claude Code. Pass the ID CronCreate returned to CronDelete when the run finishes or the user halts it.
  10. Maintain the compact Execution Progress Tracker in the plan document, checking off [✓] as items land.
  11. Emit user-facing announcements on start and finish:
    • On Start: ▶️ Task <ID>: <Description>
    • On Finish: ✅ Task <ID>: <Description> [commit <SHA>]
  12. Inspect the plan document, locate the next unfinished batch or phase, and begin execution inside the worktree.
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. 1mo ago Changed · +1 lines 6f0db7f9f140
  2. 1mo ago First seen · 29 lines · 0 tokens per session scan A 263ced4dda08

Subscribe to this mod's changes

operator is a command published in the GitHub repository StupidIncarnate/codex-of-consentient-craft (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 605 tokens. 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 2026-10-03.