arc

arc is a skill for Claude Code, Codex from emilvaintrub/ShowRunner. It costs 73 tokens per session (489 once invoked), scanned A, original, MIT.

A workflow for turning an approved software direction into tested branch work. It plans changes, sends the plan to an isolated implementer, reviews the result, and stops before merging it into the main branch.

In plain words
What is it for?
For initializing repository conventions, planning approved features, dispatching implementation work, verifying a feature branch, and preparing an explicitly approved merge.
Why use it?
It separates planning, implementation, review, and merging so unfinished or unsuitable work does not enter the main codebase automatically. It also requires product or scope decisions to be escalated when evidence cannot resolve them.

Skill for Claude CodeCodex

Part of the showrunner plugin — 6 skills shipped together

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 skills/emilvaintrub/showrunner/arc
Any agent
npx skills add emilvaintrub/ShowRunner --skill arc
Clone the repo
git clone --depth 1 https://github.com/emilvaintrub/ShowRunner

Made for: Claude Code, Codex.

Or install showrunner, the plugin that ships this one along with the rest of its 6 skills.

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 arc

README.md
[![agentmods](https://agentmods.dev/badge/skills/emilvaintrub/showrunner/arc.svg)](https://agentmods.dev/skills/emilvaintrub/showrunner/arc)
Your own site
<a href="https://agentmods.dev/skills/emilvaintrub/showrunner/arc"><img src="https://agentmods.dev/badge/skills/emilvaintrub/showrunner/arc.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 489 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 $0.00073 $0.00489
Opus 5 $0.00036 $0.00244
Sonnet 5 $0.00015 $0.00098
Haiku 4.5 $0.00007 $0.00049

Measured 4d ago against content hash 0bdcdc2a1153, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

arc 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 4d 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.

showrunner/arc/SKILL.md · 49 lines

What it actually says

Arc

Turn approved direction into verified branch work. Resolve conventions from evidence, escalate product or scope calls, and never merge automatically.

Load

  1. Read ../core/method.md.
  2. Read the active project's .claude/showrunner/config.md.
  3. Read method.md.
  4. For run, load ../core/dispatch.md.
  5. For verify or merge, load ../core/merge.md.
  6. Load only the templates required by the requested command.

Route

  • init: inspect repository mechanics and fill the Arc config section.
  • plan: consume approved direction, resolve conventions, and render an implementation prompt.
  • run: execute plan, dispatch a cold implementer, review Step 0, collect evidence, and stop before merge.
  • verify: independently review the exact feature tip and issue SHIP, FIX, or REDESIGN.
  • merge: after SHIP, required smoke, and explicit approval, execute the shared two-commit ceremony.

Use templates/questions.md for human decisions, templates/spec.md for Arc-owned planning, templates/impl-prompt.md for dispatch, templates/ship-report.md for completion, and templates/merge.md for merge readiness.

Hard Stops

  • Never rewrite approved Forge sections 1-8 while consuming sections 9-11.
  • Never dispatch before the front-loaded decision gate resolves.
  • Never authorize edits before Step 0 approval.
  • Never widen scope silently.
  • Never accept static inspection as required physical or operational smoke.
  • Never issue SHIP without binding the verdict to the exact feature tip.
  • Never merge without independent SHIP, required smoke, and explicit human approval.
  • Never import facts or wording from another project.
Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 49 lines · 73 tokens per session scan A 0bdcdc2a1153

Subscribe to this mod's changes

arc is a skill published in the GitHub repository emilvaintrub/ShowRunner (2 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 489 once invoked, about $0.0004 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.