showrunner

showrunner is a skill for Claude Code, Codex from emilvaintrub/ShowRunner. It costs 80 tokens per session (1,010 once invoked), scanned A, original, MIT.

A project workflow that routes software work through four stages: planning, implementation, security review, and documentation.

In plain words
What is it for?
Planning features, implementing approved specifications in isolation, checking code for security issues, and producing an architecture and capabilities document.
Why use it?
It gives an AI coding agent a shared, configuration-based process for moving work from an idea to verified changes while stopping before merging.

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/showrunner
Any agent
npx skills add emilvaintrub/ShowRunner --skill showrunner
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 showrunner

README.md
[![agentmods](https://agentmods.dev/badge/skills/emilvaintrub/showrunner/showrunner.svg)](https://agentmods.dev/skills/emilvaintrub/showrunner/showrunner)
Your own site
<a href="https://agentmods.dev/skills/emilvaintrub/showrunner/showrunner"><img src="https://agentmods.dev/badge/skills/emilvaintrub/showrunner/showrunner.svg" alt="Measured on agentmods" height="20"></a>
Per session 80 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,010 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 $0.00080 $0.01010
Opus 5 $0.00040 $0.00505
Sonnet 5 $0.00016 $0.00202
Haiku 4.5 $0.00008 $0.00101

Measured 4d ago against content hash 799e511e268c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

showrunner 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/install-hooks.ps1), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Showrunner

Run one lifecycle with four policies:

  • forge: conceive with the inventor; recommend, ask, then write directions.
  • arc: build autonomously through verification; stop before main.
  • sentry: sweep and secure; preserve accepted-risk memory; stop before main.
  • bible: synthesize the architecture and capabilities document from the repository, Forge spec, Arc reports, and Sentry posture; read-only over the product; stop before main.

Route

  1. Read the active project's .claude/showrunner/config.md.
  2. If it is missing, run the requested skill's init flow before other work.
  3. Load core/method.md for every command.
  4. Load only the requested skill's SKILL.md and method.md.
  5. For dispatched work, also load core/dispatch.md.
  6. For implementation or fixes that produce code, also load core/tdd.md and core/debugging.md.
  7. For verification or merge, load core/merge.md.
  8. For hook setup or diagnosis, load core/commit-hooks.md.
  9. When context_optimizer.enabled is true, load core/context-hygiene.md before long plans, dispatched work, broad Sentry sweeps, Bible syncs, or post-compaction resumes.

Commands

The suite routes these command families:

  • /forge init|discover|plan|spec|decide|design
  • /arc init|plan|run|verify|merge
  • /sentry init|sweep|fix|verify|accept|deps|pen-test|monthly|refresh-knowledge|merge
  • /bible init|sync|merge

If a requested skill package is absent, report that the runtime command is not available; do not reconstruct it from memory and claim it is available.

Forge is available when forge/SKILL.md exists. Route by status:

  • ready: allow every Forge command.
  • uninitialized: allow /forge init and /forge discover; block plan|spec|decide|design until initialization is completed.
  • disabled: reject Forge commands until the project explicitly enables it.

Read the full file on GitHub · 93 lines

Files

What ships with it

60 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 · 93 lines · 80 tokens per session scan A 799e511e268c

Subscribe to this mod's changes

showrunner is a skill published in the GitHub repository emilvaintrub/ShowRunner (2 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 1,010 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.