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

Planning features, implementing approved specifications in isolation, checking code for security issues, and producing an architecture and capabilities document.

It gives an AI coding agent a shared, configuration-based process for moving work from an idea to verified changes while stopping before merging.

showrunner — Skill for Claude Code and Codex by emilvaintrub

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.

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 7 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/emilvaintrub/showrunner/showrunner/github.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/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/emilvaintrub/showrunner/showrunner"><img src="https://agentmods.dev/badge/skills/emilvaintrub/showrunner/showrunner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 212 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,358 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.

Model	Per session	Once invoked
Fable 5.1	$0.00212	$0.02358
Opus 5.5	$0.00085	$0.00943
Sonnet 5.5	$0.00042	$0.00472
Haiku 4.5	$0.00021	$0.00236

Measured today against content hash 07243673615b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 today.

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 · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ShowRunner

ShowRunner is the conductor. The owner brings the idea and the business calls; ShowRunner runs every stage from first request to release, in order, without waiting to be told the next step. It stops only where the owner must decide or supply something, and it never skips a stage on its own.

Every Turn

Load core/lifecycle.md and core/method.md.
Read .claude/showrunner/config.md and the state ledger it names in lifecycle.state_file (default .claude/showrunner/state.md; core/state.md). No config means the current stage is setup.
When active.autonomy is high or run, load core/autonomy.md before running or reporting on any stage from arc-plan to close. It changes what each owner stop contains, so never answer from core/lifecycle.md alone.
Run showrunner check when the enforcement script is installed (core/enforcement.md); fix ledger errors before anything else.
Classify the owner's message (lifecycle section 4). A request is never executed outside its stage, however small.
Run the current stage with the files it needs (below).
On exit, append the ledger row, advance, and start the next stage in the same turn when ShowRunner owns it.
End with the handoff block (lifecycle section 6).

Stage Loading

Stage	Load
`setup`	core/ownership.md and core/templates/accounts-register.md, every present policy's `SKILL.md` and `method.md` (`init`), core/config.schema.md, core/commit-hooks.md, core/enforcement.md, core/templates/state.md
`discovery`, `assessment`	forge/SKILL.md, forge/discovery.md, forge/knowledge/inquiry-bank.md, core/evidence.md, the stage's template
`business-docs`	pitch/SKILL.md, pitch/method.md, core/evidence.md, the document's template
`constitution`, `roadmap`, `spec`, `design`, `design-review`, `handoff`	forge/SKILL.md, forge/method.md, the command's template, gates/wow-check.md for GATE-OUT when enabled; for `roadmap`, also forge/discovery.md section 5
`handoff` (level choice), and `arc-plan` through `close`	core/autonomy.md
`arc-plan`, `step0`, `build`	arc/SKILL.md, arc/method.md, core/dispatch.md, core/tdd.md, core/debugging.md
`verify`	Arc files above, core/merge.md, gates/audit.md, gates/wow-check.md for UI work when enabled
`security`	sentry/SKILL.md, sentry/method.md, sentry/knowledge/catalog.md
`acceptance`, `merge`	core/merge.md, the policy's merge template, core/autonomy.md; at Run also the ship report (its ShowRunner decisions section and smoke) and the security sweep report, because the end gate quotes them
`release`	core/release.md, core/ownership.md, core/autonomy.md
`close`	bible/SKILL.md, bible/method.md, core/merge.md, core/outcomes.md
any stage, when an outcome review is due	core/outcomes.md
any stage, when production is broken or harmful now	core/incident.md
`setup` on an existing product, or when the owner needs rescue or direction mid-development	core/adoption.md, then the Bible and Sentry files for the inventory
any stage, when the owner shares customer feedback	core/feedback.md, core/templates/feedback-log.md
`close`, and whenever a budget is set	core/cost.md
any stage, before spawning an agent (implementer, sweep, auditor, research or inventory helper)	core/models.md

Read the full file on GitHub · 136 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.

today Changed · +10 lines · +55 tokens per session 07243673615b
28d ago Changed · +4 lines 24e2a3288e51
1mo ago Changed · +7 lines 703adff15325
1mo ago Changed · +22 lines · +77 tokens per session 04a25078b3c6
2mo 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 yesterday), licensed MIT. It adds 212 tokens to every session and 2,358 once invoked, about $0.0008 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.

Claude Code Planning Security agentic-workflow ai-agents codex cursor

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation. Continuation mode: infer requirements, state assumptions, propose design in one message — no Q&A loop.

chadixearth/graphyloop · 58 tokens

ai-video-prompt-engineer

Use when the user wants to create AI video generation prompts for a brand, product, website, or topic. Includes interactive Q&A flow to gather requirements then outputs a single unified prompt (one paste) for tools like OmniFlash, Runway, Pika, Kling, Sora. Do NOT use for HyperFrames/Remotion video creation workflows.

chadixearth/graphyloop · 77 tokens

frontend-security

Use this skill when writing or reviewing client-side code that renders user data, stores tokens, calls an API, or embeds third-party scripts - React/Next/Vue/Svelte or plain DOM. Covers XSS sinks, token storage, environment-variable leakage, CSP and security headers, iframe and postMessage trust, and the checks that…

chadixearth/graphyloop · 80 tokens

api-contract-design

Use this skill when freezing the interface between a backend and its clients before parallel work starts, or when changing an endpoint other code already calls - request/response shapes, status codes, error envelope, pagination, filtering, idempotency, versioning, and the breaking-change rules. Covers writing the…

chadixearth/graphyloop · 79 tokens

dependency-audit

Use this skill before adding a dependency, when an audit or Dependabot alert fires, or when a lockfile changes in a review - triaging CVEs by real reachability, spotting typosquats and install scripts, pinning and lockfile discipline, and license checks. Covers deciding what actually needs fixing instead of chasing…

chadixearth/graphyloop · 74 tokens

graphyloop-waves

Use this skill when a request spans more than one layer (database + backend + frontend, or a feature plus a data pipeline). Turns the request into contract-first parallel waves with enforced dependencies, exclusive file ownership and per-lane acceptance checks, using the graphyloop planner and swarm.

chadixearth/graphyloop · 63 tokens