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.
npx agentmods add skills/emilvaintrub/showrunner/showrunnernpx skills add emilvaintrub/ShowRunner --skill showrunnergit clone --depth 1 https://github.com/emilvaintrub/ShowRunnerWrote 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.
[](https://agentmods.dev/skills/emilvaintrub/showrunner/showrunner)<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>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 | $0.00080 | $0.01010 |
| Opus 5 | $0.00040 | $0.00505 |
| Sonnet 5 | $0.00016 | $0.00202 |
| Haiku 4.5 | $0.00008 | $0.00101 |
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.
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.
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 beforemain.sentry: sweep and secure; preserve accepted-risk memory; stop beforemain.bible: synthesize the architecture and capabilities document from the repository, Forge spec, Arc reports, and Sentry posture; read-only over the product; stop beforemain.
Route
- Read the active project's
.claude/showrunner/config.md. - If it is missing, run the requested skill's
initflow before other work. - Load core/method.md for every command.
- Load only the requested skill's
SKILL.mdandmethod.md. - For dispatched work, also load core/dispatch.md.
- For implementation or fixes that produce code, also load core/tdd.md and core/debugging.md.
- For verification or merge, load core/merge.md.
- For hook setup or diagnosis, load core/commit-hooks.md.
- When
context_optimizer.enabledis 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 initand/forge discover; blockplan|spec|decide|designuntil initialization is completed.disabled: reject Forge commands until the project explicitly enables it.
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.
- agents/openai.yaml 186 B
- arc/agents/openai.yaml 195 B
- arc/method.md 13 KB
- arc/SKILL.md 2.2 KB
- arc/templates/impl-prompt.md 4.1 KB
- arc/templates/merge.md 836 B
- arc/templates/questions.md 782 B
- arc/templates/ship-report.md 2.0 KB
- arc/templates/spec.md 1.8 KB
- bible/agents/openai.yaml 264 B
- bible/method.md 8.7 KB
- bible/SKILL.md 2.6 KB
- bible/templates/bible.md 2.4 KB
- bible/templates/merge.md 1.2 KB
- core/commit-hooks.md 2.1 KB
- core/config.schema.md 13 KB
- core/context-hygiene.md 2.1 KB
- core/debugging.md 1.9 KB
- core/dispatch.md 4.5 KB
- core/merge.md 3.9 KB
- core/method.md 8.9 KB
- core/tdd.md 1.3 KB
- core/testing-anti-patterns.md 2.2 KB
- forge/agents/openai.yaml 194 B
- forge/method.md 13 KB
- forge/SKILL.md 2.1 KB
- forge/templates/adapters/figma-make.md 2.0 KB
- forge/templates/adapters/v0.md 1.8 KB
- forge/templates/decision.md 625 B
- forge/templates/designer-brief.md 8.1 KB
- forge/templates/project.md 840 B
- forge/templates/questions.md 889 B
- forge/templates/soul.md 1.1 KB
- forge/templates/spec.md 3.0 KB
- gates/audit.md 1.8 KB
- gates/wow-check.md 2.5 KB
- scripts/hooks/commit-msg 1.0 KB
- scripts/hooks/showrunner-commit-prefixes 55 B
- scripts/install-hooks.ps1 3.0 KB runs code
- sentry/agents/openai.yaml 238 B
- sentry/knowledge/accepted-risks.md 745 B
- sentry/knowledge/catalog.md 6.4 KB
- sentry/knowledge/severity-rubric.md 850 B
- sentry/knowledge/standards.md 3.2 KB
- sentry/method.md 14 KB
- sentry/pen-test/agents/openai.yaml 204 B
- sentry/pen-test/assets/cleanup.md 597 B
- sentry/pen-test/assets/coverage-ledger.md 959 B
- sentry/pen-test/assets/finding.md 806 B
- sentry/pen-test/assets/report.md 1013 B
- sentry/pen-test/assets/retest.md 412 B
- sentry/pen-test/assets/rules-of-engagement.md 1.1 KB
- sentry/pen-test/assets/scope-manifest.md 1.1 KB
- sentry/pen-test/assets/test-plan.md 629 B
- sentry/pen-test/method.md 5.5 KB
- sentry/pen-test/references/authorization.md 2.3 KB
- sentry/pen-test/references/coverage.md 2.2 KB
- sentry/pen-test/references/profiles.md 2.8 KB
- sentry/pen-test/references/validation.md 1.6 KB
- sentry/pen-test/schemas/catalog.schema.json 996 B
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.
- 4d ago First seen · 93 lines · 80 tokens per session scan A 799e511e268c
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.
Other skills, from other repositories
testing-strategy
Selects the narrowest sufficient test boundary from requirements, repository evidence, and maintenance cost. Use when deciding integration or E2E coverage.
documentation-criteria
Determines which PRD, ADR, Design Doc, and Work Plan a change requires. Use when deciding documentation scope or creating technical documents.
ai-development-guide
Applies root-cause analysis, impact inspection, and completeness checks without expanding approved scope. Use when fixing bugs, refactoring, reviewing quality, or resolving unexpected implementation evidence.
testing
Applies repository-aware TDD, observable test design, and applicable quality checks. Use when changing behavior, writing tests, or reviewing test quality.
coding-rules
Applies repository-aware rules for maintainable implementation, contracts, errors, and refactoring. Use when writing or modifying code.
implementation-approach
Selects the smallest sufficient implementation strategy and verification boundary from current requirements and repository evidence.