Borrowing it
Nothing to install: this file belongs to khou/showrunner. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/khou/showrunner/main/AGENTS.mdgit clone --depth 1 https://github.com/khou/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/instructions/khou/showrunner/agents-md)<a href="https://agentmods.dev/instructions/khou/showrunner/agents-md"><img src="https://agentmods.dev/badge/instructions/khou/showrunner/agents-md/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.
<a href="https://agentmods.dev/instructions/khou/showrunner/agents-md"><img src="https://agentmods.dev/badge/instructions/khou/showrunner/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00305 | $0.00305 |
| Opus 5.5 | $0.00122 | $0.00122 |
| Sonnet 5.5 | $0.00061 | $0.00061 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
showrunner AGENTS.md 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 2mo 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.
What it actually says
Learned User Preferences
- Prefer dual-token auth: a shareable/commitable worker token so remote agents can join without cloud secrets; keep the director token secret and alone able to claim direction or mutate admin APIs.
showrunner initshould write the director token to.env, document worker registration from committed showrunner/MCP files, and keep README/SETUP examples aligned.- Onboard may guide optional role specialization via show rules (dedicated workers for art, local tools, etc.) when the user wants that pattern.
- Leave subagent fan-out to workers; directors may nudge workers to use their own subagents without over-documenting ownership mechanics.
- For cross-user worker shows, prefer hard security boundaries beyond protocol rules (identity, admission gates, runtime posture); server-held rules should be mutable only with the director token.
- Keep README, SETUP, and agent-facing instructions in sync whenever the auth or security model changes.
- Product changes belong in the showrunner repo; consumer projects should re-init rather than hand-patching old scaffolding.
Learned Workspace Facts
- Auth uses
SHOWRUNNER_TOKEN(director) andSHOWRUNNER_WORKER_TOKEN(worker); the worker token is intended to be shareable/committable for remote agents. - The maintainer's production Fly app is separate from consumer project Fly apps; names and secrets do not collide.
- Worker role specialization is expressed through show rules, not by showrunner owning or routing subagents.
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.
- 2mo ago First seen · 16 lines · 305 tokens per session scan A d5242d09301f
showrunner AGENTS.md is an instructions file published in the GitHub repository khou/showrunner (1 stars, last pushed 4mo ago), licensed MIT. It adds 305 tokens to every session, about $0.0012 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.
showrunner AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| showrunner AGENTS.mdkhou/showrunner | Instructions file | 1 | 4mo ago | MIT | A | 305 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |