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 instructions/t0mtaylor/peepshow/agents-mdgit clone --depth 1 https://github.com/t0mtaylor/peepshowWrote 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/t0mtaylor/peepshow/agents-md)<a href="https://agentmods.dev/instructions/t0mtaylor/peepshow/agents-md"><img src="https://agentmods.dev/badge/instructions/t0mtaylor/peepshow/agents-md.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 | $0.00889 | $0.00889 |
| Opus 5 | $0.00445 | $0.00445 |
| Sonnet 5 | $0.00178 | $0.00178 |
| Haiku 4.5 | $0.00089 | $0.00089 |
Grade A, and why
peepshow 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 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — peepshow
Generic agent context file. Consumed by Codex CLI, OpenAI Agents, Zed AI, and any tool that follows the AGENTS.md convention.
What peepshow is
CLI tool that turns videos and animated images (GIF/APNG/animated WebP) into a timeline of still frames + an extracted audio track + optional whisper.cpp / openai / groq / deepgram / assemblyai transcript, so an LLM can "watch" and "listen" to what's inside. Installed via npm i -g peepshow. Published at https://www.npmjs.com/package/peepshow.
When to invoke it
Trigger — user references a local file path, HTTP(s) URL, or data URI whose target is a video or animated image. Common extensions: mp4 mov mkv webm avi flv wmv ts mts m2ts 3gp ogv gif apng.
Don't fire for static images (png jpg jpeg static-webp) — LLMs already read those natively.
How to invoke
Preferred, most robust (structured JSON output; includes video metadata + tags):
peepshow "<path-or-url>" --emit json
Parse the stdout JSON:
frames[]— ordered frame paths (chronological).video— container, codec, resolution, fps, duration, size, plustags(title, director, producer, etc).extraction— strategy used (scenevsfps), ffmpeg source, elapsed ms. PlusframesDeduped+dedupDistance(perceptual-hash post-pass, 8×8 dHash, default-on), andmotionSignalAvg+motionSignalLevel(low/medium/high) — average pairwise hamming across kept frames. Use the motion signal to colour narration; high motion +framesDeduped == 0means every frame is genuinely distinct.
Read each frames[i].path as an image. Ground your answer in video.tags before describing frames.
Annotate the report after reading
Each run also writes report.html + manifest.json into outputDir. After you've understood the frames + transcript, pipe a JSON summary back so the report captures your synthesis for whoever opens it later:
echo '{"summary":"<2-4 sentences>","provider":"<your-tool-name>"}' \
| peepshow report annotate "<outputDir>"
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 · 64 lines · 889 tokens per session scan A 383ea00ed610
peepshow AGENTS.md is an instructions file published in the GitHub repository t0mtaylor/peepshow (67 stars, last pushed 3mo ago), licensed MIT. It adds 889 tokens to every session, about $0.0044 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 2026-08-30.
Other instructions, from other repositories
linkedin-content-engine CLAUDE.md
Claude Code instructions for mdbailin/linkedin-content-engine, covering claude implementation brief, goal, architecture constraints, required mcp tools and readbrandprofile.
carousels GEMINI.md
Instructions for sausi-7/carousels: See AGENTS.md for the full pipeline, commands and file shapes.
docvideoer CLAUDE.md
Instructions for coding-ax/docvideoer, covering claude.md — docvideoer, 触发方式, 外部 skill 依赖, 工作目录 and 核心流水线（6 步）.
ai-workflow-kit CLAUDE.md
Claude Code instructions for bezael/ai-workflow-kit, covering claude.md — ai workflow kit, what this repo is, where each tool reads skills from, available skills and specialized agents.
video-mcp CLAUDE.md
Claude Code instructions for Zoean-z/video-mcp, a project described as: 让agent学会理解视频，无需复杂依赖和额外花费.
glm-image-mcp-server CLAUDE.md
Claude Code instructions for ex-takashima/glm-image-mcp-server, covering claude.md - development guide, project overview, build & run commands, install dependencies and build typescript.