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/t0mtaylor/peepshow/sinknpx skills add t0mtaylor/peepshow --skill sinkgit 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/skills/t0mtaylor/peepshow/sink)<a href="https://agentmods.dev/skills/t0mtaylor/peepshow/sink"><img src="https://agentmods.dev/badge/skills/t0mtaylor/peepshow/sink.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 5.1 | $0.00062 | $0.00793 |
| Opus 5 | $0.00031 | $0.00396 |
| Sonnet 5 | $0.00012 | $0.00159 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
sink 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 6d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sink management
peepshow supports auto-sinks — persistent sink definitions in ~/.peepshow/sinks.json that run on every extract. This skill manages that list on the user's behalf.
Detect intent
| User says | Run |
|---|---|
| "list sinks" / "which sinks are active" / "show sinks" | peepshow sinks list |
| "enable folder sink at /Volumes/Shared" / "add folder sink" | peepshow sinks add folder:/Volumes/Shared |
| "enable mysql sink" | peepshow sinks add mysql (reminder: sink needs DATABASE_URL in env) |
| "add custom sink: " | peepshow sinks add-cmd '<command>' |
| "add X but only for .mp4/.mov files" | peepshow sinks add <spec> --when extension=mp4,mov |
| "add X for videos under /Videos/" | peepshow sinks add <spec> --when path=/Videos/ |
| "add X for films directed by Kubrick" | peepshow sinks add <spec> --when director=Kubrick |
| "add X when filename matches vacation" | peepshow sinks add <spec> --when filename='*vacation*' |
| "remove sink 2" / "disable the mysql one" | First peepshow sinks list, then peepshow sinks remove <n> |
| "clear all sinks" / "disable all sinks" | peepshow sinks clear |
| "turn off sinks for this video only" | Tell the user to pass --no-auto-sinks on the next invocation — do not touch the config |
Notes
- Always run
peepshow sinks listafter any mutation to confirm the new state. <name>maps to an executablepeepshow-sink-<name>on$PATH. Extra colon-separated tokens become positional args (folder:/tmp/shared→peepshow-sink-folder /tmp/shared).- The sink count is shown live in the Claude Code statusline badge, e.g.
[PEEPSHOW|3s]means three auto-sinks are active. - Sinks receive the full peepshow JSON payload on stdin (including container tags: title, director, producer, copyright, etc.) — mention this when the user is choosing what to persist.
- Conditional matching (
--when): extension/filename/path/container/codec + any video metadata tag (director, genre, show, producer, publisher, …). Multiple--whenflags AND together; values inside one clause (e.g.ext=mp4,mov) are ORed. Example:peepshow sinks add folder:/cinema --when director=Kubrick --when extension=mp4= "archive Kubrick mp4s only".
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.
- 6d ago First seen · 37 lines · 62 tokens per session scan A 379dec502ff4
sink is a skill published in the GitHub repository t0mtaylor/peepshow (67 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 793 once invoked, about $0.0003 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…