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 skills add kellykampen/agent-skills --skill peekgit clone --depth 1 https://github.com/kellykampen/agent-skillsWrote 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/kellykampen/agent-skills/peek)<a href="https://agentmods.dev/skills/kellykampen/agent-skills/peek"><img src="https://agentmods.dev/badge/skills/kellykampen/agent-skills/peek/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/skills/kellykampen/agent-skills/peek"><img src="https://agentmods.dev/badge/skills/kellykampen/agent-skills/peek.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 | $0.00160 | $0.01926 |
| Opus 5 | $0.00080 | $0.00963 |
| Sonnet 5 | $0.00032 | $0.00385 |
| Haiku 4.5 | $0.00016 | $0.00193 |
Grade A, and why
peek 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 10d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
peek (fleet status reporting)
peek is a tiny, local, serverless CLI that makes an agent-orchestration fleet legible: each
agent reports its own status via peek update, which peek stores in a per-agent JSON file
behind the scenes; anyone above it in the hierarchy can read the tree instantly (via peek)
instead of capturing panes to guess what's alive. No server, no daemon — just files under
~/.peek/projects/<project-slug>/, which you never touch directly (see below).
The CLI is the only contract — never touch ~/.peek/ yourself
~/.peek/ is peek's private internal storage, not something you read, write, or inspect
directly. Always go through the CLI: peek update, peek, peek --all, peek watch,
peek web. Never cat/echo/hand-edit a file under ~/.peek/, and never glob it yourself
to "check" something — if you need to know the current state, run peek/peek --json, not a
filesystem read. This keeps the on-disk schema free to change without breaking every agent that
depends on it, keeps every write atomic/valid (the CLI validates; a hand-written JSON file
might not), and means you never have to know or care what the record shape actually is.
Are you set up to use it?
Setup is plain env exports, set once per session — there is no peek register command.
You export your identity a single time (at spawn, or once at session start if you're the
conductor); every peek update call after that is bare (just --task/--status/etc, never
re-exporting anything). Reading needs no identity at all — peek, peek --all, and
peek web all work with zero PEEK_* env vars set, for anyone just looking. Only writing
(peek update) requires your identity to already be exported.
You need four env vars, normally set by whatever spawned you (a launcher script, an
orchestrator's cast command, or your own boot sequence if you're the fleet's conductor):
| Var | What it is |
|---|---|
PEEK_ID |
Your own unique identifier |
PEEK_ROLE |
conductor, orchestrator, or worker |
PEEK_PARENT |
Your parent's PEEK_ID (omit only if you're conductor) |
PEEK_WORKSPACE |
Your project's computed slug (omit only if you're conductor — see below) |
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.
- 10d ago First seen · 129 lines · 160 tokens per session scan A e4222c009eac
peek is a skill published in the GitHub repository kellykampen/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 160 tokens to every session and 1,926 once invoked, about $0.0008 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
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…