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/dan-rozhkov/pen-editor-plugin/pen-editor-setupnpx skills add dan-rozhkov/pen-editor-plugin --skill pen-editor-setupgit clone --depth 1 https://github.com/dan-rozhkov/pen-editor-pluginWrote 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/dan-rozhkov/pen-editor-plugin/pen-editor-setup)<a href="https://agentmods.dev/skills/dan-rozhkov/pen-editor-plugin/pen-editor-setup"><img src="https://agentmods.dev/badge/skills/dan-rozhkov/pen-editor-plugin/pen-editor-setup.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 | $0.00067 | $0.02698 |
| Opus 5 | $0.00034 | $0.01349 |
| Sonnet 5 | $0.00013 | $0.00540 |
| Haiku 4.5 | $0.00007 | $0.00270 |
Grade B, and why
pen-editor-setup scanned grade B with 1 finding 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
3. `~/.pen-editor/mcp.json` — a handshake file two different servers can write to the same path/shape (`{"url", "token", "port"}`): `pen-editor-backend`, in local dev when `MCP_AUTH_TOKEN` is left unset (its dev-server c How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pen Editor setup
This plugin ships a dependency-free stdio proxy (bin/pen-editor-mcp.mjs) that forwards MCP calls to the pen-editor-backend server's /api/mcp endpoint. Diagnose failures by matching the exact symptom below — don't guess.
How the proxy finds the backend
In this order:
<PLUGIN_DATA>/config.json— the portable config file; this is whatconfigure_pen_editor_connection(below) writes. Highest precedence: once this file has both a url and a token, nothing below it has any effect.PEN_EDITOR_MCP_URL/PEN_EDITOR_MCP_TOKENenv vars — a power-user channel, not guaranteed to survive in every client.~/.pen-editor/mcp.json— a handshake file two different servers can write to the same path/shape ({"url", "token", "port"}):pen-editor-backend, in local dev whenMCP_AUTH_TOKENis left unset (its dev-server counterpart,pen-editor, reads the same file to pick up the token); andpen-editor-desktop, which writes it on every launch with no configuration at all. Whichever one last published the file is what the proxy connects to — this is what makes both local dev and the desktop app zero-config, no env vars, no manual file editing.- Default
http://localhost:3001/api/mcp, no token.
Two different servers, same name: pen-editor-backend and pen-editor-desktop both publish an MCP server named pen-editor through this same handshake file, but their tool sets and tool behavior differ — see "Two pen-editor endpoints" below before assuming a symptom or fix that's specific to one applies to the other.
url and token are resolved independently across steps 1–2 (e.g. url from config.json, token from an env var is fine). Step 3 is the one exception: its token is a loopback-only secret bound to its own url, so it's only ever consulted while url is still unresolved — if config.json or an env var already pinned url to something else, the handshake file is skipped entirely rather than pairing its token with a foreign url. If you see a clean "no token configured" error even though ~/.pen-editor/mcp.json clearly has one, this is almost always why: something upstream already resolved url.
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 · 67 lines · 67 tokens per session scan B e573964acdb7
pen-editor-setup is a skill published in the GitHub repository dan-rozhkov/pen-editor-plugin (0 stars, last pushed 27d ago), licensed MIT. It adds 67 tokens to every session and 2,698 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). 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…
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…
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…