Skills/npm/red-pen-editor

red-pen-editor@0.2.1

VERIFIED· startup only

Publisher claims: "An editorial judgment skill, local-first CLI, and MCP server for removing unearned words while preserving meaning." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher quarterback · publishing for 27 daysInstalls 550Last detonated 1 h ago
$claude mcp add red-pen-editor -- npx -y red-pen-editor
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-18 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 20 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
20sclaimedstartup only: exited (0) before answering · --edits PATH JSON proposals for apply: array or {edits:[...]} --json Show complete JSON result on stdout --help Show help Nothing overwrites the input file. review/edit require a running local Ollama.
20sprocessscript backend runs setup only
20sprocessno install scripts to re-run

Static findings

No findings across 826 lines in 10 files.

Cost to the agent

Instructions loaded
≈1,349 tok
1 file · 10 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for red-pen-editor@0.2.1 as of 23 min ago. This is the package itself, not its dependencies.

red-pen-editor@0.2.1 safety verdict: Verified (startup only) — KillerSkills