no-comments
An agent skill by cursor, from cursor/plugins. Tags: analysis, code-review, encoding, review, validation.
What it does
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add cursor/plugins --skill no-commentsOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/cursor/plugins
cp -r plugins/pstack/skills/no-comments ~/.claude/skills/no-commentsSafety box score
Grade A, minimal risk: 7 of 100 risk points, rated 2026-10-21. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill is a repository-local comment and code cleanup workflow: it reads the caller’s diff/working tree and can rewrite files to remove comments, suppressions, or other accepted findings. It does not fetch remote content, touch secrets, or use elevated privileges, but it does create automatic in-repo edits and report reruns.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | No shell commands, script runners, or code evaluation appear in `SKILL.md`; it only directs the agent to inspect diffs and generate edits. |
| Network access | 0 (none) | The skill contains no URL fetches, uploads, or other remote data flows. |
| Filesystem reach | 1 (low) | It explicitly works on "the caller's files or diff" and says to "Fix trivial accepted flags directly" and "delete" comments/paths, so it can rewrite files in the working tree. |
| Secrets & credentials | 0 (none) | There is no instruction to read or request tokens, passwords, `.env` files, keychains, or browser sessions. |
| Privilege & persistence | 0 (none) | The skill does not mention sudo, global installs, services, scheduled tasks, or OS/git setting changes. |
| Instruction hijack surface | 0 (none) | It does not ask the agent to ignore higher-priority instructions, follow remote prompt text, or hide behavior; the text is confined to its own workflow. |
| Irreversible actions | 1 (low) | It can automatically process accepted findings and rerun reports via "Spawn Task" and "Revert and rerun one rejected report," but it does not push, deploy, pay, or message externally. |
| Transparency | 0 (none) | The skill is a single readable markdown file; there are no binaries, generated blobs, or opaque installers. |
Before installing
- Run it on a scratch branch first; it will edit files in the current diff/worktree.
- Check whether your repo relies on comments or suppression markers before letting it delete them.
- Confirm who is allowed to approve any requested encodings or constraint exceptions.
Rated 2026-10-21 by an automated review of 1 file from the skill's repository.
Source
- Repository
- cursor/plugins (all skills from this repository)
- Path
- pstack/skills/no-comments/SKILL.md
- Branch
- main
- Collection
- cursor
- Updated
- 2026-09-23
Related skills
- interrogate — Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
- maintain-verification-skill — Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature.
- principle-prove-it-works — Apply after completing a task, before declaring done.
- thermo-nuclear-code-quality-review — Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth.
- thermo-nuclear-review — Comprehensive security and correctness audit of a branch's changes.
- thermos — Launch both thermo-nuclear review subagents in parallel, then synthesize their findings.