Skip to content
Agentmart
Submit a tool

no-comments

Kill needless comments plus the dead code they protect, fix root causes in scope, encode real constraints as structure.

Skill by TudeOrangBiasa

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying no-comments?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/tudeorangbiasa-no-comments

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Kill needless comments plus the dead code they protect, fix root causes in scope, encode real constraints as structure. Use before review or when comments outnumber reasons.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/no-comments

What's inside

Skill name
no-comments
Description
Kill needless comments plus the dead code they protect, fix root causes in scope, encode real constraints as structure. Use before review or when comments outnumber reasons.
License
MIT
Instructions
17 lines in SKILL.md · view on GitHub

Files (3)

  • CREDITS.md
  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# No comments

Hunt needless comments and the dead code and workarounds they protect, fix the root cause in scope, and encode real constraints as structure. Comments that survive must prove they are about something unchangeable. Companion to `interrogate` (adversarial review of the change) and rule 24 (no phase-narrating comments): this one goes further, treating every comment as guilty until proven load-bearing.

## Scope

The caller's files or diff; otherwise the current diff against the base branch, working tree included.

## Steps

1. Spawn one reviewer per available model with the same brief (scope plus this rubric), all in one round; single-model harnesses run two passes (find, then challenge). Models follow the repo model map. Never restate the rubric inside the brief; point at it.
2. Judge every finding skeptically before touching code. Reject application-code edits, scope escapes, exception-protected deletions, misstated kill reasons, and flags treating kept intentional code as guilty. A keep survives only with proof it is about something unchangeable (generated code, external contract, hardware limit); run `how` or `why` on thin keeps before believing them. Ambiguous kill means do not restore; refuted or still-ambiguous keep means delete. A rejected report gets one rerun with the failure named; reject twice and the skill fails open with the report.
3. Fix trivial accepted flags directly: delete the dead path, drop the parameter, use the real API. Fixes needing shape get one `codebase-design` sketch first; the sketch shapes, implementation follows.
4. Implement the smallest root-cause fix in scope (rule 2) and remove every named workaround. Root cause out of scope means landing the smallest in-scope fix and reporting the rest open. Never bolt on symptom guards, never widen the fence.
5. Constraint comments (`do not remove`, `do not change wording`, `talk to X`) become encodings, not keeps: offer the cheapest in-scope type, runtime check, test, or CI lint (rule 13), wait for approval, encode, then delete the comment. Unattended runs need caller pre-approval; without it, delete, report the constraint open, and sketch the out-of-scope work.
6. Report: deletion count, restored comments, reruns, sketch, fixes, encoding offers and landings, unenforced constraints, other open work.

From TudeOrangBiasa/skills-for-agents, MIT.

More from TudeOrangBiasa/skills-for-agents

Signals

Stars
1
Forks
0
Open issues
1
Last commit (this folder)
Oct 17, 2026 (13 days ago)
Last release
Oct 23, 2026 (7 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from TudeOrangBiasa

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get no-comments running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying no-comments?

CallGet help
Cite this page

no-comments skill. Agent Mart. https://agentmart.dev/skills/tudeorangbiasa-no-comments (last updated 2026-10-24)