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 rp1-run/rp1 --skill code-clean-commentsgit clone --depth 1 https://github.com/rp1-run/rp1Wrote 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/rp1-run/rp1/code-clean-comments)<a href="https://agentmods.dev/skills/rp1-run/rp1/code-clean-comments"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/code-clean-comments/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/rp1-run/rp1/code-clean-comments"><img src="https://agentmods.dev/badge/skills/rp1-run/rp1/code-clean-comments.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 | $0.00023 | $0.00778 |
| Opus 5 | $0.00012 | $0.00389 |
| Sonnet 5 | $0.00005 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
code-clean-comments 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 yesterday.
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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comment Cleaner
Resolves a user scope into a durable change-manifest artifact, then spawns the comment-cleaner agent with only CHANGE_MANIFEST and CODE_ROOT.
The comment-cleaner agent remains manifest-only. Never pass SCOPE, BASE_BRANCH, branch, unstaged, or commit-range parameters to it.
1. Resolve Directories
Use generated Resolve Arguments directory values. Resolve {resolved_code_root} to CODE_ROOT when it is non-empty; otherwise use {codeRoot}. Use {workRoot} for the durable artifact directory.
Create the manifest directory if needed:
mkdir -p "{workRoot}/comment-clean-comments"
Choose the next numbered manifest/status path pair:
{workRoot}/comment-clean-comments/change-manifest-001.json
{workRoot}/comment-clean-comments/change-manifest-status-001.json
Increment the number if either file already exists. Set resolved_change_manifest_path and resolved_change_manifest_status_path to the selected pair.
2. Generate Manifest
Delegate all scope resolution to the typed generator:
rp1 agent-tools change-manifest generate \
--code-root "{resolved_code_root}" \
--out "{resolved_change_manifest_path}" \
--status-out "{resolved_change_manifest_status_path}" \
--source code-clean-comments \
--scope "{SCOPE}"
Parse the ToolResult envelope into cleanup_manifest_result. The generator is responsible for existing manifest JSON, file, directory, git ref, and git range scopes. Do not inspect files, walk directories, parse git diffs, validate existing manifest JSON, or write manifest JSON yourself.
If cleanup_manifest_result.data.status != "created", cleanup_manifest_result.data.files == 0, cleanup_manifest_result.data.ownedLineCount == 0, or cleanup_manifest_result.data.manifestPath is missing, fail closed and do not dispatch comment-cleaner. Report the status path and skip reason instead.
If the tool fails or returns malformed output, fail closed and do not dispatch comment-cleaner. Report change_manifest_generate_failed with the intended status path.
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.
- yesterday First seen · 86 lines · 23 tokens per session scan A b6e8bd332e4c
code-clean-comments is a skill published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 2d ago), licensed Apache-2.0. It adds 23 tokens to every session and 778 once invoked, about $0.0001 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 2026-09-07.
Other skills, from other repositories
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
fix
Dispatch fix subagent for FIX-FIRST gaps from review, re-review, then diagnose unresolved failures after 2 loops.
refactor-advisor
A code review helper that finds common design and maintenance problems in a codebase and suggests ways to restructure the code.
zh-code-reviewer
A Chinese-language code-review specialist that produces a structured review report. It examines coding style, possible bugs, performance, security, and design choices.
at-review
Review code changes for bugs, regressions, convention violations, and high-value cleanup opportunities. Use for diffs, commit ranges, hosted PR/MR URLs, branches, paths, staged changes, or working-tree changes.
architecture
Use when reviewing architecture in any codebase — module boundaries, stated design contracts, abstraction depth, error-handling design. Assess by default, apply changes on request; complexity is dependencies plus obscurity, and deep modules win.