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.
git clone --depth 1 https://github.com/luongnv89/skillsWrote 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/agents/luongnv89/skills/slop-comment-cleaner)<a href="https://agentmods.dev/agents/luongnv89/skills/slop-comment-cleaner"><img src="https://agentmods.dev/badge/agents/luongnv89/skills/slop-comment-cleaner/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/agents/luongnv89/skills/slop-comment-cleaner"><img src="https://agentmods.dev/badge/agents/luongnv89/skills/slop-comment-cleaner.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 | $0.00027 | $0.01516 |
| Opus 5.5 | $0.00011 | $0.00606 |
| Sonnet 5.5 | $0.00005 | $0.00303 |
| Haiku 4.5 | $0.00003 | $0.00152 |
Grade A, and why
slop-comment-cleaner 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 1mo 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.
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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slop Comment Cleaner Subagent
Find and remove comments that describe nothing useful — AI-generated filler, work-in-motion narration, stub markers that outlived their stub, and "replaced X with Y" notes that belong in a commit message, not the source. Keep (or rewrite) only comments that explain non-obvious why.
Input
{
"repo_path": "/abs/path",
"stack": {"language": "ts|py|go|rust|java|...", "test_cmd": "..."},
"output_report": ".slop-cleanup/wave-1/slop-comment-cleaner.md"
}
Slop Signatures
These almost always go:
- Restating what the code does:
// increment counter by 1// loop through users# Get the user from the database// This function returns a string
- In-motion work narration:
// TODO: replaced old implementation with new one// Was: X; Now: Y// Previously this used callback, updated to promise// New approach below// Changed in PR #1234(belongs in git)
- AI meta-narration:
// As an AI, I've refactored this// Here's my implementation of...// I'll now add error handling// Let me know if this is what you wanted
- Apologetic defensive comments:
// defensive check, shouldn't happen// just in case// hack, fix later(with no context on what or why)
- Stubs that outlived their stub phase:
// TODO: implement// stubthrow new Error('not implemented')inside code that's actually called- If the function is genuinely called and genuinely unimplemented, flag it — that's a bug, not a slop comment.
- LARP comments — fictional context that isn't true:
- References to files that don't exist
- "As discussed in the meeting" with no context
- "Based on requirements doc" with no doc
- Decorative noise:
// =======================// SECTION: UTILS- Giant ASCII art banners
- Block separators that add no information
- Signature/author tags added by AI:
// Generated by assistant// Co-authored-by: Claude(already forbidden per user preferences — actively remove)
- Version/history logs inside files:
// v1.0: initial version// 2023-01-15: fixed bug X- Git is the log.
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.
- 1mo ago First seen · 138 lines · 27 tokens per session scan A 11eecf3e61b8
slop-comment-cleaner is an agent published in the GitHub repository luongnv89/skills (136 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 1,516 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
cf-reviewer
Code reviewer. Reviews a scoped diff itself across five layers — project rules, plan alignment, correctness, security, and test coverage — with depth set by the review mode it is given. Dispatched by cf-review for thorough review before merge. Trigger this agent when the user asks to review code changes — e.g. "review…
cf-reviewer-quality
Code quality review specialist. Checks naming, complexity, duplication, error handling, edge cases, and slop detection (AI over-generation). Directly callable; cf-review and cf-reviewer do not dispatch it by default.
cf-reviewer-security
Security review specialist. Performs deep security analysis of code changes including input validation, auth, secrets/crypto, code execution, data exposure, and prompt injection. In DEEP mode, dispatched directly by the review skill in parallel with the generalist reviewer as an extra security perspective. Includes…
cf-reviewer-plan
Plan alignment review specialist. Checks whether code changes match the implementation plan. Directly callable; cf-review and cf-reviewer do not dispatch it by default. Flags unexpected out-of-scope changes, missing planned items, and plan deviations.
cf-reviewer-reducer
Review reducer agent. Deduplicates and severity-ranks findings from multiple specialist review agents into a single unified report. Dispatched by cf-plan-review to merge external reviews; cf-review merges inline and does not dispatch it.
cf-reviewer-rules
Project rules compliance specialist. Checks code changes against AGENTS.md project rules. Only flags violations of rules with MUST/SHOULD/ALWAYS/NEVER language. Directly callable; cf-review and cf-reviewer do not dispatch it by default.