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/bengous/claude-code-pluginsWrote 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/commands/bengous/claude-code-plugins/clean-pr-comments)<a href="https://agentmods.dev/commands/bengous/claude-code-plugins/clean-pr-comments"><img src="https://agentmods.dev/badge/commands/bengous/claude-code-plugins/clean-pr-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/commands/bengous/claude-code-plugins/clean-pr-comments"><img src="https://agentmods.dev/badge/commands/bengous/claude-code-plugins/clean-pr-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 | $0.00011 | $0.00804 |
| Opus 5.5 | $0.00004 | $0.00322 |
| Sonnet 5.5 | $0.00002 | $0.00161 |
| Haiku 4.5 | $0.00001 | $0.00080 |
Grade A, and why
clean-pr-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 24d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean PR Comments
Review comments in a PR. Fix comments that compensate for bad naming. Preserve comments that provide context code cannot express.
Decision Framework
| Comment compensates for... | Action |
|---|---|
| Bad variable/function name | Rename, remove comment |
| Missing abstraction | Extract to well-named function, remove comment |
| External knowledge | Keep |
| Inherent complexity | Keep |
Remove After Refactoring
Comments that explain WHAT code does—these are naming problems:
int d; // days elapsed→ rename toelapsedDays// check if user can access premiumbefore condition → extract tocanAccessPremium()setTimeout(fn, 86400000); // 24 hours→const ONE_DAY_MS = 86400000
Keep
Comments that explain what code CANNOT express:
- Business rules:
// FCC requires 30-day retention minimum - External quirks:
// Safari bug, see webkit#12345 - Performance:
// Intentionally avoiding map() - 10x faster here - History:
// Tried recursion but hit stack limits - Spec constants:
// 0x1F frame delimiter per RFC 7230 - Warnings:
// Order matters - auth before session init - License headers and public API docs
Remove Immediately
- Commented-out code (use git history)
- Restates code literally:
i++ // increment i - TODOs that should be tickets
Workflow
-
Identify scope from
$ARGUMENTS:- A PR reference:
gh pr checkout <ref>, thengh pr diff <ref> --name-only. The checkout switches the user's branch and fails on a dirty tree: say so before running it. - Empty: the current branch,
git diff --stat origin/main...HEAD
- A PR reference:
-
Select strategy based on PR size:
- Default: Process the files yourself
- Too large to read in one context: Spawn parallel agents (see Scaling below)
-
Read each file, identify all comments
-
Present findings before editing:
src/auth.js: L45: "// convert to uppercase" → REMOVE (obvious from code) L67: "// api timeout" → REFACTOR: rename `t` to `apiTimeoutMs` L89: "// Safari workaround #234" → KEEP (external quirk)
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.
- 24d ago Changed · -1 lines afb30ae626bd
- 1mo ago Changed · -3 lines 499ae911c457
- 1mo ago First seen · 108 lines · 11 tokens per session scan A 9c15b97dd043
clean-pr-comments is a command published in the GitHub repository bengous/claude-code-plugins (5 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 804 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
improve
Apply systematic improvements to code quality, performance, and maintainability.
spec-review
A command for reviewing an OpenSpec proposal with two separate AI models. OpenSpec is a way to describe planned software changes before implementation.
impl-review
John Carmack-level implementation review via Codex, Copilot, Cursor, Claude or a host reviewer.
resolve-pr
Resolve PR review feedback — fetch unresolved threads, triage, dispatch resolver agents, reply + resolve via GraphQL.
spec-completion-review
Spec completion review - verify implementation matches spec.
code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches superpowers:code-reviewer subagent to review implementation against plan or requirements before proceeding.