lens-sandbox: Skill for Claude Code

.claude/skills/review-comments/SKILL.md

review-comments is a skill for Claude Code from lensapp/lens-sandbox. It costs 112 tokens per session (2,899 once invoked), scanned A, original, Apache-2.0.

A workflow for handling pull-request review comments, which are suggestions or questions left by reviewers on proposed code changes.

In plain words
What is it for?
Use it to fetch and sort review comments, assess their severity, update the code, write replies, and resolve review threads.
Why use it?
It helps organize feedback, decide what needs changing, make fixes with tests, and close the related discussion.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is lensapp/lens-sandbox's own configuration. It tells Claude Code how to work on lens-sandbox itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything lens-sandbox configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lensapp/lens-sandbox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lensapp/lens-sandbox/main/.claude/skills/review-comments/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lensapp/lens-sandbox

Made for: Claude Code.

Wrote 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.

agentmods badge for review-comments

README.md
[![agentmods](https://agentmods.dev/badge/skills/lensapp/lens-sandbox/review-comments/github.svg)](https://agentmods.dev/skills/lensapp/lens-sandbox/review-comments)
Your own site
<a href="https://agentmods.dev/skills/lensapp/lens-sandbox/review-comments"><img src="https://agentmods.dev/badge/skills/lensapp/lens-sandbox/review-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.

agentmods 80×15 button for review-comments

Your own site · 80×15
<a href="https://agentmods.dev/skills/lensapp/lens-sandbox/review-comments"><img src="https://agentmods.dev/badge/skills/lensapp/lens-sandbox/review-comments.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,899 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 327
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00112 $0.02899
Opus 5 $0.00056 $0.01450
Sonnet 5 $0.00022 $0.00580
Haiku 4.5 $0.00011 $0.00290

Measured 6d ago against content hash c3d772c044b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

review-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 6d 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.

.claude/skills/review-comments/SKILL.md · 330 lines

How it starts

The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Comments

You help the user work through pull request review comments efficiently. Your job is to fetch all comments, understand them in the context of the PR, triage by severity, present a clear overview, and then guide the user through addressing each one — whether that means fixing the code or crafting a reply.

Quality matters. When you fix something, fix it properly — with tests, just as if you were writing the code from scratch. A reviewer asked for a change because they care about the codebase; honor that by doing the fix right.

Phase 1: Identify the PR

$ARGUMENTS may contain a PR number, URL, or owner/repo#number. If empty, detect from the current branch:

gh pr view --json number,url,title,headRefName,baseRefName 2>/dev/null

If no PR is found, ask the user which PR to work on.

Store these for later: PR_NUMBER, PR_URL, OWNER, REPO, HEAD_REF, BASE_REF.

Derive OWNER and REPO from gh repo view --json owner,name or by parsing the PR URL.

Phase 2: Fetch everything

Fetch all data in parallel:

2.1 Review threads (primary source — gives threads, resolution status, and all comments)

gh api graphql -f query='
  query($owner: String!, $repo: String!, $number: Int!) {
    repository(owner: $owner, name: $repo) {
      pullRequest(number: $number) {
        author { login }
        reviewThreads(first: 100) {
          nodes {
            id
            isResolved
            comments(first: 50) {
              nodes {
                id
                databaseId
                body
                author { login }
                path
                line
                originalLine
                diffHunk
              }
            }
          }
        }
      }
    }
  }
' -f owner="$OWNER" -f repo="$REPO" -F number="$PR_NUMBER"

This is the single source of truth for inline review comments. It gives you:

  • Thread-level id (needed for resolving via GraphQL mutation)
  • Comment-level databaseId (needed for in_reply_to when posting replies via REST)
  • Resolution status per thread
  • The full comment body, author, file path, and diff context

Read the full file on GitHub · 330 lines

Changes

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.

  1. 6d ago Changed · -7 lines c3d772c044b7
  2. 10d ago First seen · 337 lines · 112 tokens per session scan A 1d2a05785891

Subscribe to this mod's changes

review-comments is a skill published in the GitHub repository lensapp/lens-sandbox (10 stars, last pushed today), licensed Apache-2.0. It adds 112 tokens to every session and 2,899 once invoked, about $0.0006 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 2026-08-31.