sqlprism: Skill for Claude Code

.claude/skills/reviewing-prs/SKILL.md

reviewing-prs is a skill for Claude Code from darkcofy/sqlprism. It costs 60 tokens per session (552 once invoked), scanned A, original, Apache-2.0.

A GitHub pull-request review workflow that asks three reviewers—software engineering, data engineering, and quality assurance—to inspect the changes, then combines their findings into one comment.

In plain words
What is it for?
Reviewing a pull request’s description, changed files, and code diff; organizing issues by severity; and posting a structured review comment on GitHub.
Why use it?
It reduces the chance that bugs, data problems, or missing tests are overlooked and avoids having to coordinate several separate reviews.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is darkcofy/sqlprism's own configuration. It tells Claude Code how to work on sqlprism 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 sqlprism configures →

Reuse

Borrowing it

Nothing to install: this file belongs to darkcofy/sqlprism. 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/darkcofy/sqlprism/main/.claude/skills/reviewing-prs/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/darkcofy/sqlprism

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 reviewing-prs

README.md
[![agentmods](https://agentmods.dev/badge/skills/darkcofy/sqlprism/reviewing-prs/github.svg)](https://agentmods.dev/skills/darkcofy/sqlprism/reviewing-prs)
Your own site
<a href="https://agentmods.dev/skills/darkcofy/sqlprism/reviewing-prs"><img src="https://agentmods.dev/badge/skills/darkcofy/sqlprism/reviewing-prs/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 reviewing-prs

Your own site · 80×15
<a href="https://agentmods.dev/skills/darkcofy/sqlprism/reviewing-prs"><img src="https://agentmods.dev/badge/skills/darkcofy/sqlprism/reviewing-prs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 552 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.
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 $0.00060 $0.00552
Opus 5.5 $0.00024 $0.00221
Sonnet 5.5 $0.00012 $0.00110
Haiku 4.5 $0.00006 $0.00055

Measured 2mo ago against content hash 24a7558742f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

reviewing-prs 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 2mo 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/reviewing-prs/SKILL.md · 67 lines

What it actually says

PR Review

Workflow

  1. Fetch PR context using the commands below
  2. Spawn 3 sub-agents in parallel — one per reviewer persona (see REVIEWERS.md)
  3. Collect results from all three
  4. Synthesize into a single review using the format in COMMENT-TEMPLATE.md
  5. Post the comment to the PR

Step 1: Fetch PR Context

gh pr view <number> --json title,body,baseRefName,headRefName,files,additions,deletions
gh pr diff <number>
gh pr view <number> --json reviews,comments

Pass the PR number, title, diff, and file list to each sub-agent.

Step 2: Spawn Reviewers

Launch all three sub-agents in parallel using the Agent tool. Each agent receives:

  • The full PR diff
  • The file list with additions/deletions
  • The PR description
  • Their specific reviewer instructions from REVIEWERS.md

Each sub-agent must return a structured review following the format in their instructions. Do not ask them to post comments — only the main agent posts.

Step 3: Synthesize

Read all three reviews. Deduplicate overlapping findings. Assign a final severity to each issue:

  • Critical — must fix before merge (bugs, security, data loss)
  • Warning — should fix, but not a blocker
  • Suggestion — nice to have, optional

Step 4: Post Comment

gh pr comment <number> --body "$(cat <<'EOF'
<synthesized review — see COMMENT-TEMPLATE.md>
EOF
)"

Boundaries

Always:

  • Read the full diff before reviewing
  • Run all 3 reviewers in parallel
  • Include the issue number from the PR body in the review
  • Attribute findings to the reviewer who raised them

Ask first:

  • Requesting changes (blocking the PR) vs leaving comments
  • If the PR touches more than 500 lines changed

Never:

  • Approve or merge the PR automatically
  • Edit code or push commits to the PR branch
  • Post multiple comments (always one synthesized comment)
Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 67 lines · 60 tokens per session scan A 24a7558742f0

Subscribe to this mod's changes

reviewing-prs is a skill published in the GitHub repository darkcofy/sqlprism (1 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 60 tokens to every session and 552 once invoked, about $0.0002 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 2026-09-01.

Related

reviewing-prs compared with skills from other repositories

reviewing-prs next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
reviewing-prsdarkcofy/sqlprismSkill14mo agoApache-2.0A60Claude Code
autoreviewopenclaw/clawhubSkill9.5kyesterdayMITA17Claude Code, Codex
agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skillsSkill2.2k6d agoMITA115Claude Code, Codex
omh-code-reviewrlaope/oh-my-hermesSkill5.2kyesterdayMITA48Claude Code, Codex
revdiff-planumputun/revdiffSkill945yesterdayMITA84Claude Code
explore-unknownsdzhng/skillsSkill1.4k2d agoMITA162Claude Code, Codex
re0-mergeLilMGenius/paperthinSkill1.4k4d agoMITA70Claude Code