dt-mcp-server: Skill for Claude Code

.agents/skills/pr-review/SKILL.md

pr-review is a skill for Claude Code, Codex from israel-salgado/dt-mcp-server. It costs 82 tokens per session (2,135 once invoked), scanned A, a copy of pr-review, MIT.

A checklist-based review of a pull request or feature branch before it is merged into the main codebase. It checks production readiness, code quality, user experience, documentation, tests, and safety.

In plain words
What is it for?
Use it to review a branch or pull request and report specific findings with file paths and line numbers.
Why use it?
It helps find problems or missing work before a change reaches users.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is israel-salgado/dt-mcp-server's own configuration. It tells Claude Code and Codex how to work on dt-mcp-server 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 dt-mcp-server configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is go test ./pkg/output/ -run TestGolden.

Reuse

Borrowing it

Nothing to install: this file belongs to israel-salgado/dt-mcp-server. 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/israel-salgado/dt-mcp-server/main/.agents/skills/pr-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/israel-salgado/dt-mcp-server

Made for: Claude Code, Codex.

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 pr-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/israel-salgado/dt-mcp-server/pr-review/github.svg)](https://agentmods.dev/skills/israel-salgado/dt-mcp-server/pr-review)
Your own site
<a href="https://agentmods.dev/skills/israel-salgado/dt-mcp-server/pr-review"><img src="https://agentmods.dev/badge/skills/israel-salgado/dt-mcp-server/pr-review/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 pr-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/israel-salgado/dt-mcp-server/pr-review"><img src="https://agentmods.dev/badge/skills/israel-salgado/dt-mcp-server/pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,135 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 86% copy Near-identical to another mod 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 $0.00082 $0.02135
Opus 5 $0.00041 $0.01068
Sonnet 5 $0.00016 $0.00427
Haiku 4.5 $0.00008 $0.00214

Measured 11d ago against content hash 16793b5acd3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pr-review 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 11d 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.

Origin

This is a copy

86% identical to pr-review — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/pr-review/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Quality Review

Perform a comprehensive quality review of a pull request or feature branch. This skill covers production readiness, code quality, UX, documentation, tests, and safety.

The review is structured as a checklist across seven dimensions. For each dimension, investigate the actual code and report specific findings -- not just "looks good" but concrete observations with file paths and line numbers.

Getting Started

First, understand the scope of the change:

# What branch are we on, what's the base?
git branch --show-current
git log main..HEAD --oneline

# What files changed?
git diff main...HEAD --stat

# Full diff for review
git diff main...HEAD

If reviewing a remote PR, fetch it first:

gh pr view <number> --json title,body,files
gh pr diff <number>

Read the PR description and all commits to understand the intent before diving into code.

Review Dimensions

Work through each dimension below. For each one, report a status:

  • Pass -- meets the bar, no issues
  • Needs work -- specific issues found (list them)
  • N/A -- not applicable to this change

1. Production Readiness

Does this code behave correctly and handle failure gracefully?

  • Error handling: Are all errors checked? Are they wrapped with context (fmt.Errorf("context: %w", err))? Do they surface actionable messages to users?
  • Edge cases: Empty inputs, nil values, missing config, network failures, API rate limits, large datasets, pagination boundaries
  • Safety checks: All mutating commands (create, edit, apply, delete, update) must include safety checks after LoadConfig() and before client operations. Pattern:
    checker, err := NewSafetyChecker(cfg)
    if err := checker.CheckError(safety.OperationXXX, safety.OwnershipUnknown); err != nil { return err }
    
    Verify correct operation type. Skip only in dry-run paths.
  • No stdout in library code: pkg/ must return data, not print. Only cmd/ handles output.
  • No hardcoded secrets or customer data: No real names, env IDs, tokens, or emails in code or tests. Use @example.invalid for emails (RFC 2606).

Read the full file on GitHub · 200 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. 11d ago First seen · 200 lines · 82 tokens per session scan A 16793b5acd3e

Subscribe to this mod's changes

pr-review is a skill published in the GitHub repository israel-salgado/dt-mcp-server (2 stars, last pushed 4mo ago), licensed MIT. It adds 82 tokens to every session and 2,135 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to pr-review, differing in 4 lines, and is treated as a copy.