agentmods.dev

mtk-agent-toolkit: Skill for Claude Code

.claude/skills/pr-review-mining/SKILL.md

pr-review-mining is a skill for Claude Code from moberghr/mtk-agent-toolkit. It costs 31 tokens per session (784 once invoked), scanned A, original, MIT.

A tool that examines recently merged pull requests, which are proposed code changes accepted into a repository, for repeated reviewer comments. It suggests recurring feedback phrases without changing project rules.

In plain words
What is it for?
Use it to identify common reviewer requests and prepare suggestions for architecture or coding guidelines.
Why use it?
It helps reveal review issues that keep appearing without requiring someone to read every past review manually.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is moberghr/mtk-agent-toolkit's own configuration. It tells Claude Code how to work on mtk-agent-toolkit 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 mtk-agent-toolkit configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/pr-review-mine.sh --prs 10.

Part of the mtk plugin — 45 skills, 6 agents, 7 hooks, 1 MCP server shipped together

not rated 7repo yesterday A scan 31 tokens original MIT
View source ↗ moberghr/mtk-agent-toolkit moberghr.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to moberghr/mtk-agent-toolkit. 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/moberghr/mtk-agent-toolkit/main/.claude/skills/pr-review-mining/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/moberghr/mtk-agent-toolkit

Made for: Claude Code.

Or install mtk, the plugin that ships this one along with the rest of its 45 skills, 6 agents, 7 hooks, 1 MCP server.

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-mining

README.md
[![agentmods](https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/pr-review-mining/github.svg)](https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/pr-review-mining)
Your own site
<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/pr-review-mining"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/pr-review-mining/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-mining

Your own site · 80×15
<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/pr-review-mining"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/pr-review-mining.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 784 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 $0.00031 $0.00784
Opus 5 $0.00015 $0.00392
Sonnet 5 $0.00006 $0.00157
Haiku 4.5 $0.00003 $0.00078

Measured 9d ago against content hash 221d400ded31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pr-review-mining 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 9d 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/pr-review-mining/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR review mining

Overview

Wraps scripts/pr-review-mine.sh (fetches merged PR review threads via gh, clusters repeated reviewer-feedback phrases). Output is always advisory — phrases tagged [MINED:feedback] and never auto-edited into architecture-principles.md.

When To Use

  • The engineer asks: "what are reviewers asking for repeatedly?", "mine our PRs", "what should we add to our rules?"
  • As part of /mtk repo-health (periodic readiness report).
  • As an optional step inside setup-audit --mine-prs to seed architecture-principles.md candidates.

When NOT To Use

  • The repo has fewer than 3 merged PRs — not enough signal.
  • gh is unauthenticated and the engineer is offline — fail-soft will skip with a warning.
  • The engineer wants to auto-edit principles — this skill never writes to architecture-principles.md.

Workflow

  1. Pre-flight. Confirm gh is installed and authenticated: gh auth status >/dev/null 2>&1. If not, report the warning and stop — do not attempt to fix gh auth from inside this skill.

  2. Run the miner.

    bash scripts/pr-review-mine.sh --prs 10
    • --prs N (default 10, range 1..50) — number of merged PRs to scan.
    • --json — machine-readable output to stdout.

  3. Read the canonical patterns reference. .claude/references/pr-mining-patterns.md defines what phrases mean and which are denylisted. If the engineer sees obvious noise (e.g., "looks good to me" sneaks through), append it to the ## Denylist section of that file and re-run.

  4. Suggest-only. Present each candidate phrase to the engineer with its PR citations. Do NOT modify architecture-principles.md automatically — the engineer must opt in per-phrase, prefixing the resulting principle with [MINED:feedback] and citing the PR numbers.

  5. Record the run. If invoked from repo-health, the parent skill emits a "PR mining" section into .claude/repo-health-latest.md with the table.

Verification

  • The script exited 0 (mining is always advisory; non-zero only on argument validation error).
  • The output references concrete PR numbers (#<n>) — fabricated phrases without citations are a red flag.
  • No edits were made to architecture-principles.md.
  • If gh was missing or unauthenticated, the output explicitly says Skipped: <reason> rather than fabricating phrases.

Read the full file on GitHub · 59 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. 9d ago First seen · 59 lines · 31 tokens per session scan A 221d400ded31

Subscribe to this mod's changes

pr-review-mining is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (7 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 784 once invoked, about $0.0002 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.

Code review
Related

Other skills, from other repositories

autoreview

Pre-commit/ship code review: Codex default; optional Claude or Pi.

openclaw/clawhub · 20 tokens

rework-rate

Measure and interpret PR rework rate — the emerging 5th DORA metric.

bradygaster/squad · 20 tokens

omh-code-review

This is a Hermes-native code-review workflow skill.

rlaope/oh-my-hermes · 46 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

code-reviewer

Code review specialist focused on patterns, bugs, security, and performance.

RightNow-AI/openfang · 17 tokens

agent-teams-simplify-and-harden

Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…

LeoYeAI/openclaw-master-skills · 115 tokens