implementation_review

implementation_review is a skill for Claude Code from MarcusJellinghaus/mcp-tools-py. It costs 8 tokens per session (355 once invoked), scanned A, a copy of implementation_review, MIT.

A compact code-review workflow for examining the current branch and its changes before merging. It checks the branch and diff, then reports critical issues, suggestions, strengths, and a short summary without modifying anything.

In plain words
What is it for?
Use it to review an implementation branch, assess its changed files, and decide whether the work is ready to merge.
Why use it?
It helps catch bugs, accidental breakage, debug code, and architecture violations before changes are merged. Reviewing the diff keeps attention on what actually changed.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Install

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.

agentmods
npx agentmods add skills/marcusjellinghaus/mcp-tools-py/implementation_review
Any agent
npx skills add MarcusJellinghaus/mcp-tools-py --skill implementation_review
Clone the repo
git clone --depth 1 https://github.com/MarcusJellinghaus/mcp-tools-py

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 implementation_review

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcusjellinghaus/mcp-tools-py/implementation_review.svg)](https://agentmods.dev/skills/marcusjellinghaus/mcp-tools-py/implementation_review)
Your own site
<a href="https://agentmods.dev/skills/marcusjellinghaus/mcp-tools-py/implementation_review"><img src="https://agentmods.dev/badge/skills/marcusjellinghaus/mcp-tools-py/implementation_review.svg" alt="Measured on agentmods" height="20"></a>
Per session 8 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 355 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 97% 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 $0.00008 $0.00355
Opus 5 $0.00004 $0.00178
Sonnet 5 $0.00002 $0.00071
Haiku 4.5 $0.00001 $0.00036

Measured 2d ago against content hash 734fe923c034, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

implementation_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 2d 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

97% identical to implementation_review — 0 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.

.claude/skills/implementation_review/SKILL.md · 44 lines

What it actually says

Implementation Review (Code Review)

First, ensure we're up to date: Call mcp__mcp-workspace__git with command "fetch" and args ["origin"]. Use mcp__mcp-workspace__git with command "status" to check working directory state. Call mcp__mcp-workspace__check_branch_status.

Confirm and display the current feature branch name.


Then run the code review:

Code Review Request

Use mcp__mcp-workspace__git with command "diff" to get the changes to review.

No need to run all checks; do not use pylint warnings. Feel free to further analyse any mentioned files and/or the file structure.

Focus Areas:

  • Logic errors or bugs
  • Tests for __main__ functions should be removed (not needed)
  • Unnecessary debug code or print statements
  • Code that could break existing functionality
  • Compliance with existing architecture principles, see docs/architecture/architecture.md

Output Format:

  1. Summary - What changed (1-2 sentences)
  2. Critical Issues - Must fix before merging
  3. Suggestions - Nice to have improvements
  4. Good - What works well

Do not perform any action. Just present the code review.

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. 2d ago Changed · -1 lines 734fe923c034
  2. 6d ago First seen · 45 lines · 8 tokens per session scan A 68d41edcbc8c

Subscribe to this mod's changes

implementation_review is a skill published in the GitHub repository MarcusJellinghaus/mcp-tools-py (18 stars, last pushed yesterday), licensed MIT. It adds 8 tokens to every session and 355 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to implementation_review, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

test-quality

Test quality bar for this repo. Read when writing, reviewing, or designing tests — covers naming, abstraction level, assertions, determinism, and the process for agent-driven test work.

modelcontextprotocol/python-sdk · 40 tokens

idapython

IDA Pro Python scripting for reverse engineering. Use when writing IDAPython scripts, analyzing binaries, working with IDA's API for disassembly, decompilation (Hex-Rays), type systems, cross-references, functions, segments, or any IDA database manipulation. Covers ida modules (50+), idautils iterators, and common…

mrexodia/ida-pro-mcp · 77 tokens

vibeue

Unreal Engine 5 development using the VibeUE Python API. Use when working in Unreal Engine — blueprints, state trees, materials, actors, landscapes, animation, niagara, widgets, sound, foliage, gameplay tags, enhanced input, skeletons, PCG (procedural content generation), and more. VibeUE is an extension of Unreal's…

kevinpbuckley/VibeUE · 82 tokens

test-generator

Generate pytest test cases for Python functions and classes.

vstorm-co/pydantic-deepagents · 12 tokens

n8n-code-python

Write Python code in n8n Code nodes. Use when writing Python in n8n, using input/json/node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes. Use this skill when the user specifically requests Python for an n8n Code node. Note — JavaScript is recommended for 95% of use…

czlonkowski/n8n-mcp · 157 tokens

touchdesigner-self-debug

A generic workflow for self-starting TouchDesigner via computer-use (or an already-running instance), loading mcpwebserverbase.tox, and verifying any TD-side Python change (td/modules/) directly from the Textport — reading back real TD runtime values and reconciling them. Use after changing TD-side code in the…

8beeeaaat/touchdesigner-mcp · 134 tokens