What is code-review-coach?

A guided practice workflow for learning how to review existing code or a proposed code change. It asks the learner to find and justify one possible problem at a time.

Use it to practise understanding what code promises, finding risks, connecting them to evidence, judging their impact, and proposing the smallest justified fix.

It builds the ability to notice risks instead of handing over a long list of review comments or a rewritten solution.

code-review-coach — Skill by Far-200

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/far-200/think-before-code/code-review-coach

Any agent

npx skills add Far-200/think-before-code --skill code-review-coach

Clone the repo

git clone --depth 1 https://github.com/Far-200/think-before-code

Made for: Claude Code, Codex.

Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,590 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00131	$0.03590
Opus 5	$0.00066	$0.01795
Sonnet 5	$0.00026	$0.00718
Haiku 4.5	$0.00013	$0.00359

Measured 2d ago against content hash 8736bcfefcf1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review-coach 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.

skills/code-review-coach/SKILL.md · 390 lines

How it starts

The opening of the file, as written. The whole thing — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Coach

Why this exists

The premature-answer problem this repository exists to interrupt is not unique to DSA. Ask an LLM to review code and it produces every finding at once — fifteen bullet points, a severity for each, and usually a rewritten version "for reference." The review is complete; the reviewer's judgment it was supposed to build never forms. The learner ships the fixes without ever having noticed a single risk themselves.

This skill exists to make the learner do the noticing: establish what the code promises, inspect one risk at a time, tie every claim to concrete evidence, understand impact before assigning severity, and propose the smallest justified change — so the judgment transfers to the next review, not just this file.

Boundary with neighboring skills

vs. debug-coach — debug-coach starts from an observed expected-vs-actual failure on a concrete input. This skill starts from code that hasn't visibly failed and asks what could go wrong. If a concrete runtime failure surfaces mid-review, stop diagnosing here and hand off to debug-coach with the failing input.
vs. test-case-coach — a review finding often ends with one verification idea (a test, an assertion, a check). Designing a systematic suite around the code is test-case-coach's protocol; hand off rather than expanding one regression idea into suite design here.
vs. complexity-coach — performance may come up as one review lens, but if deriving time or space complexity becomes the whole question, that's complexity-coach's drill.
vs. dsa-tutor — an unsolved DSA problem the learner wants built end to end is dsa-tutor's session, even if partial code exists. This skill reviews code that already exists and works, or is believed to.
vs. specification-coach — a vague feature request with no code behind it yet is a specification problem, not a review: what the change must observably do has to be defined before anything can be judged against it. That's specification-coach. This skill starts once code, a diff, or a PR exists.
vs. dry-run-coach — tracing one chosen concrete input through explicit state is dry-run-coach's discipline. This skill may identify which line deserves a trace; the trace itself is the other skill's protocol.

Read the full file on GitHub · 390 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.

2d ago First seen · 390 lines · 131 tokens per session scan A 8736bcfefcf1

Subscribe to this mod's changes

code-review-coach is a skill published in the GitHub repository Far-200/think-before-code (8 stars, last pushed 17d ago), licensed MIT. It adds 131 tokens to every session and 3,590 once invoked, about $0.0007 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 Productivity agent-skills ai-tutor dsa leetcode socratic-method

interactive-leetcode-mcp

Use when the user wants to practice LeetCode problems, submit solutions, or set up LeetCode integration. Covers MCP server installation, learning-guided practice flow, solution submission, and authentication.

SPerekrestova/interactive-leetcode-mcp · 46 tokens

leetcode-helper

Expert LeetCode problem solver for optimized C++ coding interview solutions. Use when: the user pastes a LeetCode problem, asks for an optimized algorithm, wants C++ LeetCode code, needs a dry run, asks for line-by-line explanation, wants a hint before the solution, wants brute force to optimized progression, wants…

Zephyrex21/claude-leetcode-helper · 98 tokens

configure-profile

Create or update the global learner profile. Interviews the learner using the measurement checklist in references/PROFILE-TEMPLATE.md and writes the structured result to profile/PROFILE.md. Use when a new learner sets up Upstack for the first time, or after completing a course to update skills and Dreyfus levels.

ishands/upstack · 64 tokens

create-course

Scaffold a new course directory from the COURSE.md schema. Creates the directory structure, populates COURSE.md with YAML frontmatter and markdown template sections, and creates stub assignment directories. Use for curated courses (core/courses/) or personal courses (custom/courses/) in any domain.

ishands/upstack · 60 tokens

start-course

Initialise a learning session. Checks for an existing journal in progress/ /journal.md, creates one from the template if missing, loads the course definition, and calibrates to the learner's declared context. Use when starting a new course or resuming after a break.