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.
npx agentmods add skills/fareedkhan-dev/claude-code-from-scratch/code-reviewnpx skills add FareedKhan-dev/claude-code-from-scratch --skill code-reviewgit clone --depth 1 https://github.com/FareedKhan-dev/claude-code-from-scratchWhat 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 | $0.00034 | $0.00773 |
| Opus 5 | $0.00017 | $0.00387 |
| Sonnet 5 | $0.00007 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00077 |
Grade A, and why
code-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.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Skill
When to use this skill
Load when the user asks you to:
- Review a file or function for bugs
- Check code quality or style
- Suggest improvements or refactors
- Audit security or error handling
- Compare two implementations
Review process
Always follow this order. Do not skip steps.
Step 1 — Read before commenting
Use the read tool to read the full file first.
Use grep to find related code (callers, tests, imports).
Never comment on code you haven't fully read.
Step 2 — Understand intent
Ask: what is this code trying to do? Read any docstrings, comments, and function names. If the intent is unclear, note it — don't assume.
Step 3 — Categorise issues
Use these categories consistently:
| Category | When to use |
|---|---|
| BUG | Code that will produce wrong results or crash |
| SECURITY | Input not validated, secrets exposed, injection risks |
| PERF | Unnecessary work, wrong data structure, O(n²) that could be O(n) |
| STYLE | Inconsistent naming, long functions, missing docstrings |
| SUGGEST | Optional improvements — not required to fix |
Step 4 — Write findings
Format each finding:
[CATEGORY] file.py:line_number
Issue: one sentence describing the problem
Why: why this matters
Fix: concrete suggestion or corrected code snippet
Step 5 — Summary
End with:
- Total issues found per category
- The most critical issue (if any BUG or SECURITY)
- Whether the code is safe to deploy as-is
What good code review looks like
- Specific: cite file + line number, not "somewhere in the code"
- Actionable: every issue has a suggested fix
- Proportionate: distinguish blocking bugs from style nits
- Respectful: review the code, not the author
Common bugs to look for in Python
# Mutable default argument (very common)
def append(item, lst=[]): # BUG: lst shared across all calls
lst.append(item)
# Exception swallowed silently
try:
do_something()
except Exception: # BUG: hides errors, use `except Exception as e: log(e)`
pass
# Off-by-one in slices
items[1:len(items)] # STYLE: prefer items[1:]
# Late binding closure
fns = [lambda: i for i in range(5)] # BUG: all return 4
fns = [lambda i=i: i for i in range(5)] # Fix
# Forgetting to close resources
f = open("file.txt") # BUG: use `with open("file.txt") as f:`
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 · 106 lines · 34 tokens per session scan A 47c3f2b79ddc
code-review is a skill published in the GitHub repository FareedKhan-dev/claude-code-from-scratch (294 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 773 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 2026-08-30.
Other skills, from other repositories
skill-creator
Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.
image-generation
Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.
implementation-final-review
Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…
metrics-instrumentation
Specification for instrumenting an opik-backend workflow with operational OpenTelemetry metrics — per-stage throughput/latency/error counters and native histograms, dimensioned per-customer (workspace). Use when a pipeline (scoring, ingestion, experiments, jobs) needs per-stage visibility. Covers metric emission only…
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…