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 skills add lttr/claude-marketplace --skill code-reviewgit clone --depth 1 https://github.com/lttr/claude-marketplaceWrote 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.
[](https://agentmods.dev/skills/lttr/claude-marketplace/code-review)<a href="https://agentmods.dev/skills/lttr/claude-marketplace/code-review"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/code-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.
<a href="https://agentmods.dev/skills/lttr/claude-marketplace/code-review"><img src="https://agentmods.dev/badge/skills/lttr/claude-marketplace/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00070 | $0.00967 |
| Opus 5 | $0.00035 | $0.00483 |
| Sonnet 5 | $0.00014 | $0.00193 |
| Haiku 4.5 | $0.00007 | $0.00097 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Single entry point. Detect input source, produce a diff file, then run the review pipeline.
Input Detection
Argument is $ARGUMENTS (may be empty).
| Form | Source |
|---|---|
| empty | current branch vs base (master/main) |
staged |
git diff --staged |
numeric (12345) |
Azure DevOps PR id |
URL containing _git/.../pullrequest/<id> |
Azure DevOps PR URL |
URL containing _workitems/edit/<id> or ticket id mapped to PR |
resolve work item → PR via az boards |
path ending .diff or .patch |
local diff file |
| anything else | treat as git ref (branch / sha / tag) |
Ambiguous → ask user. Do NOT guess.
Workflow
1. Resolve input → diff file path + metadata
empty
base=$(git rev-parse --verify master 2>/dev/null && echo master || echo main)
cur=$(git branch --show-current)
[ "$cur" = "$base" ] && abort "On base branch ($base). Switch to a feature branch."
git diff "$base"...HEAD > "/tmp/review-diff-$(date +%s).diff"
files=$(git diff --name-only "$base"...HEAD)
title="$cur"
staged
git diff --staged > "/tmp/review-diff-staged-$(date +%s).diff"
files=$(git diff --staged --name-only)
title="staged changes"
PR id / PR URL
Extract numeric id from URL if needed. Then:
az repos pr show --id <id> --output json
az repos pr diff --id <id> > "/tmp/review-diff-pr-<id>.diff"
Title/description/author/targetRefName from pr show output. Skip if status completed/abandoned, title has [WIP]/[Draft], author is bot, or only auto-generated files changed.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 112 lines · 70 tokens per session scan A 4f6e9ec25d53
code-review is a skill published in the GitHub repository lttr/claude-marketplace (2 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 967 once invoked, about $0.0003 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.
Other skills, from other repositories
verify-change
A change-checking skill that reviews code differences and checks whether related documentation, tests, and records were updated.
verify-quality
A code-quality checker that measures complexity, size, naming, and common code smells. It reports problems such as duplicated code, unused code, and overly long functions.
verify-module
A module-checking skill that scans a project’s folders, code, and documentation. It expects each module to include a README.md and DESIGN.md, which explain how the module is used and why it was designed that way.
flow-next-impl-review
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
flow-next-spec-completion-review
Verify that a spec's completed tasks fully implement the spec requirements. Use at spec completion before close.
flow-next-resolve-pr
Resolve PR review feedback. Fetches unresolved threads, triages, fixes, replies and resolves via GraphQL. Use when asked to address review comments.