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 commands/xinyuqu/llm-review/claude-codegit clone --depth 1 https://github.com/XinyuQu/llm-reviewWrote 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/commands/xinyuqu/llm-review/claude-code)<a href="https://agentmods.dev/commands/xinyuqu/llm-review/claude-code"><img src="https://agentmods.dev/badge/commands/xinyuqu/llm-review/claude-code.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.00690 |
| Opus 5 | $0.00012 | $0.00345 |
| Sonnet 5 | $0.00005 | $0.00138 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
claude-code 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 4d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Get an adversarial code review from Claude as an independent reviewer (its
own claude CLI subscription run, or a separate Anthropic API call) —
deliberately not the Claude Code session you are talking to.
Raw slash-command arguments: $ARGUMENTS
Parse $ARGUMENTS into the engine command (build as separate args, never splice
the raw string into a shell line):
- first bare word not starting with
-→ base git ref, pass as--base <ref> --staged→ review staged changes only--diff-only→ restrict the reviewer to the diff (don't let it read other repo files), pass as--diff-only--wait→ execution mode (don't pass to engine; foreground)--background→ execution mode (don't pass to engine; background)
Execution mode
Reviews against large diffs legitimately take several minutes. Default to background so the Claude Code session is not blocked.
- If
$ARGUMENTScontains--wait: foreground, skip the question. - If
$ARGUMENTScontains--background: background, skip the question. - Otherwise, estimate diff size first, then ask:
- Run
git diff --shortstat(orgit diff --shortstat --stagedif--staged, orgit diff --shortstat <base>...HEADif a base was given). - Tiny (≤2 files changed and no large directory rewrite) → recommend wait.
- Otherwise → recommend background.
- Call
AskUserQuestiononce with two options, recommended first and suffixed with(Recommended):Wait for resultsRun in background
- Run
Foreground path
Run synchronously:
node "${CLAUDE_PLUGIN_ROOT}/scripts/llm-review.mjs" review --provider claude [--base <ref>] [--staged] [--diff-only]
Then present the review to the user verbatim — do not soften, summarize,
or re-rank its findings. Preserve its severities and verdict. If the command
errored (e.g. not configured or no changes), relay the error and point the user
to /llm-review:claude-code-setup.
Background path
Launch with Bash(run_in_background: true):
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.
- 4d ago First seen · 65 lines · 24 tokens per session scan A 2b7cf037b89a
claude-code is a command published in the GitHub repository XinyuQu/llm-review (6 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 690 once invoked, about $0.0001 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.