Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add XinyuQu/llm-review/plugin install 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/jobs)<a href="https://agentmods.dev/commands/xinyuqu/llm-review/jobs"><img src="https://agentmods.dev/badge/commands/xinyuqu/llm-review/jobs/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/commands/xinyuqu/llm-review/jobs"><img src="https://agentmods.dev/badge/commands/xinyuqu/llm-review/jobs.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 | $0.00012 | $0.00411 |
| Opus 5 | $0.00006 | $0.00205 |
| Sonnet 5 | $0.00002 | $0.00082 |
| Haiku 4.5 | $0.00001 | $0.00041 |
Grade A, and why
jobs 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 11d 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.
What it actually says
Show background /llm-review:* jobs for this repo. Reviews launched in the
background persist as files under .claude/llm-review-jobs/, so you can pick
up their output later (even from a fresh Claude Code session).
Parse $ARGUMENTS and build the engine command from separate arguments
(never splice the raw string into a shell line — a crafted job id could
otherwise inject shell metacharacters):
- a bare word matching
^\d{8}-\d{6}-[a-z0-9]+-[a-z0-9]{4}$→ that job id, passed to the engine as a positional argument --all→ pass through to the engine (show all jobs, not just recent)- anything else → reject; tell the user the expected format and stop
Then run, passing the parsed arguments as separate arguments (one per array element if invoking via JSON tool input, or each quoted separately in bash):
node "${CLAUDE_PLUGIN_ROOT}/scripts/llm-review.mjs" jobs [<id>] [--all]
Relay the output verbatim.
- No argument → a compact table of recent jobs (active first, then completed),
with id, status, provider, elapsed, started. Tell the user they can run
/llm-review:jobs <id>to see a specific review's full output. <id>argument → that job's full captured review text, verbatim. If the job is stillrunning, the partial output so far is shown — the user can re-run the command later to see more. If the jobfailed, the error is shown.
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.
- 11d ago First seen · 35 lines · 12 tokens per session scan A 1ad86f5dd2d8
jobs is a command published in the GitHub repository XinyuQu/llm-review (6 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 411 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
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.