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 raine/consult-llm --skill review-panelgit clone --depth 1 https://github.com/raine/consult-llmWrote 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/raine/consult-llm/review-panel)<a href="https://agentmods.dev/skills/raine/consult-llm/review-panel"><img src="https://agentmods.dev/badge/skills/raine/consult-llm/review-panel/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/raine/consult-llm/review-panel"><img src="https://agentmods.dev/badge/skills/raine/consult-llm/review-panel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 183 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00039 | $0.02555 |
| Opus 5 | $0.00019 | $0.01277 |
| Sonnet 5 | $0.00008 | $0.00511 |
| Haiku 4.5 | $0.00004 | $0.00255 |
Grade A, and why
review-panel 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 10d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run a standalone multi-model review of a diff. Reviewers receive the same prompt independently; the agent synthesizes duplicate findings into a prioritized checklist and can optionally apply unambiguous fixes.
Load the consult-llm skill before proceeding — it defines the invocation contract (stdin heredoc, flags, output format, multi-model calls). Do not call the CLI without loading it first.
Available models
Selectors resolvable in this environment (depends on configured API keys):
!`consult-llm models`
Argument handling
Arguments: $ARGUMENTS
Check $ARGUMENTS for flags:
Reviewer flags: any --<selector> from the Models block above selects that reviewer (e.g. --gemini, --openai, --deepseek). Repeat for multiple. Translate model flags and defaults according to the loaded consult-llm skill's model-selection rules.
Diff flags:
--diff-base <ref>— base ref for review. Default is auto-detected so a feature branch is reviewed in full (see Phase 1 for the resolution order). Pass an explicit ref (HEAD,HEAD~3, a branch name, a SHA) to override.--fix— opt in to applying unambiguous localized fixes formust-fixfindings. Default is read-only report.
Strip all flags from arguments to get any user-supplied review focus. If no focus remains, review for correctness, regressions, security, and maintainability.
Phase 0: Load consult-llm skill
Load it now. Follow its invocation contract for all CLI calls in this workflow.
Phase 1: Identify changed files
Resolve <diff-base>:
- If
--diff-basewas passed, use it as-is. - Otherwise detect the repo's main branch (
git symbolic-ref refs/remotes/origin/HEAD→ striprefs/remotes/origin/, fall back tomainthenmaster) and usegit merge-base HEAD <main>(preferorigin/<main>if it exists locally, else the local<main>). The branch may not be pushed and may have no upstream — don't rely on@{upstream}. - If HEAD has no divergence from the resolved base (already on the main branch), fall back to
<diff-base>=HEADso the skill still reviews uncommitted changes. - Stacked branches and feature-off-feature workflows are not auto-detected — pass
--diff-base <parent>explicitly in those cases.
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.
- 10d ago First seen · 215 lines · 39 tokens per session scan A 2794d2f73f1e
review-panel is a skill published in the GitHub repository raine/consult-llm (133 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 2,555 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…