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 workshopgit 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/workshop)<a href="https://agentmods.dev/skills/raine/consult-llm/workshop"><img src="https://agentmods.dev/badge/skills/raine/consult-llm/workshop/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/workshop"><img src="https://agentmods.dev/badge/skills/raine/consult-llm/workshop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Anti-Refusal · line 62 Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.Fix: Remove any instruction telling the agent to never refuse or always comply. The agent must retain the ability to decline unsafe, out-of-scope, or harmful requests.
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 | $0.00054 | $0.03335 |
| Opus 5.5 | $0.00022 | $0.01334 |
| Sonnet 5.5 | $0.00011 | $0.00667 |
| Haiku 4.5 | $0.00005 | $0.00333 |
Grade A, and why
workshop 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 1mo 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 — 271 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A facilitated design session. The user brings a rough idea; the agent clarifies it through dialogue, then convenes external LLMs to propose distinct approaches in parallel; the user picks one; agent and user finalize the design, with an optional multi-LLM critique pass before saving. Use this when you have a vague idea and want expert divergence without losing the user-in-the-loop. For 1:1 design dialogue with no LLMs, use /brainstorm. For role-asymmetric advisory analysis without user interaction, use /panel.
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:
Expert flags: any --<selector> from the Models block selects an expert (e.g. --gemini, --openai, --deepseek). Repeat for multiple. Translate model flags and defaults according to the loaded consult-llm skill's model-selection rules.
Mode flags:
--max-approaches N— cap how many distinct approaches surface in Phase 2 after dedup. Default4. Min2, max5.--no-critique— skip the Phase 4 multi-LLM critique pass on the finalized design.--no-save— print the design at the end but do not write tohistory/.--consult-first— before Phase 1, fan the user's raw description out to the selected experts to surface clarifying dimensions and candidate options. Phase 1 then walks the user through those LLM-suggested questions step by step instead of starting from scratch.
Strip all flags from arguments to get the user's initial idea description. If empty, ask the user to describe their idea before continuing.
Phase 0: Load consult-llm skill
Load it now. Follow its invocation contract for every CLI call.
Phase 0.5: Consult-first (only with --consult-first)
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.
- 1mo ago First seen · 271 lines · 54 tokens per session scan A ae68b06e4825
workshop is a skill published in the GitHub repository raine/consult-llm (142 stars, last pushed 14d ago), licensed MIT. It adds 54 tokens to every session and 3,335 once invoked, about $0.0002 per session on Opus 5.5. 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.