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 skills/kaydenclark/llm_workbench/ask-workbenchnpx skills add KaydenClark/LLM_Workbench --skill ask-workbenchgit clone --depth 1 https://github.com/KaydenClark/LLM_WorkbenchWrote 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/kaydenclark/llm_workbench/ask-workbench)<a href="https://agentmods.dev/skills/kaydenclark/llm_workbench/ask-workbench"><img src="https://agentmods.dev/badge/skills/kaydenclark/llm_workbench/ask-workbench.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 | $0.00017 | $0.00288 |
| Opus 5 | $0.00009 | $0.00144 |
| Sonnet 5 | $0.00003 | $0.00058 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
ask-workbench 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 5d 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
Use the selected catalog in ../README.md to recommend one
starting skill and, when useful, the short sequence after it. Ask one question
only when two routes would produce materially different work. Wait for the user
to ask before starting the recommended skill.
Default routes:
- new greenfield project from a founding prompt:
/genesis; - existing project adopts the Workbench for the first time:
/adoption; - routine harness update for an adopted project:
/update-harness; - unclear idea or unresolved product decisions:
/grill-me; - concise live orientation:
/sitrep; - settled conversation needs updates to existing documentation:
/to-docs; - settled conversation needs a durable work packet:
/to-spec; - a spec needs executable slices:
/to-tickets; - one eligible spec slice is ready for delivery:
/implement; - a fixed implementation diff needs independent findings:
/code-review; - skill authoring rules are needed:
/writing-great-skills.
The main delivery flow is:
grill-me -> to-docs or to-spec -> to-tickets -> implement -> code-review
The selected catalog also preserves pending rewrites outside live discovery.
Recommend only entries marked Active in the catalog.
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.
- 5d ago First seen · 32 lines · 17 tokens per session scan A 996bc38abf67
ask-workbench is a skill published in the GitHub repository KaydenClark/LLM_Workbench (2 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 288 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…