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 Lykhoyda/ask-llm/plugin install ask-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/lykhoyda/ask-llm/ask-llm-compare)<a href="https://agentmods.dev/skills/lykhoyda/ask-llm/ask-llm-compare"><img src="https://agentmods.dev/badge/skills/lykhoyda/ask-llm/ask-llm-compare/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/lykhoyda/ask-llm/ask-llm-compare"><img src="https://agentmods.dev/badge/skills/lykhoyda/ask-llm/ask-llm-compare.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 | $0.00098 | $0.02001 |
| Opus 5.5 | $0.00039 | $0.00800 |
| Sonnet 5.5 | $0.00020 | $0.00400 |
| Haiku 4.5 | $0.00010 | $0.00200 |
Grade C, and why
ask-llm-compare scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
trap 'rm -rf "$workdir"' EXIT How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Portable contract
Send the exact same bounded prompt to two to five selected providers concurrently. Preserve input order in the result, show each response verbatim without synthesis or adjudication, and show every provider failure instead of silently dropping it. Never invoke raw provider CLIs when a canonical Ask LLM bridge is available.
Host adapters
Pi adapter
Use one native ask-multi call. Put the common prompt in prompt and two to five unique names in providers; its implementation, not model-emitted sibling calls, guarantees concurrent bounded dispatch and stable ordering.
Other hosts adapter
Codex, Cursor Agent, Antigravity, Grok Build, Gemini CLI and OpenCode get this skill from their skills folder, not from a plugin. Select two to five unique provider names, then apply the availability filtering, dispatch, and reporting steps in ../ask-llm-review/transport.md with the common prompt. Present each response verbatim and each unavailable selection or failure in the original requested order.
Claude Code adapter
The existing detailed workflow below is the Claude Code adapter. Its Agent, MCP, hook, CLAUDE_PLUGIN_ROOT, and AskUserQuestion mechanics apply only on Claude Code; they do not override the Pi adapter above.
Compare Provider Responses Side-by-Side
Send the same question to multiple LLM providers and present their responses verbatim, side-by-side. No synthesis, no consensus highlighting, no validation pipeline — just raw outputs so the user can compare directly.
This is the right tool when:
- You want to see how each provider phrases the same answer (style, depth, confidence)
- You want a sanity check before picking one provider's recommendation
- You want to evaluate which provider best fits a specific kind of question
- You explicitly want to AVOID Claude synthesizing or weighting the responses
If you want consensus extraction → use /brainstorm instead.
If you're reviewing a code diff → use /multi-review instead.
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.
- 14d ago First seen · 164 lines · 98 tokens per session scan C f2407fa1d5a2
ask-llm-compare is a skill published in the GitHub repository Lykhoyda/ask-llm (18 stars, last pushed 2d ago), licensed MIT. It adds 98 tokens to every session and 2,001 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-03.
Other skills, from other repositories
skill-provenance
Version, validate, package, verify, recover, and hand off Agent Skill bundles across local folders, registries, platform uploads, and agent sessions. Use for MANIFEST.yaml, CHANGELOG.md, bundle hashes, stale evals, frontmatter portability, derived skill packages, or version identity that must survive filename changes…
bootstrap
Add version tracking to an existing unversioned skill bundle. Use when you have a skill project with SKILL.md but no MANIFEST.yaml, no version headers, and no changelog. Creates the initial manifest, adds version metadata to files, and generates the first changelog entry. Triggers on: "bootstrap this skill", "add…
close
Update version tracking when finishing work on a skill bundle. Use when you're done editing a skill project and need to bump version headers, recompute manifest hashes, update the changelog, flag stale files, or prepare a commit message. Triggers on: "close the session", "update versions", "save the bundle", "I'm done…
validate
Run a focused validation check for a skill bundle. Use when the user asks to validate, verify hashes, check MANIFEST.yaml, confirm files are present, or distinguish a canonical bundle from a derived install or registry copy without opening or closing a full editing session.
open
Verify a skill bundle's integrity when opening a project. Use when loading a skill project directory and you need to check file completeness, verify SHA-256 hashes against MANIFEST.yaml, detect stale files, review recent changes, or understand what state the bundle is in before starting work. Triggers on: "open this…
handoff
Generate a handoff note summarizing skill project state for a future session or collaborator. Use when crossing a non-persistent boundary (e.g., Chat upload), ending a session that made significant decisions, or when the user explicitly asks for a handoff note. Triggers on: "generate a handoff", "write a handoff…