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/kimmingul/xllm/asknpx skills add kimmingul/xllm --skill askgit clone --depth 1 https://github.com/kimmingul/xllmWrote 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/kimmingul/xllm/ask)<a href="https://agentmods.dev/skills/kimmingul/xllm/ask"><img src="https://agentmods.dev/badge/skills/kimmingul/xllm/ask.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 | $0.00086 | $0.01070 |
| Opus 5 | $0.00043 | $0.00535 |
| Sonnet 5 | $0.00017 | $0.00214 |
| Haiku 4.5 | $0.00009 | $0.00107 |
Grade A, and why
ask 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 3d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ask — Single-provider headless advisor
Get one authentic external model opinion. Always go through the advisor script.
Resolve the advisor script (mandatory)
Pick the first that exists:
- Contents of
.xllm/xllm-advisor-path(legacy:.grok/xllm-advisor-path) $XLLM_ADVISOR_PATH(legacy$XLLM_ADVISOR_PATH)$GROK_PLUGIN_ROOT/scripts/xllm-advisor.jsor$XLLM_PLUGIN_ROOT/scripts/…./scripts/xllm-advisor.js(plugin repo or vendored copy)
If none exist: tell the user to run /xllm-setup or
node <plugin-checkout>/scripts/xllm.mjs remember from this project. Do not invent CLI flags.
Discovery helpers:
node <advisor.js> --which
node <advisor.js> --remember
node <advisor.js> --doctor
node <advisor.js> --list-providers
Spec syntax
provider
provider:model
provider@effort
provider:model@effort
Examples: codex@high, claude:opus@medium, grok:grok-4.5@high,
antigravity:gemini-3.6-flash-high, ollama:qwen3.6:latest, ollama:qwen3.6:latest@low
Profiles / defaults: .xllm/xllm-providers.toml (legacy .grok/ honored)
(design side prefers antigravity on every platform; the standalone gemini
CLI is substituted in only when agy is not on PATH — and vice versa)
Safety defaults
- Advisors run read-only: no approval bypass, no sandbox escape. Opt in to
mutating advisors only when the user explicitly asks:
--allow-write(orXLLM_ALLOW_MUTATION=1). - Same-provider advising inside that provider's own CLI is refused
(
--allow-selfto override). - Artifacts persist prompts/outputs with secret redaction;
--no-artifactsprints instead of writing.
Supported providers
| Kind | Spec | Model / effort |
|---|---|---|
| Cloud | codex |
-m model, effort via -c model_reasoning_effort= |
| Cloud | claude |
--model, --effort |
| Cloud | grok |
-m, --reasoning-effort |
| Cloud | antigravity (preferred over gemini) |
--model, --effort low|medium|high |
| Cloud | gemini |
--model (used only when agy is not installed) |
| Cloud | cursor |
--model when set |
| Local | ollama[:model] |
model required-ish (default from profile/env) |
| Local | lmstudio[:model] |
OpenAI body model + optional effort field |
| Local | lemonade |
LEMONADE_BIN |
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.
- 3d ago First seen · 113 lines · 86 tokens per session scan A 7caa0a6b70a1
ask is a skill published in the GitHub repository kimmingul/xllm (2 stars, last pushed 11d ago), licensed MIT. It adds 86 tokens to every session and 1,070 once invoked, about $0.0004 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
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
research
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make…
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).