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 SII-Holos/synergy --skill integrate-llmgit clone --depth 1 https://github.com/SII-Holos/synergyWrote 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/sii-holos/synergy/integrate-llm)<a href="https://agentmods.dev/skills/sii-holos/synergy/integrate-llm"><img src="https://agentmods.dev/badge/skills/sii-holos/synergy/integrate-llm/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/sii-holos/synergy/integrate-llm"><img src="https://agentmods.dev/badge/skills/sii-holos/synergy/integrate-llm.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 Prompt Injection · line 10 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00080 | $0.02952 |
| Opus 5 | $0.00040 | $0.01476 |
| Sonnet 5 | $0.00016 | $0.00590 |
| Haiku 4.5 | $0.00008 | $0.00295 |
Grade A, and why
integrate-llm 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 yesterday.
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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integrate an LLM Call
Choose the Execution Path First
| Required behavior | Path |
|---|---|
| Derive metadata, classify, summarize, or transform without durable work history | Sessionless internal-agent call through the shared LLM layer |
| Continue work already owned by a product session | SessionInvoke / the existing session loop |
| Run bounded delegated or reviewed work with lineage, lifecycle, progress, cancellation, and an output contract | Cortex.launch() child session |
| Probe a provider before normal agent/session runtime is available | Narrow direct AI SDK call in setup/probe infrastructure |
Do not choose by convenience. If users or parent agents must inspect, resume, cancel, audit, or receive the work as a task, it belongs in a session. If the result is only derived data and a transcript would be noise, keep it sessionless.
Sessionless Internal-Agent Calls
Text-only sessionless callers use AgentCall.text() without creating a durable session. The Control Plane records call intent, semantic requests, consumed stream events, and SDK usage under the owning session or a Scope operation. Provider transport attempts are captured separately at the final built-in fetch boundary, with worker chunks committed by the Control Plane before acknowledgement. Preserve explicit completeness status; semantic events alone do not prove transport capture. Title/turn summary, SmartAllow classification, agent generation, GitHub classification, and Experience encoding all use the external AgentTurn worker boundary. Product code must not add a direct LLM.stream() caller outside session/agent-turn/runner.ts; setup/provider bootstrap probes are the only narrow direct AI SDK exception.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday Changed · +12 lines e52a17e6346e
- 3d ago Changed · +2 lines 4ae1b0757328
- 10d ago First seen · 96 lines · 80 tokens per session scan A ca5f3a22f55d
integrate-llm is a skill published in the GitHub repository SII-Holos/synergy (490 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 2,952 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 2026-08-30.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
enhance-prompt
Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
seedance-vocab-en
This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…