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 architecturegit 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/architecture)<a href="https://agentmods.dev/skills/sii-holos/synergy/architecture"><img src="https://agentmods.dev/badge/skills/sii-holos/synergy/architecture/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/architecture"><img src="https://agentmods.dev/badge/skills/sii-holos/synergy/architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00064 | $0.00676 |
| Opus 5 | $0.00032 | $0.00338 |
| Sonnet 5 | $0.00013 | $0.00135 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
architecture 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 9d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trace Synergy Architecture
Orient
- Read Architecture overview and Package map.
- Select only the relevant canonical documents:
- runtime/Scope:
runtime-and-scope.md - workspace and files:
workspace-and-files.md - session/message/compaction:
session-and-messages.md,llm-loop.md - Web state:
frontend-data-sync.md - Channels and Native Clarus:
channels.md - permissions/tools:
execution-boundaries.md - delegation:
cortex.md - Plan, BlueprintLoop, Light Loop, Lattice:
workflows.md - Browser:
browser-runtime.md
- runtime/Scope:
- Read the nearest
AGENTS.mdbefore inspecting package code. - Load the focused implementation workflow when the trace becomes a change:
- Web/shared UI:
develop-frontend - LLM-backed operation:
integrate-llm - HTTP/OpenAPI/SDK contract:
change-server-api - durable state or migration:
change-persistence - capability/permission/sandbox behavior:
change-execution-boundaries - Channel runtime, managed Projects, or Native Clarus:
change-channel-runtime - Browser/Desktop/WebRTC runtime:
change-browser-runtime - plugin public/host/runtime behavior:
change-plugin-runtime
- Web/shared UI:
Trace from Evidence
- Identify the user-facing entry point: CLI command, server route, Web action, Desktop IPC, tool, Agenda trigger, Channel event, plugin hook, or migration.
- Search with
rgfor the public name, schema, event, route operation ID, storage path, and error string. - Follow the write path through ownership boundaries. Record the module that validates input, owns state, enforces capabilities, persists data, and emits events.
- Follow the read/sync path independently. For Web behavior, trace generated SDK calls, snapshot watermarks, bus events, replay, reconcile writes, and loading/eviction.
- Inspect adjacent domains before concluding that a directory boundary is the abstraction boundary.
- Verify tests and migrations that encode the behavior. Treat comments, docs, and old design files as supporting evidence only when code/tests agree.
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.
- 9d ago First seen · 56 lines · 64 tokens per session scan A b05a31e925c2
architecture is a skill published in the GitHub repository SII-Holos/synergy (548 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 676 once invoked, about $0.0003 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
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…