AOS Community Edition is an open operating system for AI agents, providing the command-line tool, HTTP API, bundled agent components, model-provider setup, and audit features that make up its product environment. It is for people who want to inspect and compose agent workflows.
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 unicity-aos/aos-ce --skill capsule-forgegit clone --depth 1 https://github.com/unicity-aos/aos-ceWrote 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/unicity-aos/aos-ce/capsule-forge)<a href="https://agentmods.dev/skills/unicity-aos/aos-ce/capsule-forge"><img src="https://agentmods.dev/badge/skills/unicity-aos/aos-ce/capsule-forge/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/unicity-aos/aos-ce/capsule-forge"><img src="https://agentmods.dev/badge/skills/unicity-aos/aos-ce/capsule-forge.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 | $0.00087 | $0.01652 |
| Opus 5 | $0.00044 | $0.00826 |
| Sonnet 5 | $0.00017 | $0.00330 |
| Haiku 4.5 | $0.00009 | $0.00165 |
Grade A, and why
capsule-forge 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 12d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build naturally on Unicity AOS
Unicity AOS is the operating system for agents. Astrid Runtime supplies the sandbox, typed IPC, principal scope, capability enforcement, metering, and audit. Intelligence belongs in user space: instructions, skills, memory, harnesses, capsules, providers, connectors, and their composition.
Forge is the construction workbench. Use it when work needs a new executable ability or when an existing capsule must be understood, repaired, or extended.
Start with the artifact, not the code
Choose the smallest durable answer:
- discover or configure an existing ability;
- remember a fact or standing preference;
- write a Skill for reusable reasoning or procedure;
- improve harness code for context, retrieval, planning, or recovery;
- compose existing typed services;
- build a capsule for new governed executable behavior;
- add an optional worker only when the host supports it and durable independent work makes it useful;
- add a host plugin only for client-native discovery, hooks, commands, or MCP adaptation.
Load the meta-harness Skill when the opportunity arose proactively from real
work or the agent is improving its own user-space world.
Load the manual progressively
Call forge_guide with no topic to list the exhaustive author manual. Then load
only the chapters required by the current decision. A host plugin may vendor
the same chapters under references/<topic>.md; use that offline snapshot when
the Forge tool is unavailable.
| Topic | Load when |
|---|---|
foundations |
choosing an artifact or explaining AOS versus Astrid, capsules, harnesses, and plugins |
workspace |
deciding where source belongs on this machine or in a repository |
capsule |
writing Rust macros, SDK calls, lifecycle hooks, state, or principal-scoped behavior |
manifest |
authoring any Capsule.toml section or packaged asset |
capabilities |
selecting or reviewing host authority and VFS scope |
ipc |
tools, topics, wildcard matching, handlers, fan-out, middleware, layering, or priority |
wit |
imports, exports, typed payloads, providers, or a new contract |
skills |
shipping instructions, progressive references, precedence, or a host plugin |
authority |
deciding whether to draft, install, replace, grant, persist, or activate |
build |
scaffold, check, build, install, test, diagnose, upgrade, remove, or release |
security |
adversarial review, failure behavior, limits, isolation, or evaluation |
meta-harness |
building a proactive self-extension loop from the ground up |
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.
- 12d ago First seen · 155 lines · 87 tokens per session scan A f3bea63f2c09
capsule-forge is a skill published in the GitHub repository unicity-aos/aos-ce (8,460 stars, last pushed yesterday), licensed Apache-2.0. It adds 87 tokens to every session and 1,652 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
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…