Capsule Development

Capsule Development is a skill for Claude Code, Codex from unicity-aos/aos-ce. It costs 21 tokens per session (2,362 once invoked), scanned A, original, Apache-2.0.

A development guide for Unicity AOS capsules, which are Rust programs compiled to WebAssembly and run inside a restricted Astrid Runtime environment. It covers the current project structure, security manifest, host access, and build target.

In plain words
What is it for?
Use it to create a new capsule, declare which messages it may send or receive, build it for the required WebAssembly target, and run the project's quality checks.
Why use it?
It helps developers avoid obsolete capsule formats and configure the compiler, permissions, and communication rules correctly. It also lists checks for building, testing, documenting, installing, and debugging a capsule.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create a new capsule, declare which messages it may send or receive, build it for the required WebAssembly target, and run the project's quality checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/unicity-aos/aos-ce/capsule-development
About the project

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.

unicity-aos/aos-ce · 8,460 stars · on GitHub

Install

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.

Any agent
npx skills add unicity-aos/aos-ce --skill capsule-development
Clone the repo
git clone --depth 1 https://github.com/unicity-aos/aos-ce

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for Capsule Development

README.md
[![agentmods](https://agentmods.dev/badge/skills/unicity-aos/aos-ce/capsule-development/github.svg)](https://agentmods.dev/skills/unicity-aos/aos-ce/capsule-development)
Your own site
<a href="https://agentmods.dev/skills/unicity-aos/aos-ce/capsule-development"><img src="https://agentmods.dev/badge/skills/unicity-aos/aos-ce/capsule-development/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.

agentmods 80×15 button for Capsule Development

Your own site · 80×15
<a href="https://agentmods.dev/skills/unicity-aos/aos-ce/capsule-development"><img src="https://agentmods.dev/badge/skills/unicity-aos/aos-ce/capsule-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,362 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 Rogue Agent · line 109
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.02362
Opus 5 $0.00010 $0.01181
Sonnet 5 $0.00004 $0.00472
Haiku 4.5 $0.00002 $0.00236

Measured 11d ago against content hash ff515f18152a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

Capsule Development 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 11d 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.

capsules/capsule-system/src/skills/capsule-development/SKILL.md · 294 lines

How it starts

The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capsule Development

A capsule is a Rust WebAssembly component that runs inside the Astrid Runtime sandbox shipped by Unicity AOS. The runtime routes IPC, enforces capabilities, mediates host access, and audits execution. Business logic belongs in capsules.

The manifest is part of the security boundary. Its [publish] and [subscribe] tables are the IPC access-control list: a topic that is not declared is denied. Capsules target wasm32-unknown-unknown, not WASI, and reach the host only through the audited SDK/WIT imports granted by the manifest.

Start from the supported scaffold

aos capsule new my-capsule
cd my-capsule

The generated project contains:

my-capsule/
├── .cargo/config.toml
├── rust-toolchain.toml
├── Cargo.toml
├── Capsule.toml
└── src/lib.rs

Do not begin from an old [[interceptor]] manifest or an ipc_publish / ipc_subscribe capability array. Those formats are obsolete.

Compiler target

.cargo/config.toml selects the capsule target and activates the SDK's custom randomness backend:

[build]
target = "wasm32-unknown-unknown"

[target.wasm32-unknown-unknown]
rustflags = ["--cfg=getrandom_backend=\"custom\""]

The getrandom_backend setting must live in the final capsule crate. Without it, dependencies such as UUID generators or randomized hash maps can fail to link.

Pin the toolchain and target in rust-toolchain.toml:

[toolchain]
channel = "1.94.0"
targets = ["wasm32-unknown-unknown"]
components = ["rustfmt", "clippy"]

Cargo package

Use a cdylib and the current 0.7 SDK surface:

[package]
name = "my-capsule"
version = "0.1.0"
edition = "2024"
publish = false

[lib]
crate-type = ["cdylib"]

[dependencies]
astrid-sdk = { version = "0.7", features = ["derive"] }
serde = { version = "1.0", features = ["derive"] }
serde_json = "1.0"

[profile.release]
opt-level = "z"
lto = true
codegen-units = 1
strip = true
panic = "abort"

Capsule manifest

This minimal tool capsule exposes one hello tool:

Read the full file on GitHub · 294 lines

Changes

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.

  1. 11d ago First seen · 294 lines · 21 tokens per session scan A ff515f18152a

Subscribe to this mod's changes

Capsule Development is a skill published in the GitHub repository unicity-aos/aos-ce (8,460 stars, last pushed today), licensed Apache-2.0. It adds 21 tokens to every session and 2,362 once invoked, about $0.0001 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.

Related

Other skills, from other repositories