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 agents/kivo360/omoios/workspace_isolation_systemgit clone --depth 1 https://github.com/kivo360/OmoiOSWrote 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/agents/kivo360/omoios/workspace_isolation_system)<a href="https://agentmods.dev/agents/kivo360/omoios/workspace_isolation_system"><img src="https://agentmods.dev/badge/agents/kivo360/omoios/workspace_isolation_system.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 | $0.00000 | $0.02304 |
| Opus 5 | $0.00000 | $0.01152 |
| Sonnet 5 | $0.00000 | $0.00461 |
| Haiku 4.5 | $0.00000 | $0.00230 |
Grade A, and why
workspace_isolation_system 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 5d 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 — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workspace Isolation System Documentation
Created: 2025-11-20 Status: Draft Purpose: Technical design and API specification for the Workspace Isolation System that provides isolated, Git-backed workspaces for Hephaestus agents. Related: docs/design/agents/agent_manager.md, docs/design/services/workspace_manager.md, docs/design/database_schema.md, docs/design/configuration_guide.md, docs/architecture/adr_workspace_isolation.md
Overview
The Workspace Isolation System provides automatic workspace isolation for Hephaestus agents, enabling parallel agent execution without conflicts. Each workspace maintains its own filesystem, execution environment, and Git-managed state, while remaining completely transparent to agents — they are never aware that isolation or Git operations occur behind the scenes.
Workspaces act as the foundational execution environment for agents and support:
- Local directory workspaces
- Git-backed workspaces
- Container-backed workspaces (future)
- Remote execution workspaces (future)
Key Features
- Complete Transparency: Agents do NOT know they are running in isolated workspaces.
- Git-Backed Snapshots: Each workspace is tied to a Git branch with automated commit history.
- Zero Conflicts: Parallel agents operate independently without overwriting each other's work.
- Knowledge Inheritance: Child workspaces inherit the exact Git state and filesystem contents of their parents.
- Automatic Merge Resolution: The system uses a deterministic "newest file wins" strategy.
- Clean Experimentation: Every workspace has its own branch; experiments never pollute the main branch.
- Pluggable Execution Environment: Future support for containerized or remote workspace types.
Problem Solved
When multiple agents modify the same repository simultaneously, they create:
- race conditions
- file conflicts
- overwritten commits
- polluted repository state
- unclear history of changes
The Workspace Isolation System solves all of this by providing each agent with a safe, isolated workspace backed by Git and unified through a WorkspaceManager.
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.
- 5d ago First seen · 414 lines · 0 tokens per session scan A 76d5da732bfd
workspace_isolation_system is an agent published in the GitHub repository kivo360/OmoiOS (76 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,304 tokens. 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 agents, from other repositories
assistant
You are a general-purpose assistant — the example agent that ships with Archie so a fresh install does something useful out of the box. You handle small, self-contained requests: summarizing a block of text, drafting a short reply, or explaining something plainly.
gatekeeper
You exist to exercise the MCP tool approval gate in end-to-end checks. When asked to call your tools, call them exactly as instructed and report exactly what they returned — no improvisation, no retries beyond what the instructions say.
pm
This is the example PM overlay. The text here is appended to the PM agent's system prompt, so use it to give the PM the standing context it needs for your organization — what the company/team does, who the regular requesters are, house style for replies, and any defaults that should hold across every conversation.
ralph-loop-runner
Use this agent when you need to execute a Ralph orchestration loop end-to-end and verify its completion. This includes testing prompts against the Ralph system, validating that orchestration completes successfully, and capturing both results and any runtime issues. Examples:\n\n \nContext: User wants to test if a…
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
tester
테스트 작성 전담 에이전트. 단위/통합/E2E 테스트를 설계하고 구현하며, 커버리지 목표 달성을 책임진다.