Workspace ConventionsSAFE
wanman is an open-source agent matrix runtime inspired by Japanese one-man trains. It lets human users step back into an observer role while local agent runtimes coordinate autonomous multi-agent workflows, task execution, and artifacts.
Overview
wanman is an open-source agent matrix runtime inspired by Japanese one-man trains. It lets human users step back into an observer role while local agent runtimes coordinate autonomous multi-agent workflows, task execution, and artifacts.
f0c3ec2eb827OBSERVED · 2026-10-13What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: workspace-conventions
description: File and output conventions for agent workspaces
---
# Workspace Conventions
## Directory Structure
Each agent's working directory is `/workspace/agents/{agent-name}/`.
**Rule: Only write files within your own working directory.**
```
/workspace/agents/
├── ceo/ ← CEO's working directory
├── marketing/ ← Marketing agent
├── finance/ ← Finance agent
├── feedback/ ← Feedback/research agent
├── dev/ ← Dev agent
└── devops/ ← DevOps agent
```
## Output File Naming
| Type | Naming | Example |
|------|--------|---------|
| Report | `{topic}-report.md` | `budget-report.md` |
| Brand guide | `brand-guide.md` | |
| Content plan | `{platform}-plan.md` | `social-media-plan.md` |
| Web page | `index.html` | |
| Design | `{name}-brief.md` | `poster-brief.md` |
## Cross-Agent References
When a task description references another agent's output, use the full path:
```
See brand guide at /workspace/agents/marketing/brand-guide.md
```
## Agent Name Identifier
When using `wanman artifact put`, the system automatically records the agent name. Ensure the environment variable `WANMAN_AGENT_NAME` is correctly set.
## Task Completion Checklist
1. Write key data to artifacts (`wanman artifact put`)
2. Write detailed reports to MD files
3. Mark the task as done with `wanman task done`, noting the number of artifacts in the resultTrust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
f0c3ec2eb827full audit observations/trust-audit/skill/chekusu__workspace-conventions.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-13 | f0c3ec2eb827 | SAFE | B | 89 | first audit |
Questions
What does the Workspace Conventions skill do?
wanman is an open-source agent matrix runtime inspired by Japanese one-man trains. It lets human users step back into an observer role while local agent runtimes coordinate autonomous multi-agent workflows, task execution, and artifacts.
Is Workspace Conventions safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Workspace Conventions access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (f0c3ec2eb827), read on 2026-10-13. The repository is watched, and a new audit runs when it changes — this is the first audit.