Write Agent
Create or revise the core assets for an Agent Hub agent, including soul, bundle, and optional profile.
Install
$ agentstack add skill-sdwolf4103-opencode-agenthub-write-agent ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-sdwolf4103-opencode-agenthub-write-agent) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
write-agent
Purpose
Author the asset set for a new Agent Hub agent role: a soul, a bundle, and optionally a profile. This skill handles direct asset authoring; HR handles staffing, sourcing, staging, and team assembly.
Workflow
- Gather the role's purpose, scope, runtime mode, tools, and expected collaboration pattern.
- Decide whether the result is primarily a visible primary agent or a subagent-oriented helper.
- Draft the soul with purpose, behavior contract, boundaries, and output style.
- Draft the bundle JSON that binds the soul to runtime settings, permissions, skills, and model policy.
- Optionally create or update a profile when the new bundle should be launchable as part of a named team.
- Verify that soul, bundle, and profile references line up exactly.
- If composition is uncertain, use scaffold helpers or assembly checks such as
agenthub new soul,agenthub new bundle,agenthub new profile, andagenthub start --assemble-only.
Core concepts
| Asset | What it does | |---|---| | soul | Defines identity, behavior, boundaries, and response style | | bundle | Connects a soul to runtime settings, skills, permissions, and agent metadata | | profile | Groups bundles into a launchable team and may set defaultAgent |
Relationship to HR
- HR is for staffing, sourcing, candidate review, staging, and package assembly.
write-agentis for direct asset authoring outside the HR pipeline.- This skill is not itself a soul, agent class, or HR worker.
Anti-patterns
- Creating a soul without a matching bundle.
- Hard-coding a model without a user request or clear policy reason.
- Adding guards reflexively instead of matching actual risk.
- Creating circular subagent relationships.
- Treating a profile as mandatory when only a bundle is needed.
Verification
- Confirm the bundle references the intended soul.
- Confirm every listed skill and instruction exists.
- If a profile is added, verify its bundle list and
defaultAgent. - Use
agenthub start --assemble-onlywhen you need proof that composition succeeds.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: sdwolf4103
- Source: sdwolf4103/opencode-agenthub
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.