opencode-agent-creator
Create, revise, or debug OpenCode agent definitions and teams: Markdown/JSON configuration, permissions, model routing, discovery, and native Task delegation.
v2026.11.13-21cd5682 installs+2 in 7 days39 StarsMITsynced 11 hours ago
Install
No NotHoly CLI yet? Install it first.
$ curl -fsSL https://notholy.com/install.sh | sh$ notholy skills install aeondave/opencode-agent-creatorWrites to ~/.notholy/skills after checking the signature and the SHA-256.
SignatureSigned, ed25519
Package9d26f4ef…b1daa8e4
9d26f4eff368…f7a0b1daa8e413 files · 10.0 KBScanMedium2 findings
- injection.no_confirmationreferences/agent-config-reference.md:67
- Links to outside domains
Sourcegithub.com/AeonDave/malskill/tree/main/harness-dev/opencode-agent-creator@21cd568
Create the smallest agent definition or roster that handles the requested work. Prefer project-local .opencode/agents/ unless another scope is requested. Preserve existing agent identities, permissions, and user decisions.
Use agent-md-creator for repository instructions, skill-creator for portable skills, and claude-agents-creator for Claude Code subagents. Use opencode-plugin-creator for custom tool or plugin implementations.
Workflow
- Run
opencode --version; inspect the existing project configuration and requested agent scope. These instructions target stable v1.18.35. For a different release or V2 target, verify its actual schema and runtime first. - Choose one bounded specialist, or a primary supervisor plus the needed specialists. Reuse an available built-in when it already fits. Load multi-agent-topologies.md when choosing a team shape.
- Give each custom agent a concise routing description, explicit mode, task-specific prompt, and appropriate permissions. Keep one definition per agent. Load agent-config-reference.md when writing fields, resolving discovery, or configuring nested delegation.
- Start from agent-template.md or supervisor-template.md. The examples form a read-only review team; add a real write-capable worker when implementation is required.
- Leave
modelunset to inherit, or pin a model verified byopencode models. Load model-tiering.md when choosing model policies or investigating a failed dispatch. Task has no per-dispatch model parameter. - Give workers the target, constraints, relevant context, and expected result in each dispatch. A fresh child does not receive the parent's conversation; a resumed child retains its own history. Load orchestrator-pattern.md for packets, task resumption, and experimental background work.
- Enforce capabilities with permissions.
hiddencontrols autocomplete visibility, not access. Keep leaf workers attask: deny; configure depth and task permissions explicitly for intentional nested delegation. A read-only supervisor can dispatch a write-capable worker, so constrain each worker separately. - Reload the definitions and inspect
opencode agent list. Test routing, the promised permission boundary, the returned result, and any resume/background behavior used. Load triggering-and-testing.md before completion.
Report the files changed, target OpenCode version, checks actually run, and any untested model or delegation behavior. File/schema validation alone does not prove model routing or tool enforcement.
Load plugins-and-tools.md when an agent needs a custom tool, plugin, or launch-time secret; it routes implementation work to the plugin skill.
Files in this version
assets/65.8 KB
examples/43.7 KB
- code-reviewer.md820 B
- researcher.md920 B
- summarizer.md740 B
- supervisor.md1.2 KB
- agent-template.md895 B
- supervisor-template.md1.3 KB
references/618.6 KB
- agent-config-reference.md7.8 KB
- model-tiering.md1.9 KB
- multi-agent-topologies.md1.7 KB
- orchestrator-pattern.md3.4 KB
- plugins-and-tools.md1.4 KB
- triggering-and-testing.md2.3 KB
- SKILL.md3.4 KB
Permissions
| Permission | Declared | Found by the scan |
|---|---|---|
| Reads files | No | No |
| Writes files | No | No |
| Runs shell commands | Yes | Yes |
| Uses the network | Yes | Yes |
| Uses connectors | No | No |
| Drives a browser | No | No |
Scan findings
Reviewed on Nov 13, 2026
- MediumPrompt injection · injection.no_confirmationreferences/agent-config-reference.md:67
- InfoLink · Links to outside domains
A clean scan lowers the risk but does not prove a package is safe. Read what you install.
| Version | Published | Commit | SHA-256 | Signature | Permission change |
|---|---|---|---|---|---|
| v2026.11.13-21cd568 | Nov 13, 2026 | 21cd568 | 9d26f4ef | Signed | – |
More from AeonDave
All from this publisherMore in Reporting and compliance
See the category- skillduty1g/skill5
- rea-ci-tests-auditmorluto/rea-ci-tests-audit4
- tracking-threat-actor-infrastructuremukul975/tracking-threat-actor-infrastructure4
- performing-authenticated-scan-with-openvasmukul975/performing-authenticated-scan-with-openvas4
- slicing-code-contexttrailofbits/slicing-code-context4
- 1337aeondave/13374
Ask anything your scope allows.
Create an account, add credits and ask the first question in the chat or the terminal.
- 1/3
Create the account
Individual or company. You can switch to a company later without losing balance or keys.
IndividualCompany - 2/3
Add credits
By card. Pay per token, no subscription.
$5.00minimum deposit - 3/3
Ask
In the chat, or install the CLI and run notholy login in your terminal.
$ notholy login