Ready-to-copy prompts under specialized-agents/system-prompts/:
- code-reviewer-prompt.md (subagent, read-only)
- security-reviewer-prompt.md (subagent, read-only, CWE-aware)
- backend-engineer-prompt.md (primary or all)
- frontend-engineer-prompt.md (primary or all)
- tech-lead-prompt.md (primary, opus-tier)
- database-engineer-prompt.md (Postgres-first, adapts)
- ux-engineer-prompt.md (design-system-first)
Matching one-page descriptions in specialized-agents/descriptions/.
Every prompt opens with a "one defensible set of opinions, not the only
right answer" disclaimer so readers don't treat them as authoritative.
Stack-specific defaults (Tailwind, FastAPI, Postgres) are explicitly
overridable per project.
To install one:
cp specialized-agents/system-prompts/code-reviewer-prompt.md \
.opencode/agents/code-reviewer.md
or reference via {file:...} from opencode.json without copying.
4.3 KiB
Specialized Agents
Starting points, not authoritative wisdom. These are one set of defensible defaults for common engineering roles — copy them to
.opencode/agents/<name>.mdand edit them to match your stack, your conventions, and your taste. They encode opinions that a senior engineer on your team might disagree with, which is fine — the value is having a coherent starting point, not in any one rule being universally right.
When something in a prompt says "always X, never Y," read it as "by default, X — but override per project in your
AGENTS.mdif Y is correct for you."
How to use
Each role has:
- A system prompt under
system-prompts/— copy verbatim or as a starting point - A short description under
descriptions/— what the role focuses on and when to reach for it
To install one in your project:
mkdir -p .opencode/agents
cp specialized-agents/system-prompts/code-reviewer-prompt.md .opencode/agents/code-reviewer.md
The filename you choose becomes the agent's mention name (@code-reviewer).
You can also reference the prompt file from opencode.json without copying:
{
"agent": {
"code-reviewer": {
"description": "Senior code reviewer",
"mode": "subagent",
"model": "anthropic/claude-sonnet-4-5",
"prompt": "{file:./specialized-agents/system-prompts/code-reviewer-prompt.md}",
"permission": { "edit": "deny" }
}
}
}
Available roles
| Role | Mode | Reach for it when… | Prompt | Description |
|---|---|---|---|---|
| Code Reviewer | subagent | Surface bugs / security / perf / maintainability in a diff or branch | prompt | description |
| Security Reviewer | subagent | Audit code for OWASP-style vulnerabilities | prompt | description |
| Backend Engineer | primary | TypeScript/Go/Python API work, DB integration, REST/GraphQL | prompt | description |
| Frontend Engineer | primary | React/Tailwind/TypeScript UI work, accessibility, component design | prompt | description |
| Tech Lead | primary | Architectural decisions, cross-team trade-offs, sequencing work | prompt | description |
| UX Engineer | primary | Component-first UI work, design-system alignment | prompt | description |
| Database Engineer | primary | Schema design, migrations, query performance | prompt | description |
💡 These are starting points. Edit the prompts to match your stack — replace generic guidance with your actual conventions, technologies, and naming.
Patterns
Sequential review
[build] > implement the OAuth refresh endpoint
[build] > @code-reviewer review the changes
[build] > @security-reviewer audit the same files
[build] > address the high-severity findings
Parallel research
> @backend-engineer propose a migration plan for the payments service
> @database-engineer review the schema implications
> @tech-lead decide which proposal to ship
Persistent specialist primary
For ongoing work in a single area, install a role as a primary agent (mode: primary or mode: all) so it's a Tab target.
cp specialized-agents/system-prompts/frontend-engineer-prompt.md .opencode/agents/frontend.md
# Edit the frontmatter to `mode: primary`, then Tab in the TUI cycles
# [build] ↔ [plan] ↔ [frontend]
Customizing
Three things to adapt before using these in earnest:
- Tech stack lines — the prompts mention "TypeScript, React, Tailwind" etc. Replace with your actual stack.
- Repo-specific conventions — point at your
AGENTS.mdand let it carry the conventions. - Permission profiles — every role's permission map is conservative by default. Loosen
bashpatterns for commands your team runs constantly.
The prompts are MIT-licensed (same as the repo). Fork them.