hivellm/Opencode
templates/skills/cli/opencode/SKILL.md
OpenCode (open-source terminal coding agent by SST). Reads AGENTS.md natively. Rulebook generates opencode.json plus .opencode/commands, .opencode/agents, .opencode/skills.
$ install --global
skillsauthnpx skillsauth add hivellm/rulebook OpencodeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 7, 2026, 3:03 AM136.9s1 file scanned
SKILL.md
- name:
- Opencode
- description:
- OpenCode (open-source terminal coding agent by SST). Reads AGENTS.md natively. Rulebook generates opencode.json plus .opencode/commands, .opencode/agents, .opencode/skills.
- version:
- 1.0.0
- category:
- cli
- author:
- Rulebook
- tags:
- ["cli", "opencode", "agents", "mcp"]
- dependencies:
- []
- conflicts:
- []
<!-- OPENCODE:START -->
OpenCode Rules
Tool: OpenCode — open-source terminal coding agent.
Generated surface area
When Rulebook detects OpenCode (opencode.json / .opencode/ / opencode
binary on PATH), it generates:
opencode.jsonwith$schema,mcp.rulebook, andinstructions. Existing user keys (model, theme, permission, custom agents) are preserved..opencode/commands/<name>.mdfor every user-invocable Rulebook slash command, with OpenCode-shaped frontmatter (description)..opencode/agents/<role>.mdfor every Rulebook role agent (researcher, implementer, tester, code-reviewer, architect, docs-writer, security-reviewer, build-engineer, team-lead, etc.) with model tier mapped (haiku → claude-haiku-4-5,sonnet → claude-sonnet-4-6,opus → claude-opus-4-7) and a synthesizedpermissionblock..opencode/skills/<normalized-name>/SKILL.mdfor every Rulebook dev skill, name-normalized to[a-z0-9](-[a-z0-9])*(≤64 chars) and description bounded to ≤1024 chars..opencode/.rulebook-managed.json— sidecar listing managed keys sorulebook updateknows what to refresh vs. preserve.
Idempotency
Files carrying the <!-- RULEBOOK:START --> marker are managed and
refreshed on every rulebook update. Files without the marker are
treated as user-owned and left untouched.
Sequential editing
OpenCode follows the same Rulebook discipline as Claude Code:
- Edit files one at a time.
- For 3+ files, decompose into 1–2 file sub-tasks.
- Diagnostic-first: type-check / lint before tests.
Quality gates
- Type-check / lint must be clean.
- Tests must pass.
- Coverage ≥95%.
- Pre-commit hooks enforce these — never
--no-verify.
MCP
mcp.rulebook in opencode.json exposes rulebook_task_*,
rulebook_memory_*, rulebook_decision_*, rulebook_knowledge_*,
rulebook_learn_*. Prefer MCP tools over shell commands when both
exist.
Workflow
- Reference
AGENTS.mdand.rulebook/specs/*.md. - Use
/rulebook-task-create,/rulebook-task-list,/handoff. - Delegate to role agents (
@researcher,@implementer,@tester). - Run quality checks before committing.
- Save learnings (
rulebook_memory_save,rulebook_knowledge_add).
Documentation
- opencode.ai/docs/rules
- opencode.ai/docs/config
- opencode.ai/docs/mcp-servers
- opencode.ai/docs/commands
- opencode.ai/docs/agents
- opencode.ai/docs/skills
- opencode.ai/docs/permissions
Related Skills
hivellm/spec
research
VerifiedTrustedCommunity
Author a rulebook task spec interactively — research, draft, ask the user clarifying questions, confirm, then create the tasks in rulebook ready for /rulebook-driver. Use when the user wants to plan/spec a feature before implementing.
11SKILL.mdUpdated Jun 1, 2026
hivellm/Karpathy Guidelines
development
VerifiedTrustedCommunity
Behavioral guidelines to reduce common LLM coding mistakes — overcomplication, sloppy refactors, hidden assumptions, weak goals. Use when writing, reviewing, or refactoring code. Auto-applies; invoke explicitly via /karpathy-guidelines or 'follow karpathy discipline'.
11SKILL.mdUpdated May 2, 2026
hivellm/Ralph Autonomous Loop
data-ai
VerifiedTrustedCommunity
Autonomous AI agent loop for iterative task implementation (@hivehub/rulebook ralph)
11SKILL.mdUpdated Apr 30, 2026
hivellm/SQL Server
data-ai
VerifiedTrustedCommunity
Use SQL Server for enterprise relational data storage with advanced features, high availability, and Windows integration.
11SKILL.mdUpdated Apr 30, 2026