opencode-base
Use when designing or extending this project as an OpenCode-based agent framework with minimal custom bottom-layer work.
Skill by redmaplewww
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/redmaplewww-opencode-base
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/opencode-base
What's inside
- Skill name
opencode-base- Description
- Use when designing or extending this project as an OpenCode-based agent framework with minimal custom bottom-layer work.
- License
- MIT
- Compatibility
- opencode
- Metadata
- stack: opencode · strategy: upstream-first
- Instructions
- 47 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# OpenCode Base Skill Use this skill when the task is about the agent framework architecture, OpenCode as a base, skill/plugin/tool design, MCP integration, or avoiding custom bottom-layer development. ## Principle Do not rebuild the agent kernel. Use OpenCode as the owner of: - model loop - agents and subagents - tool invocation - permissions - sessions and forks - snapshots - command entrypoints - project rules - skills - MCP integration ## Mapping | Capability | Default owner | | --- | --- | | Primary loop | OpenCode runtime | | Planning/build modes | OpenCode built-in `plan` and `build` agents | | Specialized roles | `.opencode/agents/*.md` | | Reusable behavior | `.opencode/skills/*/SKILL.md` | | Tool extension | MCP server or OpenCode plugin | | Knowledge/document search | MCP first; LlamaIndex/Haystack only as external service if needed | | Memory | OpenCode session history first; Mem0/Letta only through MCP or external service | | Scheduled tasks | external scheduler that calls `opencode run` | | State machine/workflow | OpenCode commands/agents first; external workflow engine only for production automation | | Self-evolution | proposal documents and review commands; no automatic core mutation | ## Decision Rule Before proposing custom code, answer: 1. Can OpenCode config solve this? 2. Can a project agent solve this? 3. Can a project skill solve this? 4. Can an MCP server solve this? 5. Can an upstream tool solve this with a thin command wrapper? Only if all five answers are no should custom code be proposed.
From redmaplewww/DeepReason-Agents-Framework, MIT.
More from redmaplewww/DeepReason-Agents-Framework
- 0.543score
configurator
redmaplewww
Use when helping a user understand, generate, review, or revise agent.yaml, choose skills, set knowledge and memory policies, define gates, configure models…
SkillCFreshness: C★ 15Claude Code +9 - 0.543score
evidence-first
redmaplewww
Use when answering questions, making recommendations, updating memory, proposing skill changes, or passing gates where claims must be grounded in citable…
SkillCFreshness: C★ 15Claude Code +9 - 0.543score
knowledge-rag
redmaplewww
Use when ingesting, searching, citing, or auditing local project knowledge for a heavy-reasoning agent, especially markdown, text, JSON, and other documents…
SkillCFreshness: C★ 15Claude Code +9 - 0.543score
memory-consolidation
redmaplewww
Use when deciding whether short-term state, user feedback, repeated failures, decisions, preferences, or project facts should become long-term semantic…
SkillCFreshness: C★ 15Claude Code +9 - 0.543score
minimal-change
redmaplewww
Use when planning or performing code, config, skill, documentation, or memory edits where the agent must make the smallest evidence-backed modification, avoid…
SkillCFreshness: C★ 15Claude Code +9 - 0.543score
project-intake
redmaplewww
Use when a user starts or revises a heavy-reasoning agent project and the agent must clarify goals, audience, scope, constraints, success criteria, failure…
SkillCFreshness: C★ 15Claude Code +9 - 0.543score
self-evolution
redmaplewww
Use when the agent should learn from failures, feedback, tests, or repeated patterns by generating reviewed proposals for skill, memory, config, or workflow…
SkillCFreshness: C★ 15Claude Code +9 - 0.543score
state-gates
redmaplewww
Use when an agent action needs risk assessment, approval, state-machine routing, interrupt handling, or enforcement of evidence requirements before answering…
SkillCFreshness: C★ 15Claude Code +9 - 0.513score
testing-verification
redmaplewww
Use when defining, running, or reviewing tests and acceptance checks for a heavy-reasoning agent, especially to prove evidence binding, gate enforcement…
SkillCFreshness: C★ 15Claude Code +9
Signals
- Stars
- 15
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Jul 6, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from redmaplewww
- 0.543score
configurator
redmaplewww
Use when helping a user understand, generate, review, or revise agent.yaml, choose skills, set knowledge and memory policies, define gates, configure models…
SkillCFreshness: C★ 15Claude Code +9 - 0.543score
evidence-first
redmaplewww
Use when answering questions, making recommendations, updating memory, proposing skill changes, or passing gates where claims must be grounded in citable…
SkillCFreshness: C★ 15Claude Code +9 - 0.543score
knowledge-rag
redmaplewww
Use when ingesting, searching, citing, or auditing local project knowledge for a heavy-reasoning agent, especially markdown, text, JSON, and other documents…
SkillCFreshness: C★ 15Claude Code +9 - 0.543score
memory-consolidation
redmaplewww
Use when deciding whether short-term state, user feedback, repeated failures, decisions, preferences, or project facts should become long-term semantic…
SkillCFreshness: C★ 15Claude Code +9 - 0.543score
minimal-change
redmaplewww
Use when planning or performing code, config, skill, documentation, or memory edits where the agent must make the smallest evidence-backed modification, avoid…
SkillCFreshness: C★ 15Claude Code +9 - 0.543score
project-intake
redmaplewww
Use when a user starts or revises a heavy-reasoning agent project and the agent must clarify goals, audience, scope, constraints, success criteria, failure…
SkillCFreshness: C★ 15Claude Code +9
Cite this page
opencode-base skill. Agent Mart. https://agentmart.dev/skills/redmaplewww-opencode-base (last updated 2026-10-24)