By nexttylabs
Immune-Brain skill collection for lifecycle agentic engineering workflows.
Use when reviewing evals.
Use when debugging incidents.
Use when reviewing docs.
Use when delegated review.
Use when exploring architecture.
Admin access level
Server config contains admin-level keywords
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Immune-Brain is a Skill-driven workflow system for agentic engineering. It keeps planning, execution, review, QA, and learning capture as separate roles so agents can continue work across sessions without relying on chat memory.
Use the host-native plugin surface for your agent:
.agents/plugins/marketplace.json, then
install immune-brain..claude-plugin/marketplace.json, then
install immune-brain..cursor-plugin/marketplace.json where plugin marketplaces are
available. Runtime tools are exposed through MCP.All hosts use the same canonical Skill tree:
plugins/immune-brain/skills/
Do not register a second managed copy of the same Skills while the host plugin is enabled. That can double-register Skills.
Codex and Cursor use plugins/immune-brain/.mcp.json, which exposes tools for:
Claude Code can also use plugins/immune-brain/bin/imm-* wrappers. These call
the same plugin-local runtime adapter used by MCP. The plugin package includes
its own .imm runtime, so the runtime tools work even when only
plugins/immune-brain is installed.
The public repository does not ship the source repository's root .imm
development runtime or internal planning history. Any files under
plugins/immune-brain/dist/ are packaged plugin runtime assets.
Use these Skills from your agent:
prep: clarify and planrun: continue a validated Planimm-work: drive the current Stepimm-code-review: review material changesimm-compounder: capture reusable learnings after completionTarget projects keep their workflow state in:
.imm/memory/current_iteration.json
docs/specs/
docs/plans/
docs/solutions/
Run agents from the project root so runtime tools read and write the intended project state.
python3 -m json.tool plugins/immune-brain/.codex-plugin/plugin.json
python3 -m json.tool plugins/immune-brain/.mcp.json
python3 plugins/immune-brain/dist/immune_brain_runtime.py list-tools
python3 plugins/immune-brain/dist/.imm/activation_plan.py --validate-refs
npx claudepluginhub nexttylabs/immune-brain --plugin immune-brainHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Plugin that includes the Figma MCP server and Skills for common workflows
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,561 supported skills.