Agent Claude Code
Use proactively when the user asks to trace, investigate, root-cause, plan, close, or prepare a PR for a GitHub issue or bug report. Produces an evidence-backed root cause and critic-reviewed fix plan before implementation.
Hook Claude Code
Runs before the agent uses a tool for Bash, Read and Glob tool calls, running an inline shell check (2 commands). From ZaxbyHub/opencode-swarm.
Settings file Claude Code
Agent settings declaring 3 hook events (SessionStart, Stop, PreToolUse).
Skill Claude CodeCodex
Full execution protocol for MODE: BRAINSTORM -- structured discovery dialogue, approach selection, spec drafting, QA gate selection, and transition handling.
Skill Claude CodeCodex
Full execution protocol for MODE: CLARIFY-SPEC -- resolving spec clarification markers and maintaining spec/planning alignment.
Skill Claude CodeCodex
Full execution protocol for MODE: CLARIFY -- structured clarification funnel with critic review before surfacing user decisions.
Skill Claude CodeCodex
Full execution protocol for MODE: CONSULT -- answering advisory questions with bounded evidence and clear uncertainty.
Skill Claude CodeCodex
Full execution protocol for MODE: COUNCIL -- General Council research, parallel member dispatch, disagreement handling, and synthesis.
Skill Claude CodeCodex
Full execution protocol for MODE: CRITIC-GATE -- plan critic review, revision loops, and hard stop before execution.
Skill Claude CodeCodex
Full execution protocol for MODE: DEEPDIVE — read-only codebase audit with parallel explorer waves, 2 independent reviewers, and sequential critic challenge for HIGH/CRITICAL findings. Loaded on demand by the architect when the deep-dive command emits a [MODE: DEEPDIVE ...] signal.
Skill Claude CodeCodex
Full execution protocol for MODE: DEEPRESEARCH — orchestrator-worker deep research over external sources: decompose, iterative websearch/webfetch retrieval, parallel sme synthesis, dual-reviewer claim verification, critic challenge of high-stakes claims, and a cited report. Loaded on demand by the architect when the…
Skill Claude CodeCodex
Full execution protocol for MODE: DESIGNDOCS — generate or sync structured, language-agnostic design docs (domain.md, technical-spec.md, behavior-spec.md, reference/) for the project under build, with a stable section-ID registry and a design changelog. Loaded on demand by the architect when the design-docs command…
Skill Claude CodeCodex
Full execution protocol for MODE: DISCOVER -- read-only repository discovery and governance/context mapping.
Skill Claude CodeCodex
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…
Skill Claude CodeCodex
Contract for adding, editing, moving, or removing skills in this repository (.claude/skills, .opencode/skills, .agents/skills, any SKILL.md): mirror classifications in src/config/skill-mirrors.ts, dual-tree byte-identical edits, bun run drift:check, bundling via BUNDLEDPROJECTSKILLS, frontmatter conventions, and how…
Skill Claude CodeCodex
Claude Code adapter for MODE: EXECUTE. Delegates to the canonical opencode-swarm execution protocol.
Skill Claude CodeCodex
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
Skill Claude CodeCodex
Full execution protocol for MODE: ISSUEINGEST -- GitHub issue intake, localization, spec generation, and transition to the full fix workflow.
Skill Claude CodeCodex
Tiering and economics for delegating to subagents: which agent type, model, and effort to use per role (explorer, implementer, reviewer, critic), how many agents to launch in parallel, how to write scoped subagent prompts with bounded structured returns, and how to keep the main context clean. Use when launching…
Skill Claude CodeCodex
Claude Code adapter for MODE: PHASE-WRAP. Delegates to the canonical opencode-swarm phase boundary protocol.
Skill Claude CodeCodex
Full execution protocol for MODE: PLAN -- plan creation, external plan ingestion, QA gate persistence, task granularity, and traceability checks.
Skill Claude CodeCodex
Full execution protocol for MODE: PRE-PHASE BRIEFING -- phase-start context assembly, evidence review, and task readiness checks.
Skill Claude CodeCodex
Load before editing any Rust crate in this repo (currently runners/swarm-sandbox-runner). Covers the mandatory local validation gate, common rustfmt/clippy pitfalls, and Windows-specific Rust correctness patterns that CI enforces but are hard to catch locally without a Windows toolchain.
Skill Claude CodeCodex
Full execution protocol for MODE: SPECIFY -- spec creation, codebase reality checks, SME input, QA gate persistence, and optional council spec review.