Repository
ZaxbyHub/opencode-swarm agent skills
- skills
- 91
- GitHub stars
- 488
GitHub description: “ Architect-centric agentic swarm plugin for OpenCode. Hub-and-spoke orchestration with SME consultation, code generation, and QA review.”
- Stars
- 488 (54 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Jan 2026
- agent-swarm
- ai-agents
- ai-coding
- automation
- bun
- cli
- code-review
- coding-agent
- developer-tools
- github
- guardrails
- llm
- mcp
- multi-agent
- open-source
- opencode
Install all skills
npx skills add ZaxbyHub/opencode-swarmAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in ZaxbyHub/opencode-swarm, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Runs an evidence-gated, quote-grounded audit of a codebase for security, QA, accessibility, performance and more, and writes a verified report without changing source files. | ZaxbyHub/ | 488 | — | ~2.8k | Automated safety check: Pass | MIT | today |
| 2 | Drives a bug report from validation and root-cause tracing through a critic-reviewed plan, an approved minimal fix and a PR-ready closure, never merging without recorded human approval. | ZaxbyHub/ | 488 | — | ~4.4k | Automated safety check: Pass | MIT | today |
| 3 | Codex adapter for opencode-swarm that governs commits, pushes, draft PRs, PR body updates and CI closeout, deferring to the repo's canonical commit-pr protocol. | ZaxbyHub/ | 488 | — | ~1.6k | Automated safety check: Pass | MIT | today |
| 4 | Keeps plans, decisions, evidence and reviewer verdicts in small files so long multi-phase tasks survive context compaction and session resumes. | ZaxbyHub/ | 488 | — | ~896 | Automated safety check: Pass | MIT | today |
| 5 | Ingests existing pull request feedback such as review comments and CI failures, verifies each claim, fixes confirmed issues and reports closure status for every item. | ZaxbyHub/ | 488 | — | ~14k | Automated safety check: Pass | MIT | today |
| 6 | Monitor a pull request after creation and act autonomously on pushed PR activity. | ZaxbyHub/ | 488 | — | ~2.2k | Automated safety check: Pass | MIT | today |
| 7 | Bundle transform safety — minification variant selection, consumer-constraint verification, identifier preservation, and namespace re-export coverage for build output. | ZaxbyHub/ | 488 | — | ~2.3k | Automated safety check: Pass | MIT | today |
| 8 | Batch collection and fix protocol for CI failures. An agent skill from ZaxbyHub/opencode-swarm. | ZaxbyHub/ | 488 | — | ~607 | Automated safety check: Pass | MIT | today |
| 9 | Monitor CI on a PR, diagnose failures, fix them, and re-push until green. | ZaxbyHub/ | 488 | — | ~2.3k | Automated safety check: Pass | MIT | today |
| 10 | 10.Commit PR Apply when committing, pushing, opening or updating a PR, writing a pull request, creating release notes, or closing out remote CI. | ZaxbyHub/ | 488 | — | ~6.2k | Automated safety check: Pass | MIT | today |
| 11 | 11.Contributing End-to-end PR workflow for opencode-swarm. An agent skill from ZaxbyHub/opencode-swarm. | ZaxbyHub/ | 488 | — | ~1.7k | Automated safety check: Pass | MIT | today |
| 12 | 12.Council Full execution protocol for MODE: COUNCIL -- General Council research, parallel member dispatch, disagreement handling, and synthesis. | ZaxbyHub/ | 488 | — | ~2.6k | Automated safety check: Pass | MIT | today |
| 13 | Full execution protocol for MODE: DEEPRESEARCH — orchestrator-worker deep research over external sources: decompose, iterative websearch/webfetch retrieval, parallel sme synthesis, dual-reviewer… | ZaxbyHub/ | 488 | — | ~2.7k | Automated safety check: Pass | MIT | today |
| 14 | 14.Design Docs 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… | ZaxbyHub/ | 488 | — | ~1.5k | Automated safety check: Pass | MIT | today |
| 15 | 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… | ZaxbyHub/ | 488 | — | ~2k | Automated safety check: Pass | MIT | today |
| 16 | Guidelines and non-negotiable engineering invariants for modifying opencode-swarm. | ZaxbyHub/ | 488 | — | ~4.7k | Automated safety check: Pass | MIT | today |
| 17 | Operational patterns for fork PRs (head repo differs from base repo). | ZaxbyHub/ | 488 | — | ~1.4k | Automated safety check: Pass | MIT | today |
| 18 | Per-task gate dispatch protocol for reviewer/testengineer set-dispatch attribution. | ZaxbyHub/ | 488 | — | ~749 | Automated safety check: Pass | MIT | today |
| 19 | Apply when reverting commits, undoing merges, or recovering from branch contamination. | ZaxbyHub/ | 488 | — | ~2.2k | Automated safety check: Pass | MIT | today |
| 20 | Guardrail patterns for opencode-swarm — pattern structure, bypass surfaces, regex anti-patterns, and test conventions for checkDestructiveCommand() | ZaxbyHub/ | 488 | — | ~3.5k | Automated safety check: Pass | MIT | today |
| 21 | 21.Loop Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic… | ZaxbyHub/ | 488 | — | ~3.9k | Automated safety check: Pass | MIT | today |
| 22 | 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… | ZaxbyHub/ | 488 | — | ~1.5k | Automated safety check: Pass | MIT | today |
| 23 | Apply before starting work on an existing branch. An agent skill from ZaxbyHub/opencode-swarm. | ZaxbyHub/ | 488 | — | ~1.4k | Automated safety check: Pass | MIT | today |
| 24 | Full execution protocol for MODE: PRE-PHASE BRIEFING -- phase-start context assembly, evidence review, and task readiness checks. | ZaxbyHub/ | 488 | — | ~1.7k | Automated safety check: Pass | MIT | today |
| 25 | Safe test execution patterns for opencode-swarm. An agent skill from ZaxbyHub/opencode-swarm. | ZaxbyHub/ | 488 | — | ~4k | Automated safety check: Pass | MIT | today |
| 26 | Load before editing any Rust crate in this repo (currently runners/swarm-sandbox-runner). | ZaxbyHub/ | 488 | — | ~1.7k | Automated safety check: Pass | MIT | today |
| 27 | Apply when extracting code from a large monolith file into submodules. | ZaxbyHub/ | 488 | — | ~2.6k | Automated safety check: Pass | MIT | today |
| 28 | 28.Safe Rename Workflow for safely renaming symbols (functions, types, classes, interfaces, constants, variables) across a codebase. | ZaxbyHub/ | 488 | — | ~2.4k | Automated safety check: Pass | MIT | today |
| 29 | Guidelines for safe subprocess calls in opencode-swarm. An agent skill from ZaxbyHub/opencode-swarm. | ZaxbyHub/ | 488 | — | ~2.4k | Automated safety check: Pass | MIT | today |
| 30 | 30.Swarm Enable a high-quality swarm-like Claude Code workflow for the current session, and optionally execute a task immediately using that mode. | ZaxbyHub/ | 488 | — | ~3.9k | Automated safety check: Pass | MIT | today |
| 31 | 31.Swarm Cross-agent swarm-mode behavior model — a higher-rigor workflow using parallel investigation, independent reviewer validation, and critic challenge, plus the mandatory implementation closeout gate. | ZaxbyHub/ | 488 | — | ~2.7k | Automated safety check: Pass | MIT | today |
| 32 | End-to-end CI monitor that takes an already-human-reviewed PR, exhaustively researches every CI failure, fixes it end-to-end, iterates until all required checks are green (max 5 fix cycles), then… | ZaxbyHub/ | 488 | — | ~4.9k | Automated safety check: Pass | MIT | today |
| 33 | Execute complex implementation work with a swarm-like workflow: parallel exploration, scoped planning, objective validation, mandatory independent implementation review for changed work, and final… | ZaxbyHub/ | 488 | — | ~2.3k | Automated safety check: Pass | MIT | today |
| 34 | Protocol for splitting test files that approach or exceed the FR-006 500-line limit (enforced in CI by scripts/check-test-file-cap.ts as a diff-scoped ratchet). | ZaxbyHub/ | 488 | — | ~1.3k | Automated safety check: Pass | MIT | today |
| 35 | Guidelines for writing, organizing, and maintaining tests in the opencode-swarm repository. | ZaxbyHub/ | 488 | — | ~12k | Automated safety check: Pass | MIT | today |
| 36 | Pre-queue merge-group CI simulation. An agent skill from ZaxbyHub/opencode-swarm. | ZaxbyHub/ | 488 | — | ~763 | Automated safety check: Pass | MIT | today |
| 37 | Content-assertion sweep after editing SKILL.md files. An agent skill from ZaxbyHub/opencode-swarm. | ZaxbyHub/ | 488 | — | ~532 | Automated safety check: Pass | MIT | today |
| 38 | Add path-type assertions or realpath/resolve calls in path-joining utility functions | ZaxbyHub/ | 488 | — | ~324 | Automated safety check: Pass | MIT | today |
| 39 | check skill provenance stamps before archiving knowledge entries | ZaxbyHub/ | 488 | — | ~380 | Automated safety check: Pass | MIT | today |
| 40 | Codex adapter for monitoring and fixing CI failures on opencode-swarm PRs. | ZaxbyHub/ | 488 | — | ~551 | Automated safety check: Pass | MIT | today |
| 41 | confirm failures are causally linked to the task before reporting rejection | ZaxbyHub/ | 488 | — | ~397 | Automated safety check: Pass | MIT | today |
| 42 | ensure all tests pass after code changes. An agent skill from ZaxbyHub/opencode-swarm. | ZaxbyHub/ | 488 | — | ~314 | Automated safety check: Pass | MIT | today |
| 43 | Per-task gate dispatch protocol. An agent skill from ZaxbyHub/opencode-swarm. | ZaxbyHub/ | 488 | — | ~314 | Automated safety check: Pass | MIT | today |
| 44 | grep for 'mock.module' across the entire test file and confirm every occurrence uses spread-real-exports before marking the file as converted | ZaxbyHub/ | 488 | — | ~363 | Automated safety check: Pass | MIT | today |
| 45 | include test files that assert on behavior being changed in declared scope | ZaxbyHub/ | 488 | — | ~342 | Automated safety check: Pass | MIT | today |
| 46 | isolate the specific failure mode before proposing a fix. An agent skill from ZaxbyHub/opencode-swarm. | ZaxbyHub/ | 488 | — | ~359 | Automated safety check: Pass | MIT | today |
| 47 | 47.Issue Tracer A skill your agent uses when asked to trace, investigate, root-cause, reproduce, plan, fix, resolve, close, or prepare a PR for an issue, bug report, defect, regression, failing test, or confusing… | ZaxbyHub/ | 488 | — | ~383 | Automated safety check: Pass | MIT | today |
| 48 | 48.Issue Tracer A skill your agent uses when asked to trace, investigate, root-cause, reproduce, plan, fix, resolve, close, or prepare a PR for an issue, bug report, defect, regression, failing test, or confusing… | ZaxbyHub/ | 488 | — | ~397 | Automated safety check: Pass | MIT | today |
Questions, answered from the data.
What is the best skill in ZaxbyHub/opencode-swarm?
Codebase Review Swarm from ZaxbyHub/opencode-swarm ranks first of the 91 skills in ZaxbyHub/opencode-swarm listed here, with the highest score: its repository has 488 GitHub stars, its SKILL.md loads about 2.8k tokens and it passes the automated safety check with no findings. Next come Issue Tracer and Commit and PR Publishing for Codex.
Are the skills in ZaxbyHub/opencode-swarm official?
None yet. All 91 skills in ZaxbyHub/opencode-swarm listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from ZaxbyHub/opencode-swarm?
Run npx skills add ZaxbyHub/opencode-swarm in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.