claude

orchestra

Multi-agent orchestration for structured TDD development. Bare /orchestra sets up the Claude Code + Codex environment (detects project commands, offers to install recommended plugins with consent, marks the project orchestra-enabled in CLAUDE.md); /orchestra <request> conducts a Plan -> Implement -> Review -> Commit cycle, delegating planning/review to Claude subagents and implementation to ChatGPT Codex via the `codex` CLI.

0 on GitHubby jaiv1.3.1updated 3 days agoworkflow
/

Plugin orchestra from marketplace hk-plugins in HirotoKanda/hk-plugins. Commands read from the repo's manifest — 3 days ago.

What it installs

Skills (1)

  • orchestra

    Multi-agent orchestration for structured TDD development. Use when the user invokes /orchestra. Bare `/orchestra` (setup mode) prepares the Claude Code + Codex environment and marks the project orchestra-enabled by writing guidance into its CLAUDE.md; `/orchestra <request>` (run mode) conducts a Pla

Subagents (3)

  • orchestra-codex-implementer

    TDD implementation worker for the `/orchestra` workflow. Use when the orchestra conductor delegates a phase to be implemented. Bridges to ChatGPT Codex via the `codex` CLI — constructs a phase brief, runs `codex exec`, captures the resulting diff, verifies tests, and reports back. Does NOT design th

  • orchestra-planner

    Research and context-gathering specialist for the `/orchestra` workflow. Use when the orchestra conductor needs codebase findings to inform a multi-phase plan. Read-only — analyzes structure, identifies relevant files/functions/patterns, and returns structured findings. Does NOT write plans or code.

  • orchestra-reviewer

    Quality-gate code reviewer for the `/orchestra` workflow. Use when the orchestra conductor needs an implementation phase reviewed before commit. Reads the uncommitted git diff, verifies tests pass, checks the work against the phase's acceptance criteria, and returns APPROVED / NEEDS_REVISION / FAILE

View source on GitHub

More from HirotoKanda/hk-plugins

All 5 plugins →

Map the literature of a research field or thesis niche: fan-out theme searches over arXiv / INSPIRE-HEP / Semantic Scholar / CiNii / J-STAGE build a persistent local corpus (stdlib-only fetch script, no pip installs); an LLM subagent fan-out classifies every paper into a corpus-derived taxonomy with a 0–3 relevance score; deliverables are a temporal/topical map figure, a curated reading-list CSV, a markdown briefing, and a final answer grouping the top papers by how they connect to the user's own work. INSPIRE-HEP supplies citation counts natively (no OpenAlex key needed for physics).

1 skill

0

Read, summarize, evaluate, or critique a research paper (PDF / DOI / arXiv / URL) with one unified four-stage method — Triage -> Comprehend -> Critique -> Integrate — fusing Keshav's three-pass method and Elliott/Beck/DeMarco's Four i's. Produces a structured summary + critique + integration, and loads a physics.md toolbox (units-limits-symmetries, statistical vs systematic uncertainty, 3-sigma/5-sigma significance, reduced-chi-squared/residuals, PRL/arXiv norms) for physics/experimental papers. Also runs literature surveys.

1 skill

0

Reviews the STRUCTURE and logical flow of a science/engineering bachelor's thesis (理工系卒業論文) against a standard 6-chapter template — funnel-shaped Introduction, the build-up of Theory, the parallelism of Theory/Method/Result/Discussion along one axis (baseline→proposed, simple→general), figure/table placement, and Acknowledgement/References. Reads PDF, LaTeX, or Markdown and reports in the thesis's own language. Evaluates structure only, never content correctness.

1 skill

0

Fortran language server (fortls) for code intelligence — go-to-definition, find-references, symbol search, hover, and diagnostics across free-form and fixed-form Fortran. Wires fortls into Claude Code's built-in LSP tool. Requires `fortls` on PATH (pip install fortls).

0

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

Use Alibaba Open Code Review from local Codex.

2 skills

alibaba/open-code-review 50,068

Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development

9 skills · 1 command · 8 agents

wshobson/agents 42,461

codex

claude

Use Codex from Claude Code to review code or delegate tasks.

3 skills · 8 commands · 1 agent · hooks

openai/codex-plugin-cc 35,098

Maintain orchestra?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins5 plugins