Development
Plugin
codeg
English | 简体中文 | 繁體中文 | 日本語 | 한국어 | Español | Deutsch | Français | Português | العربية Codeg (Code Generation) is a multi-agent coding workspace: run every AI coding agent in one place — and let them work together.
Plugin Signal81/100Strong
maintained99
capable69
documented75
adopted73
Install
$ npx -y skills add xintaofei/codeg --agent claude-code
Run the curl in your terminal, the rest in Claude Code.
Stats
2,620
Stars
322
Forks
Active
Maintenance
Rust
Language
Apache-2.0
License
1h ago
Last commit
6mo ago
Created
Repo: xintaofei/codeg
In this plugin
- brainstorming
- dispatching-parallel-agents
- executing-plans
- finishing-a-development-branch
- receiving-code-review
- requesting-code-review
- subagent-driven-development
- systematic-debugging
- test-driven-development
- using-git-worktrees
- using-superpowers
- verification-before-completion
- writing-plans
- writing-skills
- citation-management
- experimental-design
- exploratory-data-analysis
- hypothesis-generation
- paper-lookup
- peer-review
- scholar-evaluation
- scientific-brainstorming
- scientific-critical-thinking
- scientific-schematics
- scientific-visualization
- statistical-analysis
- statistical-power
What's inside
Skills
27/brainstormingYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation./dispatching-parallel-agentsUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies/executing-plansUse when you have a written implementation plan to execute in a separate session with review checkpoints/finishing-a-development-branchUse when implementation is complete, all tests pass, and you need to decide how to integrate the work/receiving-code-reviewUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation/requesting-code-reviewUse when completing tasks, implementing major features, or before merging to verify work meets requirements
Show all 27 skillsShow fewer
/subagent-driven-developmentUse when executing implementation plans with independent tasks in the current session/systematic-debuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes/test-driven-developmentUse when implementing any feature or bugfix, before writing implementation code/using-git-worktreesUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback/using-superpowersUse when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions/verification-before-completionUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always/writing-plansUse when you have a spec or requirements for a multi-step task, before touching code/writing-skillsUse when creating new skills, editing existing skills, or verifying skills work before deployment/citation-managementComprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation/experimental-designDesign experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so the results will actually be interpretable. Use whenever someone is planning a study, asks how to assign subjects/samples to groups,/exploratory-data-analysisPerform comprehensive exploratory data analysis on scientific data files across 200+ file formats. This skill should be used when analyzing any scientific data file to understand its structure, content, quality, and characteristics. Automatically detects file type and generates/hypothesis-generationStructured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended/paper-lookupSearch 10 academic literature APIs for papers, preprints, citations, and open-access full text, and return results with reproducible provenance. Covers PubMed, PMC (full text), bioRxiv, medRxiv, arXiv, OpenAlex, Crossref, Semantic Scholar, CORE, Unpaywall. Use when searching for/peer-reviewStructured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review/scholar-evaluationSystematically evaluate scholarly work using the ScholarEval framework, providing structured assessment across research quality dimensions including problem formulation, methodology, analysis, and writing with quantitative scoring and actionable feedback./scientific-brainstormingCreative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For/scientific-critical-thinkingEvaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality,/scientific-schematicsCreate publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only regenerates if quality is below threshold for your document type. Specialized in neural network architectures, system/scientific-visualizationMeta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly/statistical-analysisGuided statistical analysis for research data - test selection, assumption checking, effect sizes, power analysis, Bayesian alternatives, and APA-formatted reporting. Use whenever a user wants to compare groups, test a hypothesis, analyze experimental or survey data, check/statistical-powerSample-size and statistical power calculations for planning studies. Use whenever someone asks "how many subjects/samples/replicates do I need", wants an a priori power analysis, a minimum detectable effect (MDE), a power curve, or needs to justify a sample size for a grant, IRB
Badges
3
README
1Codeg
Codeg (Code Generation) is a multi-agent coding workspace: run every AI coding agent in one place — and let them work together.
It aggregates your sessions from every supported agent CLI into one searchable workspace, lets a main agent delegate to sub-agents of other types within a single task, and runs as a desktop app, a standalone server, or a Docker container — with native iOS and Android clients for when you're away from your desk. Twelve agents come built in, and since 0.22 you can register any other ACP-compatible agent yourself.
📖 Documentation
Full documentation lives at docs.codeg.app — Getting Started · Guide · Reference
💖 Sponsors
Want to become a Codeg sponsor? Reach out to us by email.
🤖 Supported Agents
Claude Code · Codex · Gemini · OpenClaw · OpenCode · Cline · Hermes · CodeBuddy · Kimi Code · Pi · Grok · Cursor
Codeg installs, pins, and updates most of them for you. See Supported Agents for the full roster, each agent's runtime requirements, and where it keeps its sessions on disk.
Not on the list? Add it yourself. Pick any agent from the public ACP registry or paste its distribution JSON, and Codeg installs it, checks it can launch, and treats it like a built-in — it shows up in the picker, takes @ delegation and skills, and gets its conversations recorded and searchable even when the agent keeps no history of its own. → Custom Agents
🤝 Multi-Agent Collaboration
Multi-agent collaboration, reduced to a single keystroke: type @, pick an agent, hit send. Codeg handles the scheduling — it launches each mentioned agent as its own session, hands over the task, and streams the work back into the thread you're already in. Mention two and they run side by side: Claude Code drafting while Codex reviews. No context switching, no copy-pasting between terminals.
And when an agent spawns sub-agents of its own — Claude Code's, for instance — their output streams inside the card as they work, instead of landing all at once when they finish.
🪟 Split View
One tab strip isn't always enough. Right-click a conversation tab to split the view right or down, as many times as you like: two panes side by side, a stack of three, a grid. Each group is a workspace of its own — its own tabs, its own header, its own new-conversation button — so Claude Code can refactor in one pane while Codex reviews a diff in the next.
Drag a tab from one group into another and its session keeps streaming through the move; drag the divider between two groups to change how they share the space. Your layout is remembered per workspace, drafts included: reopen Codeg and the split comes back, with the text you never sent still in the box.
📄 Office Documents
Ask for a deck, a report, or a workbook and the agent builds a real .pptx / .docx / .xlsx — while the pane on the right renders it live. Every edit lands in the preview on its own: slides fill in, tables take shape, numbers land in cells. Don't like slide 4? Say so in the next message — the agent edits the same file in place and the preview catches up. No export step, no external Office app, no leaving Codeg.
💻 Workspace
One workspace, every agent. Whichever one is driving — Claude Code, Codex, Cursor — it works in the same editor, the same live diffs, the same git client, and what it produces is real files in your repo, changing while you watch.
Sessions. Pull in the history you already have: past sessions from every installed agent, imported in one click and resumable where you left them. Once they're in, they stop being separate silos — @-mention an old session and the agent you're talking to can read it, even when a different agent wrote it, so today's Codex run picks up where last week's Claude Code session ended.
Files. The agent's edits show up as diffs beside the conversation as they land. Open any file in a real editor with syntax highlighting, send a file — or just a selection — straight to the agent with ⌘L, and preview Markdown, HTML, images, and Office documents in the same pane.
Git. A full client, not a status readout: commit and push, browse history with per-commit push state, and branch, merge, rebase, stash, reset, or diff against another branch. Conflicts open a three-pane merge editor where you accept hunk by hunk or type the fix yourself. And worktrees make parallel work one action — a new branch, its own directory, and a fresh conversation rooted in it, so a fleet of agents build different features at once without touching each other's files.
📱 iPhone, iPad & Android
Step away from your desk, not your work. The native iOS and Android clients connect to the Codeg you already run — the Web Service of your desktop app, or your own codeg-server — and from there you start sessions, watch replies and tool calls stream in, answer permission prompts, and browse projects and branches. Nothing moves onto the phone: your files, agent CLIs, and conversations stay on the machine running Codeg, and the access token sits in iOS Keychain or Android Keystore. Both clients are open source (iOS, Android) and currently in testing; pairing takes three steps, covered in Mobile apps.
| iPhone & iPad | Android |
|---|---|
✨ Highlights
- Conversation Aggregation — import sessions from every supported agent into one unified, searchable workspace, and pick any of them up where you left off
- Multi-Agent Collaboration —
@-mention any agent to delegate: sub-agents of different types run as their own sessions, in parallel, inside a single task - Custom Agents — register any other ACP-compatible agent from the public registry or its distribution JSON; Codeg installs it, records its history, and treats it like a built-in
- The Workspace — the full engineering loop next to the agent: file tree, editor and diff, git changes, commit, and an embedded terminal
- Split View — split the conversation area into as many tab groups as you like, drag tabs and dividers between them, and get the layout back — drafts included — on restart
- Git & Worktrees — review and commit changes, manage Git remote accounts, and run work in parallel with built-in
git worktreeflows - Chat Channels — drive your agents from Telegram, Lark (Feishu), and iLink (Weixin): create tasks, approve permissions, and get live updates
- Automations — save a fully-configured composer as a reusable automation that runs headlessly, on a cron schedule or on demand
- Office Documents — create, analyze, proofread, and edit
.docx/.xlsx/.pptxthrough the bundledofficecli, with live in-tab preview - Scientific Research — bundled research skills (hypothesis generation, experimental design, statistics, visualization, critical appraisal, literature search) any agent can invoke
- Project Boot — scaffold new projects visually, with live preview, then open them straight in the workspace
- MCP & Skills — local server scan plus registry search/install, and skills managed at global or project scope
- Desktop, Server & Docker — a native desktop app, a standalone
codeg-serveryou reach from any browser, ordocker compose up - iPhone, iPad & Android — native mobile clients that connect to your desktop or server: start sessions, stream replies, approve permissions, and browse projects from anywhere
📦 Install & Run
Desktop — download the installer for macOS, Windows, or Linux from Releases, then follow Installation.
Server — run Codeg headless and reach it from any browser. On Linux or macOS:
curl -fsSL https://raw.githubusercontent.com/xintaofei/codeg/main/install.sh | bash
CODEG_STATIC_DIR=/usr/local/share/codeg/web codeg-server
On Windows, in PowerShell:
irm https://raw.githubusercontent.com/xintaofei/codeg/main/install.ps1 | iex
$env:CODEG_STATIC_DIR="$env:LOCALAPPDATA\codeg\web"; codeg-server
Docker — the same server, in one container:
docker run -d -p 3080:3080 -v codeg-data:/data ghcr.io/xintaofei/codeg:latest
Mobile — install the iOS app or the Android APK, then point it at the Web Service of your desktop app or at your own codeg-server: URL, token, done. Pairing steps in Mobile apps.
Compose, prebuilt binaries, source builds, and in-place updates are covered in Deployment; environment variables in Configuration. Building Codeg itself: Development and Architecture.
🔒 Privacy & Security
- Local-first by default for parsing, storage, and project operations — network access happens only on user-triggered actions
- Web and server modes are guarded by token-based authentication
- System proxy support for enterprise environments
Details in Privacy & Security.
👥 Community
- Scan the QR code below to join our WeChat group for discussions, feedback, and updates
- Thanks to the LinuxDO community for their support
🙏 Acknowledgments
- Agent Client Protocol — the foundation that lets Codeg connect to every agent it supports
- Superpowers — powers Codeg's expert skills module
- OfficeCLI — powers Codeg's Office documents workflow
- scientific-agent-skills — powers Codeg's Scientific Research skills (MIT-licensed subset)
📜 License
Apache-2.0. See LICENSE.
File tree
1493xintaofei/codegView on GitHub
.cargo/
config.toml
.dockerignore
.editorconfig
.github/
workflows/
release.yml
test.yml
.gitignore
.npmrc
.prettierignore
.prettierrc
AGENTS.md
CLAUDE.md
components.json
docker-compose.yml
Dockerfile
Dockerfile.ci
docs/
chat-channels/
telegram-topic-mode.md
CLIENT-PRIVACY.md
images/
collaboration-dark.gif
collaboration-light.gif
compshare.png
hezu-ink.jpg
mobile-android.jpg
mobile-ios.jpg
office-dark.png
office-light.png
onehop.jpg
split-dark.gif
split-light.gif
sui-xiang.jpg
weixin-dark.jpg
weixin-light.jpg
workspace-dark.png
workspace-light.png
readme/
README.ar.md
README.de.md
README.es.md
README.fr.md
README.ja.md
README.ko.md
README.pt.md
README.zh-CN.md
README.zh-TW.md
releasing/
macos-signing.md
eslint.config.mjs
install.ps1
install.sh
LICENSE
next.config.ts
package.json
pnpm-lock.yaml
pnpm-workspace.yaml
postcss.config.mjs
public/
icon-128x128.png
icon-32x32.png
icon.svg
next.svg
react.svg
tauri.svg
README.md
scripts/
prepare-macos-signing-secrets.sh
sync-science-skills.sh
src/
src-tauri/
.gitignore
build.rs
capabilities/
default.json
desktop.json
Cargo.lock
Cargo.toml
experts/
experts.toml
skills/
brainstorming/
scripts/
frame-template.html
helper.js
server.cjs
start-server.sh
stop-server.sh
SKILL.md
spec-document-reviewer-prompt.md
visual-companion.md
dispatching-parallel-agents/
SKILL.md
executing-plans/
SKILL.md
finishing-a-development-branch/
SKILL.md
receiving-code-review/
SKILL.md
requesting-code-review/
code-reviewer.md
SKILL.md
subagent-driven-development/
implementer-prompt.md
re-review-prompt.md
scripts/
review-package
sdd-workspace
task-brief
SKILL.md
task-reviewer-prompt.md
systematic-debugging/
condition-based-waiting-example.ts
condition-based-waiting.md
CREATION-LOG.md
defense-in-depth.md
find-polluter.sh
root-cause-tracing.md
SKILL.md
test-academic.md
test-pressure-1.md
test-pressure-2.md
test-pressure-3.md
test-driven-development/
SKILL.md
writing-good-tests.md
using-git-worktrees/
SKILL.md
using-superpowers/
references/
antigravity-tools.md
codex-tools.md
gemini-tools.md
pi-tools.md
SKILL.md
verification-before-completion/
SKILL.md
writing-plans/
plan-document-reviewer-prompt.md
SKILL.md
writing-skills/
anthropic-best-practices.md
examples/
CLAUDE_MD_TESTING.md
graphviz-conventions.dot
persuasion-principles.md
render-graphs.js
SKILL.md
testing-skills-with-subagents.md
icons/
128x128.png
128x128@2x.png
32x32.png
64x64.png
icon.icns
icon.ico
icon.png
icon.svg
Square107x107Logo.png
Square142x142Logo.png
Square150x150Logo.png
Square284x284Logo.png
Square30x30Logo.png
Square310x310Logo.png
Square44x44Logo.png
Square71x71Logo.png
Square89x89Logo.png
StoreLogo.png
tray-icon-template.gen.py
tray-icon-template.png
resources/
codex/
bundled-catalog.json
opencode/
models-dev.json
science/
NOTICE.md
science.toml
skills/
citation-management/
assets/
bibtex_template.bib
citation_checklist.md
references/
bibtex_formatting.md
citation_validation.md
google_scholar_search.md
metadata_extraction.md
pubmed_search.md
scripts/
doi_to_bibtex.py
extract_metadata.py
format_bibtex.py
generate_schematic_ai.py
generate_schematic.py
search_google_scholar.py
search_pubmed.py
validate_citations.py
SKILL.md
experimental-design/
references/
design_types.md
factorial_and_doe.md
randomization_and_blocking.md
sequential_and_adaptive.md
scripts/
doe_designs.py
randomization.py
SKILL.md
exploratory-data-analysis/
assets/
report_template.md
references/
bioinformatics_genomics_formats.md
chemistry_molecular_formats.md
general_scientific_formats.md
microscopy_imaging_formats.md
proteomics_metabolomics_formats.md
spectroscopy_analytical_formats.md
scripts/
eda_analyzer.py
SKILL.md
hypothesis-generation/
assets/
FORMATTING_GUIDE.md
hypothesis_generation.sty
hypothesis_report_template.tex
references/
experimental_design_patterns.md
hypothesis_quality_criteria.md
literature_search_strategies.md
scripts/
generate_schematic_ai.py
generate_schematic.py
SKILL.md
paper-lookup/
references/
arxiv.md
biorxiv.md
core.md
crossref.md
medrxiv.md
openalex.md
pmc.md
pubmed.md
semantic-scholar.md
unpaywall.md
SKILL.md
peer-review/
references/
common_issues.md
reporting_standards.md
scripts/
generate_schematic_ai.py
generate_schematic.py
SKILL.md
scholar-evaluation/
references/
evaluation_framework.md
scripts/
calculate_scores.py
generate_schematic_ai.py
generate_schematic.py
SKILL.md
scientific-brainstorming/
references/
brainstorming_methods.md
SKILL.md
scientific-critical-thinking/
references/
common_biases.md
evidence_hierarchy.md
experimental_design.md
logical_fallacies.md
scientific_method.md
statistical_pitfalls.md
SKILL.md
scientific-schematics/
references/
best_practices.md
QUICK_REFERENCE.md
README.md
scripts/
example_usage.sh
generate_schematic_ai.py
generate_schematic.py
SKILL.md
scientific-visualization/
assets/
color_palettes.py
nature.mplstyle
presentation.mplstyle
publication.mplstyle
references/
color_palettes.md
journal_requirements.md
matplotlib_examples.md
publication_guidelines.md
scripts/
figure_export.py
style_presets.py
SKILL.md
statistical-analysis/
references/
assumptions_and_diagnostics.md
bayesian_statistics.md
effect_sizes_and_power.md
reporting_standards.md
test_selection_guide.md
scripts/
assumption_checks.py
SKILL.md
statistical-power/
references/
closed_form_recipes.md
effect_sizes.md
simulation_based_power.md
scripts/
power.py
simulate_power.py
SKILL.md
scripts/
prepare-sidecars.mjs
src/
acp/
acp_transcript.rs
background_watch.rs
binary_cache.rs
chat_authoring.rs
codex_catalog_source.rs
codex_goal.rs
codex_model_catalog.rs
connection.rs
custom_registry.rs
delegation/
broker.rs
companion.rs
depth.rs
event_emitter.rs
listener.rs
live_reply.rs
meta_writer.rs
mod.rs
parent_watcher.rs
spawner.rs
tool_schema.json
transport.rs
types.rs
error.rs
event_stream.rs
feedback.rs
file_system_runtime.rs
fork.rs
idle_sweep.rs
internal_bus.rs
lifecycle.rs
manager.rs
mod.rs
opencode_catalog.rs
opencode_plugins.rs
plan_approval.rs
preflight.rs
prompt_hydration.rs
question.rs
registry.rs
remote_registry.rs
session_info.rs
session_state.rs
stderr_tail.rs
terminal_runtime.rs
types.rs
work_task_tools.rs
app_error.rs
app_state.rs
automation/
engine.rs
mod.rs
backgrounds/
mod.rs
bin/
codeg_mcp.rs
codeg_server.rs
chat_channel/
backends/
lark.rs
mod.rs
telegram.rs
weixin.rs
command_dispatcher.rs
command_handlers.rs
error.rs
event_subscriber.rs
i18n.rs
manager.rs
message_formatter.rs
mod.rs
scheduler.rs
session_bridge.rs
... 1278 moreFAQ
codeg is a Claude Code plugin with 27 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes brainstorming, dispatching-parallel-agents, executing-plans. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is codeg?
- English | 简体中文 | 繁體中文 | 日本語 | 한국어 | Español | Deutsch | Français | Português | العربية Codeg (Code Generation) is a multi-agent coding workspace: run every AI coding agent in one place — and let them work together.
- How do I install codeg?
- Run these in Claude Code: npx -y skills add xintaofei/codeg --agent claude-code. Then prompt normally.
- Does codeg auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is codeg free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.