Skip to content

feat: add Qoder custom subagent support#25

Open
dougsong wants to merge 217 commits intojnMetaCode:mainfrom
dougsong:main
Open

feat: add Qoder custom subagent support#25
dougsong wants to merge 217 commits intojnMetaCode:mainfrom
dougsong:main

Conversation

@dougsong
Copy link

Summary

Add Qoder as the 13th supported AI coding tool integration, enabling batch conversion and one-click installation of all 180 agents into Qoder's custom subagent format.

Changes

scripts/convert.sh

  • Add get_qoder_tools() function: maps agent directories to recommended Qoder tool permissions (Read, Edit, Bash, etc.)
  • Add convert_qoder() function: transforms frontmatter (name → kebab-case slug, removes color/emoji/vibe, adds tools) while preserving body content
  • Register qoder in valid tools list and help message

scripts/install.sh

  • Add detect_qoder() function: detects Qoder via qoder command or ~/.qoder directory
  • Add install_qoder() function: copies converted agents to .qoder/agents/ (project-level)
  • Register qoder in ALL_TOOLS, is_detected(), tool_label(), and install_tool()

README.md / README.zh-TW.md

  • Update supported tool count from 12 to 13
  • Add Qoder entry to quick start commands and integration table
  • Add Qoder detailed installation guide with auto/manual trigger usage examples

Qoder Agent Format

---
name: engineering-frontend-developer    # kebab-case slug from filename
description: 精通 React/Vue/Angular...  # original Chinese description preserved
tools: Read, Grep, Glob, Bash, Edit, Write  # auto-recommended by directory
---
# Body content preserved as-is

Usage

# Convert all 180 agents to Qoder format
bash scripts/convert.sh --tool qoder

# Install to current project
bash scripts/install.sh --tool qoder

# Use in Qoder (manual trigger)
/engineering-frontend-developer

References

msitarzewski and others added 30 commits October 13, 2025 07:17
Complete collection of specialized AI agent personalities:
- 7 Engineering specialists (Frontend, Backend, Mobile, AI, DevOps, etc.)
- 6 Design specialists (UI, UX, Brand, Whimsy, etc.)
- 8 Marketing specialists (Growth, Content, Social Media, etc.)
- 3 Product specialists (Sprint Planning, Research, Feedback)
- 5 Project Management specialists
- 7 Testing specialists (QA, Performance, API, etc.)
- 6 Support specialists (Analytics, Finance, Legal, etc.)
- 6 Spatial Computing specialists (XR, AR/VR, Vision Pro)
- 3 Specialized agents (Orchestrator, Data Analytics, LSP)

Each agent includes:
- Distinct personality and communication style
- Technical deliverables with code examples
- Step-by-step workflows
- Success metrics and benchmarks
- Real-world tested approaches

Ready for community contributions and feedback!
Replace placeholder 'yourusername' with 'msitarzewski' in:
- GitHub stars badge
- Discussions links
- Issues links
- Footer navigation links

Repository: https://github.com/msitarzewski/agency-agents
New design specialist focused on crafting professional photography
prompts for AI image generation tools. Includes comprehensive
frameworks for portrait, product, landscape, and fashion photography
with platform-specific optimization for Midjourney, DALL-E, Stable
Diffusion, and Flux.
- Fix malformed YAML frontmatter with literal \n characters in agent files
- Fix insecure HTTP link in README (http:// -> https://)
- Update outdated year references (2024 -> 2025)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
- Sales Data Extraction Agent: monitors Excel files and extracts MTD/YTD/Year End metrics
- Data Consolidation Agent: aggregates sales data into live dashboard reports
- Report Distribution Agent: automates territory-based report delivery to reps

https://claude.ai/code/session_01AEiWwqyjysw81oCnATatBg
…nd-security-issues

Fix YAML frontmatter parsing and security issues
Thank you!
…nitial-scaffold-ci-and-readme-64-3g

Merge agent/featproject-add-initial-scaffold-ci-and-readme-64-3g into main
Thank you!
Update 19 agent name: fields from slug-style (e.g. "engineering-ai-engineer")
or code-style (e.g. "ArchitectUX") to clean human-readable names (e.g.
"AI Engineer", "UX Architect"). Add missing YAML frontmatter to 2 spatial-
computing agents. All 51 agents now use consistent naming that aligns with
the NEXUS strategy docs.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…ter-name-consistency

Fix agent frontmatter name consistency
…-BDrOP

feat: Add three specialized STGCRM reporting agents
…aphy-prompt-01N766LRToUNDSUFukcbsHoC

Add Image Prompt Engineer agent
Remove all hardcoded "51" agent counts from README and strategy docs to
avoid future maintenance burden as new agents are contributed. Add Image
Prompt Engineer (Design), Sales Data Extraction Agent, Data Consolidation
Agent, and Report Distribution Agent (Specialized) to all roster listings.
Fix slug-style name on Image Prompt Engineer frontmatter.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…ed-agent-counts

Remove hardcoded agent counts, add new agents to rosters
Fix docs: GitHub links in CONTRIBUTING.md
…tity-trust

Add Agentic Identity & Trust Architect - Specialized
Thank you!
Remove unrestricted Bash tool access from 7 agents that only need
analytical/advisory capabilities, rewrite the Social Media Strategist
agent (was a duplicate of Twitter Engager) to cover multi-platform
strategy as intended, fix incorrect descriptions, harden webhook
example to use env vars, and clarify ambiguous AMA language.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Fix security vulnerabilities from AI agent prompt audit

Excellent. Thank you!
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds a lint script and GitHub Actions workflow that checks agent
markdown files for required YAML frontmatter fields (name, description,
color) and recommends standard sections. Only changed files in PRs
are validated to avoid blocking on pre-existing issues.
Adds structured templates for new agent requests, bug reports,
and pull requests to streamline contributions and ensure consistency.
Adds a specialized Security Engineer agent covering threat modeling,
vulnerability assessment, secure code review, and security architecture.
This fills a gap in the Engineering Division where no dedicated security
specialist existed.
- Add missing color field to 4 agents: content-creator, growth-hacker,
  social-media-strategist, data-analytics-reporter
- Replace non-standard tools field with the required color field
- Fix CRLF line endings in agentic-identity-trust.md
Prevents CRLF line endings from being committed on Windows, which
can break frontmatter parsing in agent markdown files.
Adds two step-by-step workflow examples showing how to coordinate
multiple agents for real projects:

- Startup MVP: 7 agents across a 4-week build cycle
- Landing Page Sprint: 4 agents shipping a page in one day

Each example includes exact prompts to copy, handoff patterns, and
tips for passing context between agents. Checks off the
"Multi-agent workflow examples" item from the roadmap.
- Add Security Engineer to README Engineering Division table
- Update Semgrep action from returntocorp to semgrep namespace
- Update Pydantic example to v2 syntax (field_validator + classmethod)
- Fix ((errors++)) causing early exit under set -e
- Fix command injection in workflow by using env variable
- Add strategy/ directory to lint paths and AGENT_DIRS
msitarzewski and others added 28 commits March 14, 2026 18:15
Clarify what belongs in a PR vs. a Discussion — agent files are always
welcome, but tooling/architecture/bulk changes should start as a
Discussion first. Committed build output will always be closed.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
feat: add Workflow Architect specialized agent
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
147 agents, 12 divisions, contributors from around the world.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Signed-off-by: CagesThrottleUs <manstein.felix@gmail.com>
Signed-off-by: CagesThrottleUs <manstein.felix@gmail.com>
Solution architecture agent for Salesforce platform — multi-cloud design,
integration patterns, governor limits, deployment strategy, and data model
governance for enterprise-scale orgs.
Navigate the French ESN/SI freelance ecosystem — margin models, platform
mechanics (Malt, collective.work), portage salarial, rate positioning,
and payment cycle realities.
Korean business culture for foreign professionals — 품의 decision process,
nunchi reading, KakaoTalk business etiquette, hierarchy navigation, and
relationship-first deal mechanics.
Add Anthropologist, Geographer, Historian, Narratologist, and Psychologist
agents to support world-building and narrative design with scholarly rigor.
Update README with new Academic Division table.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…s-default-mode

feat(scripts): add opt-in parallel execution to convert & install
Great additions @sebastientang — all three agents are excellent. We'll handle the README table updates on our end. 😉
Add French Consulting Market Navigator - Specialized
Adds Specialized Division table rows for agents merged in #207, #208, #209.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
feat: add Academic Division with 5 storytelling agents
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Closes #220

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Refined from #51 by @SiamakSafari — restructured into standard template
with proper YAML frontmatter, deliverable templates, and platform-specific
citation patterns.

Co-Authored-By: SiamakSafari <SiamakSafari@users.noreply.github.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Sync with upstream: keep all Chinese translations, add 30 new files
from upstream including integrations/, examples/, new agents, and
GitHub templates/workflows.
- README.md: 扩展 Cursor 章节,增加 Settings > Rules > Project Rules 操作路径、
  使用示例和常见问题排查
- README.zh-TW.md: 同步更新繁体中文版
- integrations/cursor/README.md: 更新安装路径、新增 Finding and Activating Rules
  和 Troubleshooting 章节,修正智能体数量为 180
- 说明 alwaysApply:false 的智能匹配机制
- 警告 180 个规则可能影响匹配准确度
- 提供全量安装+精简和按需复制两种方案
- 补充 @规则名 手动引用方式
- 恢复 convert.sh 步骤(integrations/ 在 .gitignore 中,用户 clone 后为空)
- 6 个上游新智能体的 description 翻译为中文(提升 Cursor 智能匹配准确度)
- 智能体总数从 180 更新为 186(142 翻译 + 44 原创)
- 中文/繁体 README 同步更新
@jnMetaCode
Copy link
Owner

感谢 Qoder 支持的贡献!核心功能(convert.sh + install.sh)看起来不错,但 PR 范围太大了(34 个文件),包含了很多与 Qoder 无关的改动,review 起来比较困难。

核心 Qoder 改动(可以合并):

  • scripts/convert.shconvert_qoder() + get_qoder_tools()
  • scripts/install.shdetect_qoder() + install_qoder()
  • ✅ README 中 Qoder 相关的更新

建议拆出去的改动:

  1. 项目模板 — FUNDING.yml、issue template、PR template 属于项目治理,请单独提 PR
  2. 新智能体 — marketing-ai-citation-strategist、marketing-bilibili-content-strategist、recruitment-specialist、supply-chain-strategist 请单独提 PR(注意 supply-chain-strategist 可能和现有的重复,见 智能体 重复 #26
  3. lint-agents.yml 工作流 — 我们已有 ci.yml,可能冲突,请单独提 PR 讨论
  4. integrations/ README — 各工具文档有价值,但请单独提 PR
  5. examples/ 工作流 — 单独提 PR

请拆分为:

  1. PR-A: 纯 Qoder 支持(convert.sh + install.sh + README 更新)← 这个可以很快合并
  2. PR-B: 新智能体
  3. PR-C: 项目模板 + CI 工作流
  4. PR-D: integrations 文档 + examples

这样核心功能可以先合并,其他改动也能得到更仔细的 review。谢谢!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.