badi
CLAUDE.md8 starsChanged 3 months agoMITView on GitHub
Structured operations management for Claude Code. 30 agents, 86 commands, 14 hooks, 63 opt-in skill categories. v1.20+ prompt-aware skill router; v1.25+ pentest-* family (25 categories, advisory/defensive); v1.26+ profile-based command management (core/dev/content/pentest) + command routing; v1.27+ expo-* family (12 categories, Expo + React Native mobile dev lifecycle); v1.32+ virtual eng team (product-strategist, engineering-manager, release-manager, qa-lead + /ceo-review, /eng-review, /qa, /ship) + the /team orchestrator; v1.33+ ads review (ads-strategist agent + /meta-review + /ads-review, advisory-only). v1.34+ research/SEO/data advisory agents (market-researcher, seo-strategist, data-analyst).
In this repository63 other files it gives its agents.
- ai-automationSkill
- consultingSkill
- contentSkill
- customer-successSkill
- data-analyticsSkill
- designSkill
- design-tokensSkill
- developmentSkill
- devopsSkill
- ecommerceSkill
- emailSkill
- expo-app-configSkill
- expo-config-pluginSkill
- expo-dev-clientSkill
- expo-eas-buildSkill
- expo-eas-submitSkill
- expo-eas-updateSkill
- expo-modulesSkill
- expo-notificationsSkill
- expo-orchestratorSkill
- expo-prebuildSkill
- expo-routerSkill
- expo-troubleshootingSkill
- financeSkill
- frontend-tasteSkill
- marketingSkill
- market-researchSkill
- mobileSkill
- pentest-adSkill
- pentest-apiSkill
- pentest-bizlogicSkill
- pentest-bugbountySkill
- pentest-cicdSkill
- pentest-cloudSkill
- pentest-credentialsSkill
- pentest-ctfSkill
- pentest-detectionSkill
- pentest-engagementSkill
- pentest-exploit-chainSkill
- pentest-forensicsSkill
- pentest-llmSkill
- pentest-malwareSkill
- pentest-mobileSkill
- pentest-opsec-evidenceSkill
- pentest-orchestratorSkill
- pentest-privescSkill
- pentest-reconSkill
- pentest-reportSkill
- pentest-socialSkill
- pentest-stigSkill
- pentest-threat-modelSkill
- pentest-webSkill
- pentest-wirelessSkill
- productivitySkill
- productSkill
- salesSkill
- security-checkSkill
- securitySkill
- seo-crawl-budgetSkill
- seoSkill
- The first 60 shown.
The file
Files
Badi - Workflow Management System
Structured operations management for Claude Code. 30 agents, 86 commands, 14 hooks, 63 opt-in skill categories. v1.20+ prompt-aware skill router; v1.25+ pentest-* family (25 categories, advisory/defensive); v1.26+ profile-based command management (core/dev/content/pentest) + command routing; v1.27+ expo-* family (12 categories, Expo + React Native mobile dev lifecycle); v1.32+ virtual eng team (product-strategist, engineering-manager, release-manager, qa-lead + /ceo-review, /eng-review, /qa, /ship) + the /team orchestrator; v1.33+ ads review (ads-strategist agent + /meta-review + /ads-review, advisory-only). v1.34+ research/SEO/data advisory agents (market-researcher, seo-strategist, data-analyst).
Memory Rules
| Layer | File | Limit |
| Session | .claude/memory.md | 100 lines; /clear when exceeded |
| Knowledge Base | .claude/knowledge-base.md | 200 lines, with Auditor approval |
| Task Board | .claude/workspace/TaskBoard.md | No limit |
| Skills Vault | .claude/skills-vault/ | 63 categories (26 general + 25 pentest-* + 12 expo-*), not loaded (opt-in) |
| Active Skills | .claude/skills/ | User selection (badi skills) |
| Commands Vault | .claude/commands-vault/ | 86 commands canonical (v1.26+), not loaded |
| Active Commands | .claude/commands/ | Filtered by profile (badi commands profile) |
- TBD/TODO/FIXME are FORBIDDEN inside
knowledge-base.md - A source is mandatory for knowledge entries:
[Kaynak: ...] settings.jsonmust be valid JSON; hooks must be executable
Daily Flow
Morning: /start | Midday: /sync | Evening: /wrap-up | When needed: /audit, /review, /unstickCLI
badi init | update | doctor | list | plugin | content | stats | completion | schedule
badi skills [available|list|add|remove|clear] # Opt-in skill management (v1.17+)
badi list --agents|--commands|--hooks|--skills # Detailed component listing
badi content [post|carousel|video|visual|calendar|brand|search|template|perf]
badi schedule [add|list|remove|check]Context Health
- Suggest
/clearwhen the token limit approaches memory.md> 80 lines: consolidation warning- Compaction:
pre-compact-handoff.mjs→ compact →post-compact-resume.mjs
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

