framework-development

Guides editing, syncing, testing, and releasing ai-badger framework source files.

2|Updated Aug 2, 2026
One-click install
npx skills add https://github.com/Arasz/ai-raccoon --skill framework-development-arasz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: framework-development
Source: https://github.com/Arasz/ai-raccoon/tree/main/.ai-badger/skills/learned/uncategorized/framework-development
Command: npx skills add https://github.com/Arasz/ai-raccoon --skill framework-development-arasz

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Modifying the ai-badger framework is error-prone because edits must happen in features/<stack>/skills/ source directories while scaffolded copies in .ai-badger/skills/ and skills/ are overwritten by sync, and skipping the sync, freshness, or version steps breaks pre-commit gates and tests. This Skill encodes the verified edit-sync-test-build cycle and the pitfalls that repeatedly break contributors. ## Core Features & Use Cases - Source-of-truth workflow: Enforces editing features/<stack>/skills/<name>/ then running sync_plugin_skills.py, pytest, index_build.py --check, and the scaffold freshness guard before committing. - Subsystem recipes: Provides verified procedures for adding MCP catalog servers, framework hooks (Claude/Copilot/Hermes), project-local invariants, and skill scope registration in SKILL_SCOPES. - Release mechanics: Documents the VERSION bump, changelog, version_sync, and release_guard ordering, including the two-commit packaging forced by the pre-commit hook chain. - Use Case: When adding a new common MCP server to the catalog, follow the reference recipe covering meta.json, server.md line budget, tools.json tag vocabulary, availability gating, and the self-scaffold refresh with AI_BADGER_MCP_AVAILABILITY=all. ## Quick Start Ask the assistant to modify an ai-badger framework source file and run the full sync, test, and freshness-gate cycle before committing.

Frequently Asked Questions about framework-development

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I modify an ai-badger framework skill correctly?

Edit the source under features/<stack>/skills/<name>/, never the scaffolded copies in .ai-badger/skills/ or skills/. Then run sync_plugin_skills.py, pytest, index_build.py --check, and the scaffold freshness guard before committing all changed files together.

How do I add a new MCP server to the ai-badger catalog?

Create meta.json, server.md (15 lines maximum), and tools.json under features/common/mcp/<server>/, declare it in stack-mcp.json with an availability.command gate, bump VERSION first, then rebuild index.json and refresh the self-scaffold with AI_BADGER_MCP_AVAILABILITY=all.

Why does test_repo_plugin_copy_is_in_sync fail after my edit?

The test fails when scaffolded copies diverge from source files. You edited features/ source without running python3 tooling/sync_plugin_skills.py, or you edited the generated .ai-badger/skills/ or skills/ copies directly, which sync overwrites.

Why does the scaffold freshness guard report a stale tree?

The guard re-scaffolds a copy of the tree and diffs it against committed files. It fails when new feature files lack a matching self-scaffold refresh, or when a manual scaffold ran without AI_BADGER_MCP_AVAILABILITY=all and rewrote host-dependent files.

When should a skill be added to SKILL_SCOPES?

Add universal common skills to SKILL_SCOPES in engine/badger_lib.py as default or optIn. Stack-local skills must not be declared there; their stack directory is the declaration, and adding them creates a contradiction that breaks scaffold and sync tests.