Adds a new skill, `/core:debug`, to provide a structured workflow for debugging issues. The skill is defined in `claude/code/commands/debug.md` and follows the systematic protocol outlined in the original request.
The debugging protocol includes the following steps:
1. Reproduce
2. Isolate
3. Hypothesize
4. Test Hypotheses
5. Fix
6. Verify
New slash commands:
- /collect:collect - Auto-detect and collect any resource
- /collect:github - Collect GitHub repos/orgs
- /collect:website - Crawl websites with depth control
- /collect:excavate - Full project archaeology dig
- /collect:papers - Collect whitepapers from registry
All commands use Borg CLI (github.com/Snider/Borg) for collection.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Remove custom collection scripts in favour of Borg
(github.com/Snider/Borg) for data collection. Skills now document
what to collect, with Borg handling the actual collection.
Removed:
- collect-whitepaper.sh, dispatch.sh, update-index.sh
- All skill-specific bash scripts (collect.sh, generate-jobs.sh, etc.)
- hooks.json and HOOKS.md
Updated:
- plugin.json to reference Borg dependency
- SKILL.md files with Borg command examples
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Move collection hooks, scripts, and all skills from claude/code to
new claude/collect plugin. Updates marketplace.json and plugin
descriptions accordingly.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Restructure Gemini extension files that were incorrectly placed at repo
root. Updates script paths to reference shared claude/code/ scripts.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Reorganise as a marketplace with multiple focused plugins:
- claude/code: Core development (hooks, scripts, data collection)
- claude/review: Code review automation
- claude/verify: Work verification
- claude/qa: Quality assurance loops
- claude/ci: CI/CD integration
Structure:
- .claude-plugin/marketplace.json lists all plugins
- Each plugin has its own .claude-plugin/plugin.json
- Commands namespaced: /code:*, /review:*, /qa:*, etc.
Install individual plugins or all via marketplace:
claude plugin add host-uk/core-agent
claude plugin add host-uk/core-agent/claude/code
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add .claude-plugin/plugin.json manifest for auto-updates
- Move claude/ contents to root level (commands/, hooks/, scripts/, skills/)
- Update hooks.json to use ${CLAUDE_PLUGIN_ROOT} for portability
- Add .gitignore for IDE files
- Update CLAUDE.md with new structure and installation instructions
Plugin can now be installed via:
claude plugin add host-uk/core-agent
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Scripts:
- auto-approve.sh: PermissionRequest hook that allows all tools
- ensure-commit.sh: Stop hook that blocks with uncommitted changes
- qa-filter.sh: PostToolUse hook that extracts QA failures only
- qa-verify.sh: Stop hook that runs QA and blocks on failures
Updated skill files to reference script paths.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add skill files for autonomous workflows:
- yes.md: Auto-approve mode with commit requirement
- qa.md: Iterative QA fix loop for Go/PHP projects
Both skills use skill-scoped hooks to modify Claude's behavior
during execution.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Skill that enables "just do it" mode:
- Auto-approves all permission requests via PermissionRequest hook
- Ensures work completes with commit via Stop hook
- Skill-scoped hooks (only active during skill)
- Still respects safety blocks from prefer-core.sh
Usage: /core:yes fix the failing test and commit
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
6 new issues for Claude Code hook improvements:
- 012: Test output filtering (reduce noise, show failures only)
- 013: Stop verification (verify work complete before stopping)
- 014: Auto-test on edit (async tests after code changes)
- 015: Session context injection (git/issues/CI on startup)
- 016: Silent auto-formatting (suppress formatter output)
- 017: Expose/hide policy (define what to show vs suppress)
Based on Claude Code hooks documentation:
- PostToolUse with suppressOutput for noise reduction
- Stop hooks with agent verification
- Async hooks for background testing
- SessionStart for context injection
- additionalContext for exposing important info
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Document the approach of using `core` CLI instead of raw commands:
- Command mapping table (go/php/git → core equivalents)
- Key commands reference for dev, go, php, build, ai, qa
- Missing features → raise issues on host-uk/core
- TDD approach: code as if functionality exists
Every agent using core tests the framework, making it bulletproof.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Consolidates the repository structure:
- Move skills/ to claude/skills/
- Move collection hooks to claude/collection/
- Update CLAUDE.md to reflect unified structure
Public version remains at core-claude; this is the advanced in-house version.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
