core/agent
8
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
8 commits 2 branches 0 tags 446 KiB
Commit graph

7 commits

Author SHA1 Message Date
Snider
fd84bf2bd1 docs: add skills section to overview (018, 019) 
Added Skills (autonomous workflows) section:
- #018: /core:yes - auto-approve, ensure commit
- #019: /core:qa - iterative QA fix loop

Updated implementation phases to include skills in Phase 4.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-02-01 19:06:59 +00:00
Snider
42f536b351 docs: add /core:qa iterative QA fix loop skill task 
Skill that runs QA and fixes issues iteratively:
- Detects Go/PHP project type
- Runs core go qa / core php qa
- Parses output, extracts actionable issues
- Fixes in priority order: fmt → lint → test
- Re-runs QA until all checks pass
- Stop hook prevents stopping until QA clean

Hooks:
- PostToolUse: qa-filter (suppress verbose, show failures only)
- Stop: qa-verify (block if QA still failing)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-02-01 19:03:32 +00:00
Snider
e16aff7162 docs: add /core:yes auto-approve skill task 
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>
 2026-02-01 19:00:25 +00:00
Snider
8fed5bc6ef docs: add hook improvement tasks for better feedback cycle 
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>
 2026-02-01 18:57:16 +00:00
Snider
beb24f71d2 docs: add feature request issues for core CLI migration 
12 issue files documenting features needed to replace shell scripts:

Claude Code hooks:
- 001: core ai session (state management)
- 002: core ai context (fact capture)
- 003: core ai hook (command validation)
- 004: core qa debug (debug statement detection)

Data collection:
- 005: core collect github (issues/PRs archive)
- 006: core collect bitcointalk (forum threads)
- 007: core collect market (CMC/CoinGecko)
- 008: core collect papers (whitepapers)
- 009: core collect excavate (project archaeology)
- 010: core collect process (HTML→MD)
- 011: core collect dispatch (event hooks)

000: Overview tracking issue

These will be submitted to host-uk/core when rate limit resets.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-02-01 18:49:35 +00:00
Snider
9f1950c231 refactor: unify claude-cowork into claude directory 
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>
 2026-02-01 18:23:41 +00:00
Snider
7faa974546 feat: add Claude Code plugin and CLAUDE.md documentation 
Initial commit establishing core-agent repository with:
- Claude Code plugin hooks (safety checks, auto-formatting, context preservation)
- Collection skills for blockchain research archival (claude-cowork/)
- CLAUDE.md documenting repository structure and development patterns

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2026-02-01 18:15:01 +00:00