mirror of
https://github.com/boshu2/agentops.git
synced 2026-09-14 15:08:13 +08:00
Boden Fuller
2b338ee0c3
Go fixes: - Fix UTF-8 boundary slicing in narrative truncation (rune-safe truncateRunes helper) - Add signal.Stop to rpi_serve signal handlers (prevent goroutine leak) - Replace CORS wildcard with localhost-only validation (prevent cross-site reads) - Surface SSE polling errors to client instead of silent continue - Extract section name constants (HISTORY/INTEL/TASK) from magic strings - Add intel_scope enum validation (none/topic/full) - Sort resolveSkillPath glob matches for deterministic resolution - Add random suffix to adhoc context IDs (prevent 1-second collision) - Surface writePromptAuditTrail errors to stderr unconditionally - Document RPI_RUN_ID env var in ao inject --help Doc fixes: - Replace stale /learn skill references with /retro --quick across 9 workflow docs - Replace .agents/retros/ with .agents/council/ in post-mortem SKILL.md + references - Reorder GOALS.md directives to sequential 1-8 numbering - Rename post-mortem Phase 2 steps from 4.x to EX.x - Update SKILL-TIERS.md: council + retro → council + knowledge lifecycle - Sync all changes to skills-codex mirror Epic: na-7r3 (6 issues, 2 waves)
2.2 KiB
2.2 KiB
name, description, estimated_time, phases
| name | description | estimated_time | phases |
|---|---|---|---|
| knowledge-synthesis | Extract and synthesize knowledge from multiple sources | 30-60 minutes | 3 |
Knowledge Synthesis Workflow
Purpose: Combine knowledge from code, docs, history, and patterns
When to use:
- Onboarding (understand new codebase)
- Documentation (create comprehensive guides)
- Pattern extraction (learn from multiple implementations)
- Architecture review (understand system design)
Token budget: 40-60k tokens (single session)
Workflow Phases
Phase 1: Gather (15-20% context)
↓
Phase 2: Synthesize (10-15% context)
↓
Phase 3: Document (5-10% context)
Phase 1: Gather
Goal: Collect knowledge from multiple sources
Commands:
/research-multi "[topic]"
# Launches 3 agents in parallel:
# - code-explorer: Code structure
# - doc-explorer: Documentation
# - history-explorer: Git history
Output: Combined research from 3 perspectives
Phase 2: Synthesize
Goal: Connect insights, identify patterns
Activities:
- Cross-reference findings
- Extract common patterns
- Identify best practices
- Note gaps or inconsistencies
Output: Synthesized understanding
Phase 3: Document
Goal: Capture knowledge for future use
Commands:
/retro --quick [topic]
# Creates pattern documentation
# Updates knowledge base
Output: Documentation + pattern catalog
Example: Understand Auth System
Read CLAUDE.md
/research-multi "authentication and authorization system"
# Agent 1 (Code):
# - auth/ directory structure
# - JWT validation in middleware
# - Session management in handlers
# Agent 2 (Docs):
# - docs/auth-design.md explains OAuth2 flow
# - examples/auth-example/ shows usage
# Agent 3 (History):
# - Added in commit abc123 (2024-03)
# - Refactored in commit def456 (2024-08)
# - Pattern: Standard OAuth2 + custom claims
# Synthesis:
# Authentication: OAuth2 with JWT
# Authorization: Role-based (admin, user, guest)
# Pattern: Middleware-based validation
# Best practice: Separate auth concerns from business logic
/retro --quick auth-system-knowledge
# Documented for future reference
Start knowledge synthesis with: Read CLAUDE.md + /research-multi