- Mini-Reflect for fast workflow: Creator must restate task, list assumptions,
name highest-damage risk before proposing (catches misunderstandings early)
- Alternatives Considered section: Creator must evaluate 2+ approaches with
rejection rationale before committing to one (prevents tunnel vision)
- Structured confidence scoring: 3-axis table (task understanding, solution
completeness, risk coverage) replaces bare 0.0-1.0 number. Low scores
trigger targeted action (clarify, upgrade workflow, or research)
- Mini-Reflect fallback for skipped tasks: quick reflection even when
ArcheFlow doesn't activate (non-trivial single-file changes)
The 3-Sets framework doesn't transfer well to agents — all three
dimensions are fully visible and controllable config, not hidden
human psychology. Removed the branding, kept the practical bits:
- attention-filters: what context each archetype receives (token savings)
- memory: persistent learnings across orchestrations (project knowledge)
New skill: agent-diagnostic — applies the 3-Sets framework
(Tool-Set, Skill-Set, Mind-Set) to agent orchestration:
- Pre-orchestration diagnostic: check each agent's configuration
across three dimensions, fix the weakest set first
- Chain principle: weakest set caps output (Opus + bad prompt = waste)
- Alignment principle: modest aligned agents beat excellent misaligned ones
- Attention filters: each archetype reads only relevant artifacts
- Post-orchestration learning: extract learnings to persistent memory
structured by the three sets
Based on the 3-Sets Method diagnostic framework.
- Consolidate to single shadow per archetype (fold best bits from
dropped shadows into the remaining one)
- Trim bootstrap skill from 515 to 254 words (~50% token reduction)
- Remove redundant shadow table from bootstrap (already in archetype table)
