mv_load_scars
Load weighted corrective lessons from past contradictions to ground reasoning in audit lenses, sharpening insights into what consensus might suppress.
Instructions
Load the system's accumulated scars (corrective lessons), weighted by recency × reinforcement.
Use this in audit lenses to ground reasoning in what the system has been re-taught. Most useful for the Diverger lens: "what would consensus kill?" sharpens significantly when read against the system's own history of contradictions.
Weighting formula: weight = exp(-ageDays/30) × (1 + log2(1 + reinforceCount))
30-day recency halflife.
Logarithmic dampening on reinforcement (1 = ×2, 3 = ×3, 7 = ×4).
A scar reinforced 3+ times from 30+ days ago beats a one-time recent correction.
Scar source: feedback_*.md files in the memory directory. Each file's frontmatter:
name: description: type: feedback reinforces: # optional; absent = independent date: # optional; absent = falls back to file mtime
Default directory: ${HOME}/.claude/projects/${encoded-cwd}/memory Override via SCAR_DIR env var or scar_dir param.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| top_n | No | Limit to top N scars by weight. Omit for all. | |
| include_body | No | Include full prose body of each scar. Default false (header + description only). | |
| filter_type | No | Filter by frontmatter `type:` field. Default "feedback". Use "all" to disable. | |
| scar_dir | No | Override the scar directory. Falls back to SCAR_DIR env var, then computed default. |