# Tlamatini Planner Trace Replay

> Replay the most recent global execution planner trace from tlamatini.log and explain why each capability got the score it did.

- Skill: `xaiht/tlamatini-planner-trace-replay` (Agent Skill)
- Install (CLI): `npx skillmds@latest add xaiht/tlamatini-planner-trace-replay`
- Raw SKILL.md: https://api.skillmd.com/api/skills/xaiht/tlamatini-planner-trace-replay/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: XAIHT (https://skillmd.com/u/xaiht)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/xaiht/tlamatini-planner-trace-replay

---

<!--
═══════════════════════════════════════════════════════════════════
  ✦  T L A M A T I N I  ✦   —   "one who knows"
  Created by  Angela López Mendoza   ·   @angelahack1
  Developer · Architect · Creator of Tlamatini
  Tlamatini Author Banner — do not remove (Angela's name is kept in every build)
═══════════════════════════════════════════════════════════════════
-->

# Planner trace replay

Read the tail of `Tlamatini/tlamatini.log`. Locate the most recent
`build_global_execution_plan` invocation and the per-capability scoring
output.

For each capability the planner scored:
- record its score and the keywords that contributed
- record whether it was selected (top-N cap, see
  `max_selected_tools = 20` per gotchas.md #11)
- if a capability that "should" have been selected was not, explain why

Return `{ traces: [...], notes }`. Keep traces under 32 KB total to
preserve context.