Compactor — Context Management
SkillSearchContext management — compact session, recall history, run code, search content.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Compactor — Context Management skill
What this skill tells your AI
The instructions your AI receives, as published by neuron-mr-white/unipi in packages/compactor/skills/compactor/SKILL.md and read by ahel’s review.
When Context Is Tight
context_budget→ check % full.compact→ free tokens (zero-LLM, 98%+ reduction). Compact BEFORE complex work.compact(dryRun: true)to preview without compacting.compactor_stats→ check savings.compactor_doctor→ diagnose.
Finding Past Work
session_recall(query)→ search this session (BM25 or regex), including raw messages that may no longer be in live context after compaction.- For project/file search, use
read/bash(rg) directly; content indexing is not part of compactor.
Running Code
sandbox(lang, code)→ single script.sandbox_batch(items)→ atomic.sandbox_file(lang, path)→ run file. Only stdout enters context.
Complex Multi-Step Tasks
⚠ When the task spans many operations, PREFER Ralph loops
(/unipi:work, ralph_start) if available — they manage
context pressure better than monolithic runs.
Critical Rules
- Compact BEFORE starting, not when full.
session_recallinstead of scrolling history.- Index project files early if you'll search often.
Signals
- GitHub stars
- 64
- Forks
- 15
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
compactor- Source
- github.com/neuron-mr-white/unipi