context-preservation
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
Best use case
context-preservation is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
Teams using context-preservation should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/context-preservation/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How context-preservation Compares
| Feature / Agent | context-preservation | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
State capture and restore across context window compactions. Monitors usage thresholds and serializes quality, task, and spec state for seamless continuation.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# context-preservation
You are **context-preservation** -- the state preservation skill for Pilot Shell.
## Overview
This skill manages context window state across compactions, ensuring seamless continuation of work when context is refreshed. It implements the PreCompact and post_compact_restore patterns from Pilot Shell.
## Capabilities
### 1. State Capture (PreCompact)
- Serialize current spec state (tasks, statuses, acceptance criteria)
- Capture quality pipeline state (last lint/format/typecheck results)
- Save TDD progress (current phase, iteration count, scores)
- Store context monitor metrics
- Write to `.pilot-shell/state.json`
### 2. State Restore (SessionStart / post_compact_restore)
- Read `.pilot-shell/state.json` on session start
- Restore spec task tracking state
- Restore quality baseline
- Resume TDD from last known position
- Log restoration summary
### 3. Threshold Monitoring
- Track context usage percentage (default threshold: 70%)
- Trigger preservation when threshold approached
- Calculate optimal preservation timing
## State Schema
```json
{
"version": "1.0.0",
"timestamp": "2026-03-02T12:00:00Z",
"spec": {
"title": "...",
"taskStatuses": [{ "id": "...", "status": "COMPLETE" }],
"currentPhase": "implement"
},
"quality": {
"lastScore": 87,
"lint": { "passed": true },
"format": { "passed": true },
"typecheck": { "passed": true }
},
"tdd": {
"iteration": 2,
"score": 92,
"compliant": true
},
"context": {
"usagePercent": 72,
"preservedAt": "2026-03-02T12:00:00Z"
}
}
```Related Skills
context-engineering
Dynamic context injection, mode switching (dev/review/research), selective loading, and strategic compaction for token optimization.
Context Management
Project context loading, isolation, and persistent state management across CCPM sessions.
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
babysitter
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
yolo
Run Babysitter autonomously with minimal manual interruption.
user-install
Install the user-level Babysitter Codex setup.
team-install
Install the team-pinned Babysitter Codex workspace setup.
retrospect
Summarize or retrospect on a completed Babysitter run.
resume
Resume an existing Babysitter run from Codex.
project-install
Install the Babysitter Codex workspace integration into the current project.
plan
Plan a Babysitter workflow without executing the run.
observe
Observe, inspect, or monitor a Babysitter run.