context-health-monitor
Monitors context complexity and triggers state dumps before quality degrades
- License 许可
- MIT
- 最近更新
- 2026-11-05
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- context-health-monitor
- description
- Monitors context complexity and triggers state dumps before quality degrades
03 SKILL.md 正文
Context Health Monitor
Purpose
Prevent "Context Rot" — the quality degradation that occurs as the agent processes more information in a single session.
When This Skill Activates
The agent should self-monitor for these warning signs:
Warning Signs
| Signal | Threshold | Action |
|---|---|---|
| Repeated debugging | 3+ failed attempts | Trigger state dump |
| Going in circles | Same approach tried twice | Stop and reassess |
| Confusion indicators | "I'm not sure", backtracking | Document uncertainty |
| Session length | Extended back-and-forth | Recommend /pause |
Behavior Rules
Rule 1: The 3-Strike Rule
If debugging the same issue fails 3 times:
- STOP attempting fixes
- Document in
.gsd/STATE.md:- What was tried
- What errors occurred
- Current hypothesis
- Recommend user start fresh session
- Do NOT continue with more attempts
Rule 2: Circular Detection
If the same approach is being tried again:
- Acknowledge the repetition
- List what has already been tried
- Propose a fundamentally different approach
- Or recommend
/pausefor fresh perspective
Rule 3: Uncertainty Logging
When uncertain about an approach:
- State the uncertainty clearly
- Document in
.gsd/DECISIONS.md:- The uncertain decision
- Why it's uncertain
- Alternatives considered
- Ask user for guidance rather than guessing
State Dump Format
When triggered, write to .gsd/STATE.md:
## Context Health: State Dump
**Triggered**: [date/time]
**Reason**: [3 failures / circular / uncertainty]
### What Was Attempted
1. [Approach 1] — Result: [outcome]
2. [Approach 2] — Result: [outcome]
3. [Approach 3] — Result: [outcome]
### Current Hypothesis
[Best guess at root cause]
### Recommended Next Steps
1. [Fresh perspective action]
2. [Alternative approach to try]
### Files Involved
- [file1.ext] — [what state it's in]
- [file2.ext] — [what state it's in]
Auto-Save Protocol
Critical: When any warning signal triggers, the agent must save state BEFORE recommending /pause to the user. This ensures state persists even if the session hard-terminates.
Steps
- Write a state snapshot to
.gsd/STATE.mdimmediately when a threshold is hit - Include at minimum: current phase, current task, last action, next step
- Then inform the user of the situation and recommend
/pause
Why
Sessions can terminate abruptly (usage limits, context limits, network errors). If the agent waits for the user to type /pause, it may never get the chance. By saving first and recommending second, state is always preserved.
Integration
This skill integrates with:
/pause— Triggers proper session handoff (includes proactive auto-save)/resume— Loads the state dump context- Rule 3 in
GEMINI.md— Context Hygiene enforcement
04 同仓库更多 Skills
verifier
Validates implemented work against spec requirements with empirical evidence
token-budget
Manages token budget estimation and tracking to prevent context overflow
planner
Creates executable phase plans with task breakdown, dependency analysis, and goal-backward verification
plan-checker
Validates plans before execution to catch issues early
status
Show MemPalace status — room counts, storage usage, and palace health.
search
Search your MemPalace — semantic search across all mined memories, projects, and conversations.