Context Surfing

Keeps your agent coherent during long multi-step tasks by monitoring context quality like a surfer reading a wave. It activates automatically after you've set intent and plan, watches for drift signals like hallucination or hedging, and exits cleanly with a handoff file before output quality degrades. Integrates with Entire CLI to use session state as ground truth, works alongside intent-framed-agent (which checks scope while this checks coherence), and hands off to simplify-and-harden when the work completes. Most useful for complex refactors or unfamiliar codebases where silent context corruption would be expensive. Think of it as the execution wrapper that keeps you from working with a confused agent.

skills.sh installs: 269
GitHub stars: 331
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add pskoett/pskoett-ai-skills --skill context-surfing --agent claude-code

Installs into .claude/skills of the current project.

Files

Context Surfing

Install

gh skill install pskoett/pskoett-skills context-surfing

Fallback using the Agent Skills CLI:

npx skills add pskoett/pskoett-skills/skills/context-surfing

The agent rides the wave of peak context. When the wave crests, it commits. When it detects drift, it pulls out cleanly — saving state, handing off, and letting the next session catch the next wave.

No wipeouts. No zombie sessions. Only intentional, high-fidelity execution.

Mental Model

Think of context like an ocean wave:

Paddling in = loading the intent frame, plan, and initial context. Energy is building.
The peak = full context coherence. The agent knows exactly what it's doing and why. This is when to execute.
The shoulder = context starting to flatten. Still rideable, but output density is dropping.
The close-out = drift. Contradiction, hedging, second-guessing, or hallucinated details. Wipe-out territory.

The skill's job: ride as long as the wave is good, exit before it closes out.