domains / families / agent-tooling / self-managed-context

self-managed-context

separate

This skill should be used when a model gets read-write control over its own live context window instead of a harness-scheduled compaction policy: the context exposed as an editable file the model rewrites with code tools, model-driven eviction and in-place updates, the harness invariants that keep self-editing safe (pinned prefix, edit gate, edit receipts, budget readouts, rollback on overflow), the prefix-cache cost of mid-context edits, and steering or training the model's own context-editing strategy. Route note content and fixed-threshold summarization to context-compression, cache-stable layout under harness control to context-optimization, file offloading to filesystem-context, and loop governance to self-improvement-loops.

When to use

• Giving a model write access to its own live context
• Designing a context-as-a-file protocol
• Keeping exact values or updating state in place
• Pricing mid-context edits under prefix caching
• Budget readouts and rollback for self-timed compaction
• Steering or training a model's context-editing strategy
• Diagnosing self-editing agent failures

When not to use

• Replacement-note content and fixed-threshold summarization
• Cache-stable layout and observation masking under harness control
• File offloading while the live context stays append-only
• Latent KV transfer between agents
• Cross-session stores
• Loop governance and acceptance gates

Skill page

Source