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)…
Install
npx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill self-managed-contextnpx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill self-managed-context -a claude-code -gnpx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill self-managed-context -a codex -ggemini skills install https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering.git --path skills/self-managed-contextgh skill install muratcankoylan/Agent-Skills-for-Context-Engineering self-managed-contextgit clone --depth 1 https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering /tmp/muratcankoylan__Agent-Skills-for-Context-Engineering
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/muratcankoylan__Agent-Skills-for-Context-Engineering/skills/self-managed-context ~/.claude/skills/self-managed-context # Claude Code
cp -R /tmp/muratcankoylan__Agent-Skills-for-Context-Engineering/skills/self-managed-context ~/.agents/skills/self-managed-context # Codex, Cursor, Gemini CLI, Copilot, OpenCode