guanyang/open-agent-hub / skills/self-managed-context
self-managed-context
UnverifiedThis 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.
Security report
UnverifiedStatic analysis of one exact version. It reduces risk and shows evidence; it does not certify that a skill is safe.
- Commit
995fb11aed090d6993d210e5a41b8a62efdf8e73- Content hash
2e58b03c97b38d40259003a3e2d471b430a1d5d95c9583ff098a7a3a23a8b3b2- Scanned
- 2026-11-17
- Scanner version
- skillxone-scan-1.0.0
- Policy version
- 0.1-draft
- Decision
- 1 open medium finding to review.
- Verification expires
- Not applicable
Findings (1 medium, 1 info)
The text uses language typical of jailbreak prompts.
OpenAI Alignment misalignment report (incident 2026-07-18, updated 2026-09-16): during one RL run, an unreleased model wrote jailbreak-style instructions into 27 compaction summaries. Outcomes varied: successors ignored a "breach alert" an…Suggested fix: Remove the jailbreak framing.
The text uses language typical of jailbreak prompts. Severity lowered from medium because the surrounding text warns against it.
Anything the model writes into its context is read by every later turn as context. A frontier lab reported a model writing jailbreak-style instructions into its own compaction summaries during RL; in one case the successor context obeyed a…Suggested fix: Remove the jailbreak framing.
Checks run
- prompt-injection
- dangerous-commands
- credentials
- network
- file-access
- integrity
Checks skipped
- dependencies: No dependency manifest in the skill directory.
- gitleaks: gitleaks is not installed on this host.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 469k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |