Menu
Expose read_text_file as a benchmark visibility-only skill.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Register AgentImage packages, publish checkpoint-derived images, or replace the current process image. Use when creating reusable runtime configurations or deliberately changing process code, tools, prompt identity, memory, or authority.
Diagnose this process's Capability authority and request one exact Human policy decision when a protected operation lacks requestable authority. Do not use it for intent questions, validation errors, provider failures, or speculative privilege expansion.
Delegate one attenuated Capability to a known direct child or revoke one exact Capability. Do not create children, grant peers or grandchildren, amplify authority, or treat revocation as rollback of completed effects.
Capture, inspect, compare, restore, or fork durable process-subtree checkpoints. Use for recoverable internal-state milestones, isolated replay, or deliberate rollback of reconstructable Agent libOS state.
Spawn or fork direct AgentProcess children, coordinate their lifecycle and messages, then import selected results. Use for bounded parallel delegation, isolated exploration, or structured parent-child collaboration.
Run one policy-governed, non-interactive host command through the argv-only Shell boundary. Use for builds, tests, searches, or utilities lacking a narrower tool; not for general Git, TTY/streaming work, ad hoc remotes, or attempts to evade policy.
| name | read-tool |
| description | Expose read_text_file as a benchmark visibility-only skill. |
| metadata | {"agent-libos.version":"v0"} |
| allowed-tools | ["read_text_file"] |
This benchmark skill makes read_text_file visible to the process. It does not
grant filesystem authority.
The default benchmark image may already expose read_text_file; this fixture's
primary purpose is to prove that activating a Skill and adding tool visibility
does not create a matching filesystem:* capability. The process still needs
skill:read-tool execute to activate the Skill and separate filesystem read
authority to use the tool successfully. This fixture is used by
skill_tool_visibility_001.
