Menu
Defines tool permission profiles for programmatic agent execution. Controls which tools an agent can use based on execution mode and project type.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | sandbox-profiles |
| description | Defines tool permission profiles for programmatic agent execution. Controls which tools an agent can use based on execution mode and project type. |
| version | 1 |
| metadata | {"category":"security","author":"auto-workflow","evolution-stats":{"total-experiments":870}} |
| level | molecule |
| atoms | ["tool-prompts","agent-prompts"] |
Different execution contexts require different tool permissions:
{
"allowed": ["Read", "Grep", "Glob", "Edit", "ApplyPatch", "Code_Map", "Code_Inspect", "Code_Replace", "Code_Usages", "Diagnostics", "describe_symbol", "get_symbol_source", "find_buffers_and_recent"],
"readonly": ["Read", "Grep", "Glob", "Code_Map", "Code_Inspect", "Code_Usages", "Diagnostics", "describe_symbol", "get_symbol_source", "find_buffers_and_recent"],
"confirming": ["Edit", "ApplyPatch", "Code_Replace"],
"timeout": 15,
"max_calls": 25,
"result_limit": 4000
}
{
"allowed": ["Read", "Grep", "Glob", "Edit", "ApplyPatch", "Code_Map", "WebFetch", "WebSearch", "Bash", "Diagnostics"],
"readonly": ["Read", "Grep", "Glob", "Code_Map", "WebFetch", "WebSearch", "Diagnostics"],
"confirming": ["Edit", "ApplyPatch", "Bash"],
"timeout": 30,
"max_calls": 50,
"result_limit": 8000
}
{
"allowed": ["Read", "Grep", "Glob", "Edit", "Bash", "Diagnostics", "Programmatic"],
"readonly": ["Read", "Grep", "Glob", "Diagnostics"],
"confirming": ["Edit", "Bash", "Programmatic"],
"timeout": 60,
"max_calls": 100,
"result_limit": 16000
}
{
"allowed": ["Read", "Grep", "Glob", "Code_Map", "Code_Inspect", "Code_Usages", "Diagnostics", "describe_symbol", "get_symbol_source"],
"readonly": ["Read", "Grep", "Glob", "Code_Map", "Code_Inspect", "Code_Usages", "Diagnostics", "describe_symbol", "get_symbol_source"],
"confirming": [],
"timeout": 15,
"max_calls": 25,
"result_limit": 4000
}
Load profile in Emacs Lisp:
(let ((skill (gptel-auto-workflow--load-skill "sandbox-profiles")))
(plist-get skill :profiles))
scripts/validate_profile.py - Validate profile JSON against schemascripts/generate_profile.py - Generate profile from project analysisBased on analysis of 0 experiments.
| Tool | Level | Success Rate | Experiments |
|---|
Transforms research paper analysis from extraction to narrative storytelling. Uses 7-beat narrative spine (protagonist/dilemma/old-path/turning-point/solution/ending/core) to make papers understandable to non-experts. Includes speed-read card, PhD advisor review, and real-world testing. Use when researcher encounters a research paper and needs to extract deep understanding, not just surface facts. Triggers on "paper", "research paper", "analyze paper", "tell me about this paper", "讲论文", "读论文".
Workflow chain: researcher → paper-storytelling. When researcher encounters a research paper, automatically invoke paper-storytelling to transform extraction into narrative understanding. Use when user says "research paper", "analyze this paper", "tell me about this paper", or when researcher detects arxiv/PDF links.
Prompt template for external research specialist subagent. Auto-evolves based on experiment outcomes.
Inspect and operate OV5 (Ouroboros V5) through the live Emacs daemon. Use when checking auto-workflow status, starting guarded runs, reviewing experiment results, or querying researcher and evolution state.
Clojure REPL client (nREPL-based, Babashka). Use for evaluating Clojure code, loading Clojure files, fixing unbalanced brackets, and interactive nREPL work. Not the Elisp daemon-repl.
Daemon REPL for Elisp — evaluate Elisp code in a running Emacs daemon via emacsclient, validate brackets before save, auto-evaluate .el files on change. Use when you need to run Elisp from outside Emacs, check daemon status, or validate Elisp syntax.