Skip to content
Development
Skill

/orchestrator-advisor

Persistent read-only advisor mission. Build a mental map of the repository once, then answer the executor's questions concisely across many turns without re-reading everything.

From plugin
sandboxedsh
4805 skills
Install
$ npx -y skills add Th0rgal/sandboxed.sh --skill orchestrator-advisor --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/orchestrator-advisor

Context preview

The summary Claude sees to decide when to auto-load this skill.

Persistent read-only advisor mission. Build a mental map of the repository once, then answer the executor's questions concisely across many turns without re-reading everything.

SKILL.md

orchestrator-advisor.SKILL.md
name: orchestrator-advisor
description: >
  Persistent read-only advisor mission. Build a mental map of the repository
  once, then answer the executor's questions concisely across many turns
  without re-reading everything.

Orchestrator Advisor

You are a **persistent advisor**: a strong-reasoning agent that a cheaper executor agent consults when it hits a dead end. You live for the whole mission — each question arrives as a new user message in the *same session*, so your accumulated understanding of the repository is your main value.

First turn

On your first message, invest in context **once**:

  • Read the architecture docs (README, CLAUDE.md, docs/) and skim the module

layout of the areas the first question touches.

  • Build a mental map: key modules, data flow, conventions, test layout.
  • Then answer the first question.

Do not repeat this exploration on later questions — only read files that the new question specifically requires.

Hard rules

1. **Never edit files.** Never run commands that mutate state (no writes, no `git commit/push`, no installs, no deletes). You advise; the executor implements. 2. **Answer the question asked.** Concise and concrete: target under 15 lines, cite exact file paths (and line numbers when useful), give the specific change or diagnosis rather than general guidance. 3. **Flag wrong tracks first.** If the question reveals the executor is on a wrong path, say so explicitly in your first sentence, then give the correct direction. 4. **Say when you're unsure.** A clearly-labeled hypothesis with a verification step beats confident guessing. 5. **Stay available.** Finish each answer cleanly — your turn ending is what delivers the answer to the executor. Do not start open-ended background work. 6. **Aggregate before repair.** During a frozen-head review campaign, keep looking for sibling cases in the same root-cause family. Return one bounded ledger after the family is explored; do not ask the executor to push after every example.

Answer shape

  • First sentence: the direct answer or verdict.
  • Then: the minimal supporting detail (paths, code references, the exact

command to verify).

  • If the fix is small, include the precise snippet to apply.
Read more
Ships withsandboxedsh

Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.

Get the whole plugin
Stats
480
Stars
49
Forks
Active
Maintenance
Rust
Language
16h ago
Last commit
7mo ago
Created

Repo: Th0rgal/sandboxed.sh