Maestro Odyssey

What it does

When your agent uses it

• Tasks that involve Mobile testing and debugging

Example prompts

• “/maestro-odyssey”

Requirements

• Pre-approved tools (allowed-tools): Bash, Edit, Glob, Grep, Read, Write, followup_task, interrupt_agent, list_agents, request_user_input, send_message, spawn_agent, spawn_agents_on_csv, update_plan, wait_agent

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

1. 1Evidence append-only — never delete or overwrite evidence.ndjson entries.
2. 2Phase goal tracking — mark each goal done/failed before transition; no silent skips.
3. 3Generalize is mandatory — GENERALIZE and DISCOVER execute unless skip_generalize == true. Prior-phase convergence, "no findings / all…
4. 4Zero-residual (improve/review/ui) — every finding MUST have a concrete action (fix / issue / decision). "Report and shelve" and blanket…
5. 5Read-only (security, defensive) — NEVER modify source code, configuration, or dependencies. Security and defensive audits produce reports…
6. 6Acceptance criteria are sacred (planex) — no "close enough", no manual override without explicit escalation.
7. 7Browser is truth (ui) — verify in real rendering, not just code review. Diverge before converge.
8. 8Goal 跟宿主原生 /goal 走 — session.json 是权威进度。不要为了刷新外观去重建 Goal；用户 clear 之后外观必须保持消失。

What it can do on your machine

Read from SKILL.md and the folder at commit f888cec. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Edit
  • Glob
  • Grep
  • Read
  • Write
  • followup_task
  • interrupt_agent
  • list_agents
  • request_user_input

  …and 5 more on the same allowed-tools line.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are json).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Maestro Odyssey loads about 4.1k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 1,691 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~77

When it runs · the whole SKILL.md, loaded when a task matches

~4.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Edit, Glob, Grep, Read, Write, followup_task, interrupt_agent, list_agents, request_user_input

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,691 words (~4,130 tokens).

name

maestro-odyssey

allowed-tools

Bash, Edit, Glob, Grep, Read, Write, followup_task, interrupt_agent, list_agents, request_user_input, send_message, spawn_agent, spawn_agents_on_csv, update_plan, wait_agent

disable-model-invocation

true

argument-hint

<intent> --mode debug|improve|planex|review|security|defensive|ui [-y] [-c]

session-mode

run

contract.discovery

self-described

version

0.5.91

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .codex/skills/maestro-odyssey of catlog22/maestro-flow.

Open the folder on GitHubat commit f888cec