foxrun-ai/foxrun / skills/orchestrate
orchestrate
FlaggedThe one menu for handing work between Claude, Codex, and Hermes. Say where you are, what you want (quick hit, second opinion, review, fix, grill, live conversation, steer, parallel workers), and an optional session id; get one route back. Use whenever an agent needs another runtime — before Codex Desktop native tools, herdr, claude -p, codex exec, or hermes -z. Replaces fleet, foxy, dex, claude-delegate, and the bundled Hermes codex / claude-code skills.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 445 B |
| SKILL.md | skill md | 15.5 KB |
| bin/README.md | markdown | 308 B |
| bin/brief-checkexecutable | script | 4.8 KB |
| bin/orchestrateexecutable | script | 67.0 KB |
| replays/README.md | markdown | 528 B |
| replays/anchored-brief.json | config | 925 B |
| replays/missing-decisions.json | config | 386 B |
| replays/read-hosted-without-herdr.json | config | 250 B |
| replays/route-codex-to-claude.json | config | 410 B |
| replays/t289-real-panel.json | config | 1.9 KB |
| tests/README.md | markdown | 668 B |
| tests/__init__.py | script | 0 B |
| tests/acceptance.md | markdown | 2.7 KB |
| tests/resolver_baseline.json | config | 173.1 KB |
| tests/support.py | script | 1.2 KB |
| tests/test_brief_check.py | script | 7.9 KB |
| tests/test_codex_thread.py | script | 5.8 KB |
| tests/test_doctor.py | script | 25.6 KB |
| tests/test_resolver.py | script | 36.6 KB |
replays/t289-real-panel.json
View on GitHub{
"name": "t289-real-panel",
"run": "dry-run",
"input": "bin/brief-check {tmp}/brief.md",
"setup": {
"files": {
"brief.md": "# T289 Level 3 panel, pass 2: every property of every table (independent)\n\nYou are one of three independent reviewers (Fable 5.1, Astra, the Adviser). Read ~/.local/state/foxrun/runs/2026-09-29-level3/common.md first. Do not read the other reviewers' folders under 2026-09-29-level3/ until the cross-review.\n\nJob: settle Level 3 (g-db-level3-checks) for every table in target-v2.jsonl after the 9.29 renames: for each column, its name, our type (from the model key), required or not, its value list if it has one, and its link if it points at another table.\n\nStatus values: list the allowed statuses for work_tasks, work_projects, work_programs, work_runs, work_bugs, work_incidents, and every other table with a status, from current rows plus decisions (T289 item 9).\n\n## The design as it stands (the rows win)\n\n- Target: `~/.local/state/foxrun/runs/2026-09-29-db-refine/target-v2.jsonl` (one data.db, table-name prefix = module; 96 rows: tables and views), `leaving-v2.json` (what stays with a tool or drops), `changes.md`, `object-types.md`, `collections.md`, `questions.md` in the same folder.\n\nRead every decision before you judge anything. Check `replaces` before calling anything settled:\n\n```\nsqlite3 -readonly ~/archive/agent-os/agent-os.sqlite \"select id,status,replaces,statement from decisions where status in ('ruled','soft') and decided_on >= '2026-09-17' order by decided_on, rowid\"\n```\n\n## Person's logged words\nPerson 9.29: Nothing live changes: every output is a proposal file in your run folder.\n\n## How to write\n\nPlain English, short sentences, one idea each. Use literal names: table, column, file.\n"
}
},
"expect": {
"exit": 1,
"output_contains": ["missing owning-lead sources section"]
}
}
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: 472k | 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 |