Skip to content

hashgraph-online/awesome-codex-plugins / plugins/beastlabai/multi-llm-plugin/skills/multi-llm

multi-llm

Flagged

Orchestrate plan reviews, task generation, implementation and code reviews across several LLM CLIs in parallel, or ask every model one free-text question about a plan. Use when the user says: review my plan, multi-llm, run a code review, generate tasks from a plan, implement this plan, ask the models about my plan.

FileKindSize
SKILL.mdskill md4.0 KB
apply_code_fixes_orchestrator.pyscript56.6 KB
apply_commit_fixes_orchestrator.pyscript2.3 KB
apply_suggestions_orchestrator.pyscript4.5 KB
apply_task_suggestions_orchestrator.pyscript19.1 KB
ask_orchestrator.pyscript162.5 KB
assets/icons/Anthropic.svgother584 B
assets/icons/Codex.svgother1.3 KB
assets/icons/Copilot.svgother1.5 KB
assets/icons/Cursor.svgother793 B
assets/icons/GoogleGemini.svgother623 B
assets/icons/Goose.svgother3.2 KB
assets/icons/Kilocode.svgother531 B
assets/icons/MiniMax.pngbinary1.5 KB
assets/icons/Mistral.svgother717 B
assets/icons/MoonshotAI.svgother957 B
assets/icons/Nvidia.svgother2.4 KB
assets/icons/OhMyPi.svgother434 B
assets/icons/OpenAI.svgother1.7 KB
assets/icons/Opencode.svgother325 B
assets/icons/Pi.svgother440 B
assets/icons/Qwen.svgother1.7 KB
assets/icons/Zhipu.pngbinary442 B
assets/icons/xAI.svgother343 B
assets/omp/overlay.ymlconfig2.4 KB
check_workflow_prerequisites.pyscript74.5 KB
code_review_orchestrator.pyscript324.0 KB
display_decisions.pyscript9.8 KB
finalize_tracking.pyscript1.3 KB
full_workflow_orchestrator.pyscript58.8 KB
generate_tasks_orchestrator.pyscript44.2 KB
hosts/capabilities.yamlconfig49.9 KB
hosts/codex/plugin-skill.md.tmplother2.8 KB
hosts/codex/shim.md.tmplother7.3 KB
hosts/opencode/plugin-command.md.tmplother2.2 KB
hosts/opencode/shim.md.tmplother6.8 KB
hosts/render_capabilities.pyscript48.4 KB
hosts/snippets/poll-loop.mdmarkdown4.4 KB
hosts/snippets/uv-preflight.mdmarkdown2.2 KB
hosts/uv-missing.txtmarkdown1.5 KB
implement_orchestrator.pyscript156.0 KB
improve_code_orchestrator.pyscript1.6 KB
improve_commits_orchestrator.pyscript2.5 KB
improve_plan_orchestrator.pyscript1.6 KB
init_config.pyscript57.6 KB
instructions/apply-code-fixes.mdmarkdown52.0 KB
instructions/apply-commit-fixes.mdmarkdown10.3 KB
instructions/apply-suggestions.mdmarkdown48.2 KB
instructions/apply-task-suggestions.mdmarkdown53.9 KB
instructions/ask.mdmarkdown27.6 KB
instructions/full-workflow.mdmarkdown24.6 KB
instructions/generate-tasks.mdmarkdown18.1 KB
instructions/implement.mdmarkdown54.0 KB
instructions/improve-code.mdmarkdown25.0 KB
instructions/improve-commits.mdmarkdown24.8 KB
instructions/improve-plan.mdmarkdown26.2 KB
instructions/init-config.mdmarkdown6.6 KB
instructions/review-code.mdmarkdown43.5 KB
instructions/review-commits.mdmarkdown11.4 KB
instructions/review-plan.mdmarkdown38.4 KB
instructions/review-tasks.mdmarkdown37.8 KB
modes.pyscript58.8 KB
multi_llm.pyscript101.1 KB
prompts/ask.txtmarkdown948 B
prompts/code_review.txtmarkdown4.5 KB
prompts/commit_review.txtmarkdown6.2 KB
prompts/consolidate_suggestions.txtmarkdown3.1 KB
prompts/implementation_task.txtmarkdown1.4 KB
prompts/plan_review.txtmarkdown8.0 KB
prompts/task_review.txtmarkdown8.3 KB
providers.yamlconfig19.6 KB
pyproject.tomlmanifest6.8 KB
references/apply-write-executor.mdmarkdown3.0 KB
references/consolidation.mdmarkdown5.6 KB
references/host-capabilities.mdmarkdown13.5 KB
references/human-decision-batch.mdmarkdown17.2 KB
references/implement-prerequisites.mdmarkdown6.0 KB
references/implement-write-executor.mdmarkdown4.9 KB
references/interrupted-run-recovery.mdmarkdown3.1 KB
references/own-check.mdmarkdown4.3 KB
references/resume-detection.mdmarkdown8.5 KB
references/revalidation.mdmarkdown6.9 KB
references/review-code-apply-fixes.mdmarkdown4.3 KB
references/salvage-handling.mdmarkdown12.5 KB
references/summary-format.mdmarkdown10.0 KB
references/uv-check.mdmarkdown5.7 KB
references/wave-batching.mdmarkdown5.2 KB
review_commits_orchestrator.pyscript2.3 KB
review_plan_orchestrator.pyexecutablescript22.3 KB
review_tasks_orchestrator.pyscript10.7 KB
schemas/cascade_record.schema.jsonconfig6.6 KB
schemas/code_review_issues.schema.jsonconfig2.0 KB
schemas/consolidated.schema.jsonconfig6.8 KB
schemas/consolidation_batch.schema.jsonconfig3.7 KB
schemas/generated_tasks.schema.jsonconfig3.1 KB
schemas/host_capabilities.schema.jsonconfig38.3 KB
schemas/human_decision_verdicts.schema.jsonconfig2.6 KB
schemas/result_line.schema.jsonconfig10.1 KB
schemas/review_suggestions.schema.jsonconfig2.4 KB
schemas/state_file.schema.jsonconfig21.5 KB
schemas/status_file.schema.jsonconfig24.9 KB
schemas/status_json.schema.jsonconfig10.8 KB
schemas/subagent_tasks.schema.jsonconfig20.5 KB
schemas/task_decomposition.schema.jsonconfig1.2 KB
schemas/write_batch_result.schema.jsonconfig8.8 KB
templates/config/providers.override.yamlconfig17.2 KB
templates/consolidated_report_template.htmlother44.1 KB
templates/pr_report_template.htmlother181.2 KB
templates/report_template.htmlother67.5 KB
templates/shared/report_core.cssother4.1 KB
templates/shared/report_core.jsscript25.5 KB
update_plan_tasks.pyscript20.9 KB
utils/__init__.pyscript284 B
utils/advisory.pyscript4.8 KB
utils/apply_orchestrator_base.pyscript220.6 KB
utils/apply_output_helpers.pyscript10.9 KB
utils/apply_path_helpers.pyscript683 B
utils/apply_report.pyscript51.2 KB
utils/apply_selection_helpers.pyscript6.8 KB
utils/apply_suggestion_phase.pyscript11.7 KB
utils/atomic_io.pyscript12.9 KB
utils/attempt_classifier.pyscript31.4 KB
utils/backup.pyscript2.0 KB
utils/batch_done.pyscript79.2 KB
utils/batch_ledger.pyscript27.4 KB
utils/batch_prompt.pyscript29.3 KB
utils/batch_prompt_builder.pyscript12.2 KB
utils/batch_reply.pyscript32.9 KB
utils/cascade_archive.pyscript50.6 KB
utils/cascade_ledger.pyscript39.3 KB
utils/cascade_provenance.pyscript22.0 KB
utils/check_records.pyscript59.3 KB
utils/check_reply.pyscript9.5 KB
utils/check_tree.pyscript1.2 KB
utils/cli_common.pyscript91.2 KB
utils/cli_version_cache.pyscript14.0 KB
utils/clock.pyscript3.5 KB
utils/code_fix_batcher.pyscript30.6 KB
utils/codex_trust.pyscript12.9 KB
utils/commit_apply.pyscript73.3 KB
utils/commit_attribution.pyscript21.2 KB
utils/commit_brief.pyscript32.2 KB
utils/commit_front_door.pyscript81.6 KB
utils/commit_paths.pyscript18.0 KB
utils/commit_range.pyscript61.2 KB
utils/commit_report.pyscript19.9 KB
utils/commit_review.pyscript413 B
utils/commit_spelling.pyscript7.9 KB
utils/commit_write_guard.pyscript9.9 KB
utils/concurrency.pyscript11.6 KB
utils/consolidation.pyscript87.3 KB
utils/detach.pyscript186.8 KB
utils/dispatch_spawn.pyscript56.3 KB
utils/doctor.pyscript76.7 KB
utils/env_vars.pyscript20.5 KB
utils/failure_capture.pyscript10.1 KB
utils/file_discovery.pyscript11.0 KB
utils/filtering.pyscript19.9 KB
utils/git_diff.pyscript23.6 KB
utils/git_utils.pyscript86.6 KB
utils/held_folder.pyscript21.3 KB
utils/host_capabilities.pyscript48.0 KB
utils/host_install.pyscript77.6 KB
utils/host_paths.pyscript12.0 KB
utils/host_routes/__init__.pyscript5.7 KB
utils/host_routes/codex.pyscript18.3 KB
utils/host_routes/npm.pyscript12.2 KB
utils/host_shim.pyscript14.7 KB
utils/html_report_generator.pyscript118.9 KB
utils/human_decisions.pyscript38.3 KB
utils/human_task_plan.pyscript30.2 KB
utils/importance.pyscript6.2 KB
utils/improve_cascade.pyscript63.7 KB
utils/improve_cascade_next.pyscript22.2 KB
utils/improve_steps.pyscript32.4 KB
utils/improve_workflow.pyscript114.4 KB
utils/interactive.pyscript31.6 KB
utils/json_extractor.pyscript61.5 KB
utils/judge_vocab.pyscript5.3 KB
utils/known_checks.pyscript37.5 KB
utils/landlock_dispatch.pyscript103.8 KB
utils/landlock_exec.pyscript21.4 KB
utils/launch_limiter.pyscript13.5 KB
utils/llm_client.pyscript126.9 KB
utils/manual_tasks.pyscript14.9 KB
utils/metrics.pyscript68.1 KB
utils/next_phase.pyscript96.1 KB
utils/next_phase_words.pyscript6.4 KB
utils/output_handler.pyscript23.2 KB
utils/phase_walk.pyscript6.4 KB
utils/plan_updater.pyscript17.9 KB
utils/positionals.pyscript5.8 KB
utils/prior_changes.pyscript28.7 KB
utils/probe_state.pyscript17.9 KB
utils/process_capture.pyscript37.6 KB
utils/process_control.pyscript228.7 KB
utils/process_state.pyscript6.6 KB
utils/progress_tracker.pyscript92.2 KB
utils/prompt_channels.pyscript34.1 KB
utils/prompt_files.pyscript24.5 KB

instructions/init-config.md

View on GitHub
# Init Config Mode Instructions

Scaffolds a **per-project provider config override** at
`<git-root>/.multi-llm/providers.yaml`. This is the opt-in way to give a single
repository its own provider/model defaults without editing the installed plugin.

Like `--status` and `--generate-tasks`, `--init` has **no Python orchestrator** —
it is handled entirely by this instruction file routing to the standalone
`init_config.py` script.

`--init` is **fully automatic and zero-prompt**. It scans `PATH` for the
supported provider CLIs (claude-code→`claude`, cursor-agent→`cursor-agent`,
gemini→`gemini`, grok→`grok`, fx→`fx`, opencode→`opencode`, codex→`codex`,
kilocode→`kilocode`, kimi→`kimi`, qwen-code→`qwen`, copilot→`copilot`,
vibe→`vibe`,
cline→`cline`, goose→`goose`,
aider→`aider`, agy→`agy`,
pi→`pi`, muse→`muse`, omp→`omp`),
copies an **inert template** to the target path, then **uncomments** the lines
that belong to the detected providers — their full `providers:` sub-blocks
(command, timeouts, concurrency, `models:` list), the `defaults.models` /
`defaults.quick_models` candidate entries whose provider is detected, and
`default_provider`. Undetected providers stay commented. There are **no prompts**
and **no model-listing subprocess calls**, so it behaves identically inside
any host, a plain terminal, or CI.

## Usage

```bash
/multi-llm:multi-llm --init [--dir PATH] [--force] [--gitignore] [--template-only]
```

`--init` does **not** take a plan path. Optional arguments:

| Arg | Meaning |
| --- | --- |
| `--dir PATH` | Target directory (defaults to the git root; falls back to CWD outside a repo, with a printed notice). |
| `--force` | Overwrite an existing `.multi-llm/providers.yaml` (the script refuses by default). Before overwriting, the previous file is automatically backed up alongside as `providers.yaml.bak.<timestamp>` and the script prints the backup path (skipped when the new content is identical). |
| `--gitignore` | Also append `.multi-llm/` to the repo's `.gitignore` (idempotent) so the override stays developer-local and untracked. Default: leave it trackable (commit it for a team-wide standard). |
| `--template-only` | Skip detection entirely; write the pristine inert template verbatim (every provider left commented) for hand-editing. |

## Process (the driving agent executes these steps)

**Prerequisite — `uv` (D6 row 1).** The scaffolder runs through `uv run`. If it
is absent the resolution is fail-closed: print `hosts/uv-missing.txt` verbatim
and **stop with exit 3** — never install it, never ask, never fall back to bare
`python`. `--init` therefore stays zero-prompt on every path: a missing runtime
manager is a fail-closed gate, not a question.

1. **Map flags.** Pass through any `--dir`, `--force`, `--gitignore` the user
   supplied. Use `--template-only` only when the user explicitly wants the
   untouched stub ("just write the template / give me the stub to edit / don't
   detect anything"). A bare `--init` runs auto-detection — no routing question
   is needed because nothing prompts.

2. **Run the scaffolder.** The command below arrives with the skill directory
   already substituted, so run it as written:

   ```bash
   uv run {UV_RUN_FLAGS} --project "{SKILL_DIR}" -- python "{SKILL_DIR}/multi_llm.py" init [--dir PATH] [--force] [--gitignore] [--template-only]
   ```

3. **Report the result.** Print the path the script wrote and its git-tracking
   state (the script prints both), plus any notice it emitted (see below). If it
   refused to overwrite an existing file, relay that and offer `--force`. If it
   backed up a previous config, relay the backup path prominently and remind the
   user to port any custom settings from the backup into the new file. Use the
   report shape in `references/summary-format.md`, omitting the rows this mode has
   nothing to fill (it has no plan and no state file).

## What gets written

- **`default_provider`** is set to the **first detected provider in base
  declaration order** (claude-code, cursor-agent, gemini, grok, fx, opencode,
  codex, kilocode, cline, goose, aider, agy, muse, pi, kimi, qwen-code, copilot,
  vibe, omp). So with both claude-code and cursor-agent installed it becomes
  `claude-code`. When **nothing** is detected it is left commented and inherits
  the base default.
- **Nothing detected → no error.** With no provider CLIs on `PATH` the script
  writes the inert template (which inherits the built-in defaults) and exits 0
  with an install-guidance notice. It never fails.
- **Off-panel-only detection.** If the only detected providers are ones absent
  from the base default model panel (gemini / opencode), the script injects their
  first catalog model into `defaults.models` / `quick_models` so the file is
  runnable, and prints a notice saying so.
- **Re-running.** Re-run `--init --force` after installing a new CLI (to pick it
  up) or after a plugin update (to refresh the pinned provider metadata and prune
  providers the new base dropped) — see the DRIFT note below. Overwriting is
  safe: the previous file is backed up as `providers.yaml.bak.<timestamp>` first,
  so hand-tuned settings can always be recovered or ported over.

## Notes

- The override is **optional and auto-discovered** from the git root at run time;
  absent → built-in defaults, identical to today. Editing the generated file
  changes which providers/models a run selects.
- **Lists replace, they do not append.** A blank/omitted key inherits the base;
  an explicit empty list `[]` is the only way to deliberately empty a list.
- The generated file now carries a full **`providers:` block** for each detected
  provider. That block **deep-merges over the base**, identical to the
  `MULTI_LLM_PROVIDERS_CONFIG` env layer (lists replace, nested dicts deep-merge).
  Invariants that still hold:
  - `command:` is **documentation-only and is NEVER executed** — provider
    binaries are hardcoded in `utils/providers/`, so a `command:` value in any
    layer can never make the tool run a different program.
  - A merged provider name with **no hardcoded adapter** (e.g. one a newer plugin
    removed or renamed) is ignored at runtime — it lists no models and can never
    be selected.
  - **DRIFT:** a copied full block pins base's scalar/model values **at init
    time**; re-run `--init --force` after a plugin update to refresh the pinned
    metadata and prune dropped providers.
- One override per repository (discovery anchors at the git root). For per-run or
  out-of-tree overrides use `MULTI_LLM_PROVIDERS_CONFIG=/path.yaml`.

See [the configuration documentation](https://github.com/beastlabai/multi-llm-plugin/blob/master/docs/configuration.md) for the full semantics.
receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementationStars: 322kUpdated Claude CodeCodexVerifiedInstall
requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirementsStars: 322kUpdated Claude CodeCodexVerifiedInstall
using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallbackStars: 322kUpdated Claude CodeCodexVerifiedInstall
verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions alwaysStars: 322kUpdated Claude CodeCodexVerifiedInstall