Multi-LLM icon

Multi-LLM

beastlabai/multi-llm · v0.1.6 · Development & Workflow

by beastlabaiScan grade: GoodAwesome AI Plugins

Parallel plan, code, and commit reviews across 19 coding CLIs, with validated findings, task generation, implementation, and automated revision.

InstallSourceClaim this plugin
Follow0
Trust Score71Security scan81Components2
Protect this install with HOL Guard

Guard checks the skills and MCP servers a plugin adds on your machine and asks you before a risky action runs. The scores above are free, and no plan changes them.

Is Multi-LLM a fit?

From the plugin's manifest and HOL's scan. Anything the plugin does not declare is shown as not declared.

Works with

  • Codex
  • 1 skill
  • 1 MCP server

Before you install

Sign-in
Asks you to sign in when you install it
Declared access
Interactive, Read, Write
License
MIT

Check before relying on it

  • Some security checks did not finish: Cisco skill scan and Cisco MCP scan. See the evidence
  • 2 medium findings from the scan. See the evidence
  • The publisher has not verified ownership on HOL.

What is Multi-LLM?

Multi-LLM is a published development & workflow plugin for AI coding agents in the Codex ecosystem, developed by beastlabai and distributed through the HOL AI plugin registry. Parallel plan, code, and commit reviews across 19 coding CLIs, with validated findings, task generation, implementation, and automated revision.

Canonical slug
beastlabai/multi-llm
Version
v0.1.6 · updated Nov 8, 2026

Registry snapshot

Owner verification
Not verified
Marketplace source
.claude-plugin/marketplace.json
Scanner
HOL plugin scanner
Security result
Needs review
Digest verified
Yes
1 bundled skillRead, copy or download each SKILL.mdOpen skills

Trust and security

Trust & reputation

71

HOL Trust Score

Per-metric points (0–100 each) combined via a weighted average into the overall score.

Installability
100/100
Maintenance
10/100
MCP server setup
100/100
Plugin Security
81/100
Provenance
70/100
Publisher Quality
75/100

Provenance

Plugin root
packaging/codex/multi-llm
Source repo
https://github.com/beastlabai/multi-llm-plugin
Source commit
acfac7eb737c…
Publisher verified
No
Owner verified
Not owner verified
Agent Plugins 1.0
Not detected

Continuous scanner CI not detected

This plugin remains listed. Its overall trust score is reduced by 10% because security checks are not maintained in the source repository's CI.

Optional: maintain the scanner in the source repository's CI to receive the full trust score. Listing does not require that change.

README badge not detected

Plugin owners can add the HOL badge to the repository README from Guard Plugins. Distribution, not security evidence. It adds a 2% engagement adjustment to the overall trust score and never changes the security result.

Security posture

See how the Trust Score is computed
Needs review
Security result
81
Security score
0
High findings
Provider
codex-plugin-scanner
Grade
B · Good
Version
3.24.2
cisco-skill-scanner: failedcisco-mcp-scanner: unavailable

Manifest Validation

28/31

9 checks

Security

14/20

9 checks

Operational Security

N/A

5 checks · not applicable

Best Practices

6/12

5 checks

Marketplace

N/A

3 checks · not applicable

Skill Security

5/5

4 checks

Code Quality

10/10

2 checks

Published advisories

None matched in GitHub security advisories, checked . This covers published advisories only, not problems nobody has reported.

GitHub security advisories are those the source repository has published.

Findings

mediumsecurityRISKY_APPROVAL_DEFAULT

skills/multi-llm/providers.yaml contains a dangerous approval or sandbox default.

Avoid shipping configurations that default to bypassed approvals or unrestricted sandboxes.

mediumsecurityRISKY_APPROVAL_DEFAULT

skills/multi-llm/hosts/capabilities.yaml contains a dangerous approval or sandbox default.

Avoid shipping configurations that default to bypassed approvals or unrestricted sandboxes.

lowsecuritySECURITY_MD_MISSING

Plugins should publish a SECURITY.md file for responsible disclosure and support guidance.

Add a SECURITY.md file with reporting guidance and supported versions.

lowbest-practicesREADME_MISSING

Plugins should document installation, usage, and security expectations in README.md.

Add a README.md that explains setup, usage, and operational constraints.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_WEBSITEURL

The interface field "websiteURL" must use HTTPS or point to a safe in-repo asset.

Update "websiteURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_PRIVACYPOLICYURL

The interface field "privacyPolicyURL" must use HTTPS or point to a safe in-repo asset.

Update "privacyPolicyURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_TERMSOFSERVICEURL

The interface field "termsOfServiceURL" must use HTTPS or point to a safe in-repo asset.

Update "termsOfServiceURL" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_LOGO

The interface field "logo" must use HTTPS or point to a safe in-repo asset.

Update "logo" to use HTTPS or an existing relative asset path.

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_SCREENSHOTS

The interface field "screenshots" must use HTTPS or point to a safe in-repo asset.

Update "screenshots" to use HTTPS or an existing relative asset path.

infobest-practicesCODEXIGNORE_MISSING

A .codexignore file helps prevent accidental inclusion of local artifacts and secrets.

Add a .codexignore file with generated assets, local state, and secret paths.

Install guidance

Install in Codex

Install through the Codex CLI plugin marketplace.

Codex plugin docs

Optional: install HOL Guard for Codex first, so it can check this plugin's tools on your machine before Codex uses them.

  1. 1

    Register the marketplace

    Run in any terminal. Codex reads the marketplace entry from .agents/plugins/marketplace.json (or the legacy .claude-plugin path) in the repository. If the repository ships none, add the generated entry from the Advanced section below first.

    shell
  2. 2

    Install the plugin

    Installs the multi-llm entry from the beastlabai marketplace. You can also install it from the Plugins browser inside Codex.

    shell
  3. 3

    Check the marketplace is registered

    This confirms the marketplace source only. Confirm the plugin itself is enabled in the Plugins browser before relying on it.

    shell

To remove it later, run codex plugin remove multi-llm@beastlabai.

Did setup work in Codex?

No setup reports for Codex yet. Self-reported by signed-in visitors. Copying a command is not counted, and most installs are never reported.

Attested installs: Fewer than 10 attested installs of this plugin in week 2026-W45, so no number is shown. Counted from opt-in HOL Guard install reports, once per machine and runtime, and never mixed with the answers above. How install reports work.

Loading reviews

Plugin manifest

{
  "name": "multi-llm",
  "version": "0.1.6",
  "description": "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.",
  "author": {
    "name": "beastlabai",
    "url": "https://github.com/beastlabai"
  },
  "homepage": "https://github.com/beastlabai/multi-llm-plugin",
  "repository": "https://github.com/beastlabai/multi-llm-plugin",
  "license": "MIT",
  "keywords": [
    "code-review",
    "multi-llm",
    "planning"
  ],
  "skills": "./",
  "mcpServers": "./.registry/mcp.json",
  "interface": {
    "displayName": "Multi-LLM",
    "developerName": "beastlabai",
    "composerIcon": "./assets/icon.svg",
    "shortDescription": "Review plans and code with several LLM CLIs in parallel.",
    "longDescription": "Runs the multi-llm workflow inside a Codex session: plan reviews, task generation, implementation and code reviews fanned out across several coding CLIs in parallel, or one free-text question put to every configured model. A bundled stdio tool, multi_llm, composes the dispatcher's flags, supervises the run to a result and returns one JSON answer. Needs python3 and uv on PATH.",
    "category": "Developer Tools",
    "capabilities": [
      "Interactive",
      "Read",
      "Write"
    ],
    "defaultPrompt": [
      "Review my plan with multiple models."
    ]
  },
  "holManifestOrigin": "repository",
  "registryIndexVersion": 9
}

Marketplace source

Repo URL
https://github.com/beastlabai/multi-llm-plugin
Marketplace path
.claude-plugin/marketplace.json
Source path
plugins/beastlabai/multi-llm-plugin
Install policy
AVAILABLE

Skills

1 SKILL.md file ship with this plugin. Preview, copy, or download each one, then install them with the Skills CLI.

Share
skills-cli

  • multi-llm

    skills/multi-llm/SKILL.md

    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.

    Raw SKILL.md

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

File inventory

.codex-plugin/plugin.json

plugin-manifest

1,300 bytes

4a054e2c7e9e7ed9…

.mcp.json

file

853 bytes

93298d27402ea2c0…

.registry/mcp.json

mcp-config

600 bytes

0f9c500c6626eb44…

assets/icon.svg

asset

1,945 bytes

b5e64f2f46b5cd70…

LICENSE

file

1,424 bytes

961cea61b879b291…

skills/multi-llm/apply_code_fixes_orchestrator.py

skill

59,929 bytes

f89c6b42f4c44b50…

skills/multi-llm/apply_commit_fixes_orchestrator.py

skill

2,027 bytes

3a3f0dbe42ef44f5…

skills/multi-llm/apply_suggestions_orchestrator.py

skill

15,042 bytes

c7c970a9fe4e34d1…

skills/multi-llm/apply_task_suggestions_orchestrator.py

skill

29,702 bytes

daeb81f4ca7de400…

skills/multi-llm/ask_orchestrator.py

skill

119,166 bytes

f52d84982d717da9…

skills/multi-llm/assets/icons/Anthropic.svg

skill

584 bytes

a7dc6e7705f702a1…

skills/multi-llm/assets/icons/Codex.svg

skill

1,360 bytes

dde8b3563a40d55a…

skills/multi-llm/assets/icons/Copilot.svg

skill

1,546 bytes

b5bfc7d50d1ec20a…

skills/multi-llm/assets/icons/Cursor.svg

skill

793 bytes

c483c02f78eb2619…

skills/multi-llm/assets/icons/GoogleGemini.svg

skill

623 bytes

968da8483e45257b…

skills/multi-llm/assets/icons/Goose.svg

skill

3,318 bytes

b4a9ab0aa1da3787…

skills/multi-llm/assets/icons/Kilocode.svg

skill

531 bytes

02386f2469272dcd…

skills/multi-llm/assets/icons/Mistral.svg

skill

717 bytes

66ceaf186f2075da…

skills/multi-llm/assets/icons/MoonshotAI.svg

skill

957 bytes

0ba35ce31b57bb6d…

skills/multi-llm/assets/icons/Nvidia.svg

skill

2,468 bytes

034bb5cb032e6174…

skills/multi-llm/assets/icons/OhMyPi.svg

skill

434 bytes

9419975a0c249613…

skills/multi-llm/assets/icons/OpenAI.svg

skill

1,692 bytes

2e1570091e2a6978…

skills/multi-llm/assets/icons/Opencode.svg

skill

325 bytes

5a44ee78769508c7…

skills/multi-llm/assets/icons/Pi.svg

skill

440 bytes

a5624bc3b8cac94d…

skills/multi-llm/assets/icons/Qwen.svg

skill

1,790 bytes

dcb3ba2f2b55ccba…

skills/multi-llm/assets/icons/xAI.svg

skill

343 bytes

a805762f862713b8…

skills/multi-llm/assets/omp/overlay.yml

skill

2,429 bytes

0549de94ebdf16d0…

skills/multi-llm/check_workflow_prerequisites.py

skill

77,149 bytes

c17ce6d916273ea9…

skills/multi-llm/code_review_orchestrator.py

skill

340,163 bytes

07c0cb7255e3606a…

skills/multi-llm/display_decisions.py

skill

10,094 bytes

0ce82910d7ec4aad…

skills/multi-llm/finalize_tracking.py

skill

40,585 bytes

bd1d36d5eb097225…

skills/multi-llm/full_workflow_orchestrator.py

skill

57,227 bytes

ac1437a42bd78a63…

skills/multi-llm/generate_tasks_orchestrator.py

skill

39,308 bytes

038c2c925ed61c04…

skills/multi-llm/hosts/capabilities.yaml

skill

48,864 bytes

6fc0f5e4fed1b5c9…

skills/multi-llm/hosts/render_capabilities.py

skill

49,513 bytes

bf106c4eb350be5e…

skills/multi-llm/hosts/snippets/poll-loop.md

skill

4,527 bytes

024517572a3f7e30…

skills/multi-llm/hosts/snippets/uv-preflight.md

skill

2,300 bytes

22138851a10b5500…

skills/multi-llm/hosts/uv-missing.txt

skill

1,485 bytes

9a652aa2094b0908…

skills/multi-llm/implement_orchestrator.py

skill

152,286 bytes

5de9eb9d97dfd771…

skills/multi-llm/improve_code_orchestrator.py

skill

1,513 bytes

6174a2c7f7a47668…

skills/multi-llm/improve_commits_orchestrator.py

skill

2,122 bytes

7527f7f0a1e2fe9a…

skills/multi-llm/improve_plan_orchestrator.py

skill

1,456 bytes

dae6300b038a0574…

skills/multi-llm/init_config.py

skill

58,608 bytes

07c26d21e8f72eed…

skills/multi-llm/instructions/apply-code-fixes.md

skill

58,108 bytes

f735e2de7ab7e46d…

skills/multi-llm/instructions/apply-commit-fixes.md

skill

10,561 bytes

a504ede070c433ad…

skills/multi-llm/instructions/apply-suggestions.md

skill

54,745 bytes

86f899e2fc72e0e7…

skills/multi-llm/instructions/apply-task-suggestions.md

skill

53,450 bytes

1aec376955ec0229…

skills/multi-llm/instructions/ask.md

skill

28,310 bytes

8ebd45dd31a76293…

skills/multi-llm/instructions/full-workflow.md

skill

25,027 bytes

ca4fce015331e651…

skills/multi-llm/instructions/generate-tasks.md

skill

18,514 bytes

3052c5a674fc20b0…

skills/multi-llm/instructions/implement.md

skill

64,189 bytes

6e81a2165abb769a…

skills/multi-llm/instructions/improve-code.md

skill

18,996 bytes

46f9b6b5f5a90d6f…

skills/multi-llm/instructions/improve-commits.md

skill

25,335 bytes

d60615f93a348f81…

skills/multi-llm/instructions/improve-plan.md

skill

19,967 bytes

9b6efaff9b456fd9…

skills/multi-llm/instructions/init-config.md

skill

6,779 bytes

fffc00aed308e72c…

skills/multi-llm/instructions/review-code.md

skill

45,989 bytes

f6e6718e97802166…

skills/multi-llm/instructions/review-commits.md

skill

11,638 bytes

7a77887b097ea9b3…

skills/multi-llm/instructions/review-plan.md

skill

43,572 bytes

545b3e53df259bf4…

skills/multi-llm/instructions/review-tasks.md

skill

37,754 bytes

ff487c31813fd42d…

skills/multi-llm/modes.py

skill

62,052 bytes

079a9c720c0a3a84…

skills/multi-llm/multi_llm.py

skill

82,931 bytes

3ec58ba2ef0ba28f…

skills/multi-llm/prompts/ask.txt

skill

948 bytes

922f89081c14c40b…

skills/multi-llm/prompts/code_review.txt

skill

4,585 bytes

d294a886e885f3e7…

skills/multi-llm/prompts/commit_review.txt

skill

6,366 bytes

f49d39c443df232b…

skills/multi-llm/prompts/consolidate_suggestions.txt

skill

3,190 bytes

01df4ecd3f8dd82a…

skills/multi-llm/prompts/implementation_task.txt

skill

1,393 bytes

905c8ff61755ccc1…

skills/multi-llm/prompts/plan_review.txt

skill

8,176 bytes

8ccb5dd91bb321f8…

skills/multi-llm/prompts/task_review.txt

skill

8,499 bytes

0d2db037ee4eb85b…

skills/multi-llm/providers.yaml

skill

79,505 bytes

8f0c8edbd0fbee3f…

skills/multi-llm/pyproject.toml

skill

5,214 bytes

7db1f4a09f4d2ae7…

skills/multi-llm/references/host-capabilities.md

skill

14,429 bytes

b2e9e5abb356580d…

skills/multi-llm/references/human-decision-batch.md

skill

17,642 bytes

400191f2641326f4…

skills/multi-llm/references/own-check.md

skill

4,420 bytes

e876fd7a83375269…

skills/multi-llm/references/resume-detection.md

skill

2,206 bytes

2f72ddf6f2ff02a5…

skills/multi-llm/references/salvage-handling.md

skill

12,788 bytes

cf3c7c42a304439a…

skills/multi-llm/references/summary-format.md

skill

9,834 bytes

113efadef277689e…

skills/multi-llm/references/uv-check.md

skill

5,791 bytes

2de4dad456f22db8…

skills/multi-llm/references/wave-batching.md

skill

5,328 bytes

4cc9a264e327023c…

skills/multi-llm/review_commits_orchestrator.py

skill

2,080 bytes

174b405df57cb1bc…

skills/multi-llm/review_plan_orchestrator.py

skill

31,925 bytes

a590963f44efdfbf…

skills/multi-llm/review_tasks_orchestrator.py

skill

10,978 bytes

7ea3906c378f22d3…

skills/multi-llm/schemas/code_review_issues.schema.json

skill

2,037 bytes

4f9764b988e6075c…

skills/multi-llm/schemas/consolidated.schema.json

skill

6,688 bytes

322bf46087655ede…

skills/multi-llm/schemas/consolidation_batch.schema.json

skill

3,795 bytes

baa84ad1a6b3569f…

skills/multi-llm/schemas/generated_tasks.schema.json

skill

3,172 bytes

5aed8029ece8014f…

skills/multi-llm/schemas/host_capabilities.schema.json

skill

38,582 bytes

f43af3523e88299c…

skills/multi-llm/schemas/human_decision_verdicts.schema.json

skill

2,623 bytes

420868636bc33aff…

skills/multi-llm/schemas/review_suggestions.schema.json

skill

2,477 bytes

723df8137f0b236f…

skills/multi-llm/schemas/state_file.schema.json

skill

18,494 bytes

5b0e06c4e779fa1e…

skills/multi-llm/schemas/subagent_tasks.schema.json

skill

19,555 bytes

51794791e94b42ef…

skills/multi-llm/schemas/task_decomposition.schema.json

skill

1,254 bytes

d623e7dd211cc052…

skills/multi-llm/schemas/write_batch_result.schema.json

skill

9,002 bytes

f96e1970bd297017…

skills/multi-llm/SKILL.md

skill

4,105 bytes

0e941d5a52defac6…

skills/multi-llm/templates/config/providers.override.yaml

skill

17,575 bytes

ab2705bf45d96263…

skills/multi-llm/templates/consolidated_report_template.html

skill

69,019 bytes

416e8c3735a8434b…

skills/multi-llm/templates/pr_report_template.html

skill

209,686 bytes

37f08436103621f7…

skills/multi-llm/templates/report_template.html

skill

96,651 bytes

d03c4e6356ec064b…

skills/multi-llm/update_plan_tasks.py

skill

15,100 bytes

b5e58d3c4e97feca…

skills/multi-llm/utils/__init__.py

skill

9,185 bytes

43111171bf4c0147…

skills/multi-llm/utils/apply_orchestrator_base.py

skill

267,471 bytes

70cf50935b1a0c74…

Browse all 210 files

Multi-LLM — Frequently asked questions

What is Multi-LLM?
Multi-LLM is an AI plugin in the HOL registry. Parallel plan, code, and commit reviews across 19 coding CLIs, with validated findings, task generation, implementation, and automated revision.
How do I install Multi-LLM?
Install Multi-LLM in your harness: Codex — codex plugin marketplace add beastlabai/multi-llm-plugin; Any agent — npx [email protected] add beastlabai/multi-llm-plugin. Full step-by-step guidance is on the HOL plugin page.
How do I install Multi-LLM in HOL Guard?
To install Multi-LLM in HOL Guard, start with hol-guard plugin install beastlabai/multi-llm --apply. The complete step-by-step install guide for HOL Guard is on the HOL plugin page.
How do I install Multi-LLM in Codex?
To install Multi-LLM in Codex, start with codex plugin marketplace add beastlabai/multi-llm-plugin. The complete step-by-step install guide for Codex is on the HOL plugin page.
How is the Trust Score for Multi-LLM computed?
Multi-LLM has a HOL Trust Score of 71 out of 100. The score is a weighted sum of six components from a static scan of the source, capped for high-severity findings and adjusted by two disclosed policies. Memberships and payments are not inputs, and a scan is not a safety guarantee. Full breakdown: https://hol.org/registry/plugins/beastlabai%2Fmulti-llm/trust
Who publishes Multi-LLM?
Multi-LLM is published by beastlabai and listed on HOL.

Directory acceptance

Listed in 1 of 5 directory lists

Read from the list each directory publishes on GitHub. Being listed means the directory accepted the plugin; it is not a HOL security rating.

Lists last read . HOL re-reads them every day.

Submitting it? Check it against each directory's rules

Install signal

HOL cannot see every install. These are separate signals from different sources, so they are not added together. Counts under each floor show as <N.

Install commands issued here
<5
HOL Guard install commands issued from this listing, last 28 days.
Opt-in install reports
<10
Machines that reported installing it through HOL Guard in week 2026-W45. Reporting is opt-in, so most installs are not counted.
HOL Guard workspaces
<5
Workspaces that approved it or include it in an approved-plugin feed, as of today.

Related plugins

Ordered by Trust Score. Listings cannot pay for these positions. Check each one fits your task before switching from Multi-LLM.

Alternatives in Development & Workflow

See all Development & Workflow plugins

Reviews and similar plugins