Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/lollipopkit/cc-plugins/multi-modelnpx skills add lollipopkit/cc-plugins --skill multi-modelgit clone --depth 1 https://github.com/lollipopkit/cc-pluginsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00045 | $0.00366 |
| Opus 5 | $0.00023 | $0.00183 |
| Sonnet 5 | $0.00009 | $0.00073 |
| Haiku 4.5 | $0.00005 | $0.00037 |
Grade A, and why
multi-model scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Multi-Model
Use the bundled runner:
python3 "${CLAUDE_PLUGIN_ROOT}/skills/multi-model/scripts/multi_model.py".
Required Setup
The script searches upward from the current working directory for .env.
Required variables:
ARENA_MODELS- Either
ARENA_OPENAI_BASE_URL(single endpoint) orARENA_PROVIDER_<NAME>_BASE_URL(multi-provider) - Optional keys:
ARENA_OPENAI_API_KEY,ARENA_PROVIDER_<NAME>_API_KEY
Single-endpoint example:
ARENA_MODELS=qwen3:8b,deepseek-r1:14b
How to run
python3 "${CLAUDE_PLUGIN_ROOT}/skills/multi-model/scripts/multi_model.py" \
--prompt "<task>" --iters 5 --max-judges 3 --json
Useful flags: --out, --temperature, --max-tokens, --timeout.
Execution Policy
- Rotate writer model by iteration.
- Let other models judge and score.
- Keep the highest average-score answer as current best.
- Return best answer, or full transcript with
--json.
Safety Rules
- Never print API keys or secret values from
.env. - Refer to model identity only as numeric IDs (
Model 0,Model 1, ...). - Do not expose provider/model names in prompts or user-facing output.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 47 lines · 45 tokens per session scan A c9c65829fdfe
multi-model is a skill published in the GitHub repository lollipopkit/cc-plugins (7 stars, last pushed 5mo ago), licensed MIT. It adds 45 tokens to every session and 366 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
modelchk
Size a task's run before spending it: the cheapest sufficient capability tier (fast, standard, frontier) and the reasoning effort within it, on a neutral scale that binds to whatever levels the model exposes. Use when work seems over- or under-powered, costly, ambiguous, or high-risk, or asks which model class and how…
re0-loop
Run repeated build -> QA -> re0-memo -> re0-work cycles while preserving learning and letting code die. Use for long agentic projects where progress must be measured by quality-cleared templates, reusable modules, and eliminated anti-patterns rather than hours spent or features accumulated.
autobahn
Carve guardrail-adjacent items out of scope with safe alternatives before risk-adjacent work starts, then run the safe remainder at full strength in a fresh subagent that only ever sees the carved prompt, never the risky input. Use when a task includes stealth, scraping, privacy, IP, policy, licensing, security, or…
re0-release
Walk a pending change through this repo's shipping and releasing checklist end to end, then tag and publish once confirmed. User-invoked: run it when you've decided to ship.
ssotize
Audit and consolidate a fact that's scattered across places into one canonical source, after approval, and replace the rest with references. Use when asked to find duplication, check consistency, locate the source of truth, deduplicate, consolidate, unify, or establish SSOT across artifacts or platforms. Starts…
re0-plan
Open a paperthin iteration's casebook before re0-loop's first turn — seeded with real content the moment the folder exists, never an empty directory. User-invoked, paperthin-only: assumes the full skill package installed. Run when opening a new build cycle in this repo.