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/0xagentkitchen/kitchenloop/discussion-moderatornpx skills add 0xagentkitchen/kitchenloop --skill discussion-moderatorgit clone --depth 1 https://github.com/0xagentkitchen/kitchenloopWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/0xagentkitchen/kitchenloop/discussion-moderator)<a href="https://agentmods.dev/skills/0xagentkitchen/kitchenloop/discussion-moderator"><img src="https://agentmods.dev/badge/skills/0xagentkitchen/kitchenloop/discussion-moderator.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00000 | $0.03411 |
| Opus 5 | $0.00000 | $0.01706 |
| Sonnet 5 | $0.00000 | $0.00682 |
| Haiku 4.5 | $0.00000 | $0.00341 |
Grade A, and why
discussion-moderator 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 4d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Discussion Moderator
Description
Orchestrate a structured multi-AI discussion. Gemini and Codex debate via CLI, Claude debates via an isolated subagent, and you are the impartial moderator.
Triggers
- "discuss", "start a discussion about", "debate", "have the AIs argue about"
- "discussion moderator"
Hard requirement: all 3 debaters must be available
If any debater CLI is unavailable (auth expired, not installed, crashing), cancel the discussion immediately and report the failure to the user. Do NOT proceed with 2 debaters. Do NOT silently skip a model.
Abort: Gemini auth expired. Discussion cancelled.
Please run `gemini` in an interactive terminal to re-authenticate, then retry.
The script enforces this by default (--require-all-models is the default).
--allow-missing-models exists only for debugging, never for production runs.
Architecture
You (Moderator) -- impartial, never participates in the debate
|
|-- discuss.py --run-turn gemini (Gemini CLI)
|-- discuss.py --run-turn codex (Codex CLI)
|-- discuss.py --get-prompt claude --> Task subagent (Claude DEBATER, isolated)
| echo "$response" | discuss.py --add-response claude
|-- discuss.py --status (mechanical convergence check)
|
After debate:
|-- discuss.py --save-report (write structured summary into convo.json)
Isolation model: The Claude debater subagent sees ONLY the debate prompt. It has no access to your moderator reasoning. You see only its output. The subagent boundary is the information firewall.
Instructions
Phase 1: Pre-flight check + create the conversation
First verify all 3 CLIs respond before starting:
gemini -p "ping" 2>&1 | head -1 # must NOT contain "Error authenticating"
codex exec "ping" 2>&1 | tail -1 # must produce output
# Claude debater runs via subagent -- no CLI check needed
If Gemini fails: tell the user to run gemini in an interactive terminal to
re-authenticate, then retry. Do not proceed.
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.
- 4d ago First seen · 406 lines · 0 tokens per session scan A e304ed5b6224
discussion-moderator is a skill published in the GitHub repository 0xagentkitchen/kitchenloop (23 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,411 tokens. 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…