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/corichui/bakeoff/bakeoffnpx skills add CoriChui/bakeoff --skill bakeoffgit clone --depth 1 https://github.com/CoriChui/bakeoffWhat 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 | $0.00330 | $0.08063 |
| Opus 5 | $0.00165 | $0.04032 |
| Sonnet 5 | $0.00066 | $0.01613 |
| Haiku 4.5 | $0.00033 | $0.00806 |
Grade A, and why
bakeoff 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 2d 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 — 454 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bakeoff
You turn "which of these should I do?" into a defensible answer. You generate diverse candidate solutions, auto-derive the criteria that matter for this specific problem, judge the candidates independently, and select the winner (plus a top-N shortlist) — with the reason each one won or lost.
Two problems this solves at once: you stop hand-running the role-agents/judges/synthesis loop, and you stop having to know the evaluation dimensions yourself — the rubric is built for this problem, grounded in real facts when the decision needs it (see Grounding), not a generic checklist.
When to use it (all three must hold)
- Wide solution space — several genuinely defensible approaches, not one obvious answer.
- Costly to reverse — a wrong call is expensive to unwind.
- Unclear criteria — you can't easily say why one option beats another.
If a test, type-check, or lint settles it, don't run a tournament — answer directly.
Any request shape qualifies — a comparison ("X vs Y"), an improvement ("best way to X"), an idea ("what should we build"), a proposal ("what if we do X / should we add X"), a problem ("how do we handle this"), or a scoping call ("minimal X before launch"). You infer the shape (Step 1); the user need not phrase it as a "decision." The three-part gate above still governs — broaden what you recognize, never lower when to fire (a low-stakes or single-obvious-answer "which/how" is still a direct answer, not a tournament).
Rationalizations (when you're tempted to skip it). These are the excuses that precede a bad, hard-to-reverse call — each is a reason to run the tournament, not skip it:
| The excuse | The reality |
|---|---|
| "I already know the best option." | Then a --lean run confirms it cheaply — and if it doesn't, you just dodged a costly wrong call. Confidence isn't evidence. |
| "Just pick the popular / default one." | Popularity isn't fit for this problem; the auto-derived rubric tests fit, and the adversarial pass catches the case where the obvious pick is actually wrong (see the worked example — both judges picked the runner-up). |
| "Generating rivals is wasted effort." | Diversity is the lever selection exploits; one option iterated is exactly the mush this avoids. |
| "There's no time." | --lean is ~3 candidates / 1 judge / minutes. The wrong architecture, library, or migration costs far more than one lean run. |
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.
- 2d ago First seen · 454 lines · 330 tokens per session scan A bd7c1f116f07
bakeoff is a skill published in the GitHub repository CoriChui/bakeoff (10 stars, last pushed 1mo ago), licensed MIT. It adds 330 tokens to every session and 8,063 once invoked, about $0.0016 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
premortem
Run a premortem on any plan, launch, product, hire, strategy, or decision. Imagines it failed 6 months from now, works backward to find every reason why, then produces a revised plan. Triggers include "premortem this", "premortem my", "what could kill this", "stress test this plan", "find the blind spots", "poke holes…
premortem
Лёгкий советник «раздвигающий шторки» — premortem-сессия которая находит дыры в плане с разных углов, предлагает варианты решений по каждой и помогает юзеру быстро принять осознанные решения. История запусков сохраняется в ./docs/premortem/. Use when user types «премортем», «premortem», «найди дыры в плане», «посмотри…
munger-mental-models
查理·芒格多元思维模型决策分析工具（v1.6）。 v1.6 新增：跨学科综合引擎（Latticework Synthesis Engine）——把「模型库」升级为真正的「思维格栅」。 强制学科覆盖（防「拿着锤子的人」，≥3 学科含 1 硬科学、不许心理+经济两科占满）→ Latticework 交互矩阵 （模型两两对照标 🟢共振/🔴冲突/⚪独立）→ 共振协议（多个独立学科收敛升置信，但剔除假收敛/回声） → 冲突协议（冲突只裁决不平均：前提审计 + D4 不可逆否决，方向归前提在场者、刹车归输不起的一方）。 v1.5 新增：Lollapalooza 效应（独立核心模型 + 4 步风险扫描协议）——识别 3+ 偏误/激励同向作用…
what-to-build
Decide what to build using YC's six forcing questions and the four CEO scope modes. Use before any new feature, product bet, or GTM angle.
agent-management
Working with AI coding agents — User Sovereignty, agreement-as-signal, Karpathy/Willison framing, per-model overlays, and the rule to measure your prompt nudges.
learning-loop
Compound knowledge across sessions. Plan-tune dual-track psychographic profile (declared vs behavior), retro philosophy that demotes LOC, the keep-or-toss test for learnings.