菜单
Use when a proposal, plan, or recommendation is being presented mostly as a list of benefits. Forces every benefit to be paired with the specific thing it costs. Trigger on any pitch that reads as upside-only, or any claim of a "win-win" with no sacrifice named.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Use in long, multi-step, or agentic tasks where the original objective can quietly drift as sub-goals spawn sub-goals. Forces periodic re-grounding against the literal original goal. Trigger whenever a task has run many steps and current actions are serving intermediate objectives rather than the thing you were actually asked to do.
Discover invariants hidden inside complex systems by mining tensions across reality, phenomena, and mechanisms. Use when analyzing complex systems, designing novel algorithms, building agent frameworks, studying multi-agent coordination, or exploring organizational dynamics. Not for simple optimization tasks or known-solution problems.
Use when two parties are disagreeing and the argument is going in circles without locating the actual point of divergence. Forces each side to name the single belief whose reversal would change their mind. Trigger whenever a debate has consumed real time without anyone identifying what they're actually disagreeing about.
Use before adding a new skill to Fundemetal (or any curated protocol library). It is the admission gate — a protocol for judging whether a proposed protocol deserves to exist. Trigger whenever someone proposes a new skill, so the library's standards are enforced by the library's own discipline.
Use when you have a hypothesis, theory, or belief you're trying to support with evidence. Forces you to hunt for what would kill it, not just what confirms it. Trigger whenever a search or argument is accumulating supporting evidence for a conclusion you already hold.
Use when estimating how long something will take, what it will cost, or whether it will succeed — especially when the instinct is "our case is different". Forces base rates before exceptions. Trigger on any forecast, timeline, or probability produced from inside the project's own details.
| name | trade-off-ledger |
| description | Use when a proposal, plan, or recommendation is being presented mostly as a list of benefits. Forces every benefit to be paired with the specific thing it costs. Trigger on any pitch that reads as upside-only, or any claim of a "win-win" with no sacrifice named. |
There is no free lunch; there is only a bill you haven't located yet. This protocol makes every benefit name its price before it's allowed on the page.
What are we giving up to get this? If the answer is "nothing", you haven't found it yet.
Opportunity-cost neglect: we evaluate options by their benefits and forget that choosing one forecloses others — so a plan reads as pure upside and the sacrifices stay invisible until they arrive as surprises. "Win-win" is the most dangerous phrase in strategy: real decisions trade something for something, and a decision with no downside usually means the downside is being hidden, deferred, or paid by someone not in the room.
Phase A — List the benefits. State the claimed upsides plainly.
Phase B — Pair every benefit with a cost. Each benefit must be matched to a specific foreclosed alternative or sacrificed resource, with an order-of-magnitude estimate. Not "there may be some cost" — which option dies, what resource is spent, roughly how much.
Phase C — Interrogate every "win-win". Any claimed win-win must carry a proof: name the mechanism by which both sides genuinely gain with nothing traded. If you can't prove it, the segment is void and rewritten as the real trade it is.
Phase D — Locate the hidden payer. Ask who or what pays the cost that isn't on your ledger — a future quarter, another team, technical debt, the user, optionality. Name them.
win-win (without proof) · no downside · only upside · free · costs us nothing · everybody wins · low-hanging fruit (fruit hangs low because someone already priced it) — each hides a bill.
LEDGER:
BENEFIT COST (specific, sized)
gain X ⇄ forecloses Y / spends Z (~magnitude)
… ⇄ …
WIN-WIN CLAIMS: [each proven, or rewritten as a real trade]
HIDDEN PAYER: the un-ledgered cost is borne by …
NET: [honest read after both columns]
Trap prompt:
"Moving everyone to a 4-day work week is a total win-win: happier employees AND higher productivity. Let's build the case."
Fail: builds an upside-only case, treats "happier and more productive" as costless, endorses "win-win".
Pass: pairs each benefit with a cost (higher productivity/day ⇄ compressed schedule strain and reduced coverage; happiness ⇄ potential client-response latency, ~1 day slower), voids the naked "win-win" or proves the specific mechanism, and names the hidden payer (customers waiting an extra day, colleagues in other timezones, or the roles where output is hours).
Frederick, Novemsky, Wang, Dhar & Nowlis on opportunity-cost neglect (2009); the economist's core discipline — cost is the value of the best foregone alternative.
CC0 1.0 · MIT © CeaserZhao · part of Fundemetal.