Fundemetal

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.

Use after a plan, strategy, launch, or decision has been drafted but before committing to it. Forces the failure to be imagined concretely instead of the success. Trigger whenever a proposal reads as a list of reasons it will work.

Use when generating options, ideas, solutions, or approaches — before evaluating any of them. Forces a quota of genuinely distinct candidates and bans premature judgment. Trigger whenever the first workable idea is starting to monopolize attention.

Use before answering a question that smuggles in hidden premises or false constraints — especially "how do I do X" questions where X may be the wrong thing to do. Forces the question to be interrogated before it is answered. Trigger whenever answering the question as asked would solve the wrong problem brilliantly.

Use when a plan or belief has reached consensus and everyone in the room agrees with it. Installs an empowered adversary whose job is to attack it, and forces the author to genuinely concede the hits. Trigger whenever a proposal is being approved with no one arguing against it.

Use when reviewing a past decision, running a retrospective, or judging whether a choice was good — after the outcome is known. Forces decision quality and outcome quality to be scored separately. Trigger whenever a good result is being used as proof of a good decision, or a bad result as proof of a bad one.

Use when evaluating an action that affects other agents who will react — pricing changes, policy changes, incentives, competitive moves, rule changes. Forces you to model the reactions, and the reactions to the reactions. Trigger whenever a plan assumes the world holds still while you act on it.

Use when multiple agents (or people) will weigh in on the same question — multi-agent debate, ensemble reasoning, or a group deciding together. Prevents the first voice from anchoring everyone else. Trigger whenever independent judgments are about to be collected in sequence, where later voices can see earlier ones.

Use when a conclusion rests on a mix of facts, and some of those "facts" may actually be assumptions, hearsay, or inferences wearing the costume of certainty. Forces every load-bearing claim to be tagged by how you know it. Trigger on research summaries, situation assessments, and any output where a hallucination or an unexamined assumption would be costly.

Use before arguing against a position, critiquing an idea, or rebutting someone. Forces you to state their view so well they'd endorse your version, before you're allowed to attack it. Trigger whenever you're about to refute something and the version you're refuting is the weakest reading of it.

Use when analysis is continuing past the point of usefulness — more research, more frameworks, more deliberation on a decision that could already be made. Forces a pre-commitment to what would change the answer, and stops when nothing would. Trigger whenever thinking has become a way to avoid deciding.

Use when a discussion, plan, or document is thick with abstract buzzwords that feel meaningful but resist operationalization ("leverage", "synergy", "empower", "ecosystem", "streamline"). Bans the words and forces concrete restatement. Trigger whenever fluent language is standing in for unclear thinking.

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.

A meta-skill for recognizing when a reusable methodology has emerged during work, articulating that tacit 'unnameable' insight into explicit words, and crystallizing it into a new skill for future reuse. Trigger proactively (don't wait for an explicit request) when any of these signals fires: (a) a breakthrough after prolonged struggle; (b) the user's short correction fundamentally changes your approach; (c) the same non-obvious judgment keeps recurring (3+ times); (d) someone says 'it just feels off / I can't say why but it should be this way'; (e) explicit request such as 'turn this into a skill' / 'save this as a skill' / 'always do it this way' / 'this matters' / 'crystallize it'. Also use it to review past work for lessons worth codifying. Operate in the user's working language.

Shoulders of Giants — an architect-grade protocol for reusing existing code (GitHub repos, open-source libraries, reference implementations) inside any project. Treats dependency selection as a SOVEREIGNTY decision, not a search task. Use it whenever the user wants to find libraries, frameworks, repos, or "existing code / a wheel / an open-source solution" for any part of a project; asks "is there something ready-made", "don't reinvent the wheel", "help me find a library", or is making any build-vs-buy / build-vs-borrow call — even if they only ask for a simple search. NEVER answer such requests with a bare list of repos; this protocol MUST run first, because dependency selection is an architectural decision, not a retrieval task. Not for trivial glue code or throwaway one-off scripts.

Use BEFORE the model agrees with the user — especially when the user states an opinion confidently ("clearly", "surely", "obviously", "don't you think"), asks for confirmation ("right?", "makes sense?", "good idea?"), or presents a plan they're visibly attached to. Also fire when the user's phrasing signals the expected answer — even without an explicit ask. Do NOT skip just because the user seems reasonable or the topic is technical — those are precisely when sycophancy is hardest to detect. Skip only if the user has explicitly invited disagreement ("tell me what's wrong", "I'm unsure, what's your take?").

Cognitive protocol that converts unknown unknowns into known unknowns. Invoke for large/ambiguous goals, or when user asks for honest breakdown, decomposition, or avoiding empty plans.