# Judgment Or Code > Use when about to write or change something that decides or generates - a keyword blocklist, a name or entity matcher, a regex validator, a scoring threshold, a classification or validation step, a "confirmed" or "verified" flag, a quality gate on generated output, a dedup or filter rule, or a human review queue. Also use when adding or removing an LLM call from a pipeline, or when a mechanical rule keeps needing another exception. Decides which side of the line each output belongs on - deterministic code, or a judge model with a written rubric. - Skill: `farhan1188/judgment-or-code` (Agent Skill) - Install (CLI): `npx skillmds@latest add farhan1188/judgment-or-code` - Raw SKILL.md: https://api.skillmd.com/api/skills/farhan1188/judgment-or-code/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: DevOps & Infra - License: MIT - Author: farhan1188 (https://skillmd.com/u/farhan1188) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/farhan1188/judgment-or-code --- # Judgment or code **Decide per OUTPUT, and write its acceptance rule down the way the operator would state the goal, never in the phrasing that makes your preferred tool fit.** The failure this prevents is not choosing wrong once. It is choosing by habit: reaching for a regex because regexes are cheap and testable, or reaching for a model because models feel smart, and then writing the acceptance rule backwards from the tool you already picked. ## The three failures this was written after Read these first. Each rule below is one of them generalised. - **203 vacuous outreach hooks.** A cheap model was asked to "be specific" about companies whose input records differed only in trivia. The model was not the problem; the *grounding* was. Every hook passed the check "mentions the company", and every hook was garbage. - **48 of 50 "confirmed" profile URLs were wrong.** Confirmation rested on a name-only string match against the claim's own subject. N fields scraped from one source is one signal, not corroboration. - **A 200-word name blocklist still misfiring on real names.** Every miss produced another entry. A list that keeps growing to chase an open boundary is judgment mechanised, and it never converges. ## The nine 1. **Code owns the checkable; checkable never certifies quality.** Exact match, schema, enum, arithmetic, state, or a finite table the business maintains as policy: code. But passing a mechanical check never makes creative output good. *"mentions the city" passes, and is garbage.* 2. **An LLM judge owns every open meaning boundary.** Semantic failure (vacuous, wrong entity, off topic) in an open-ended category goes to a judge model with a written rubric **plus real failing examples**. Closed policy registries are code plus normalisation. Try the cheaper exits first: normalise the input, fix the source data, drop the unreliable feature. 3. **Grounding before model tier, and the difference must be usable.** Two subjects must receive inputs that differ in material a writer could actually build the intended output from. Differentiated trivia is still starvation. **Fix what is fetched before touching the prompt or the model.** 4. **Judge creative batches against sampled siblings**, plus the class definition. Could whoever the output lands on tell it was made for them? Is it welcome, rather than merely identifying? Does it share a skeleton with its siblings? Per-row judging of a batch product is a blind spot: each row passes, and the batch is obviously machine-made. 5. **Real-world claims need evidence that could disagree.** N fields scraped from the claim's own subject are one signal. *Confirmed* requires independent corroboration or a first-party authoritative source; otherwise the state is **unconfirmed** or **conflicting**: first-class, visible, and never rounded up downstream. 6. **Verdicts are categorical, with the evidence tied to the decision.** Code thresholding a model's own uncalibrated score is judgment laundering. A genuinely calibrated probability is evidence; the default is a category plus a quoted reason. 7. **Hard invariants stay mechanical.** Spend, schemas, dedup, state machines, send and publish gates: code, enforced once, no repair-loop stacking. A gate boolean may *carry* an upstream judged verdict; the gate itself never improvises. 8. **A human gate is sized to human attention, and thinning is defined.** The machine judge rejects or flags; the human reads everything flagged plus a stated sample of the approved; machine- approved output ships only for a class the human approved *as a class*. **Bulk approve is not review.** 9. **Spend on judgment where wrongness is expensive.** Output that reaches an outside person or gates money gets judged whatever the calls cost. Internal low-stakes fields do not buy a jury. Cheap calls are no licence to add LLM passes where code computes the one right answer. ## Tripwires: any one means stop and re-route - An open-category word list that needed another entry. - A model told to "be specific" on class-shared input. - "Confirmed" derived from single-provenance evidence. - An uncalibrated self-score thresholded by code. - An LLM inserted where code already computes the answer. - A review step that has quietly become bulk approve. ## The short version Code owns the checkable. A judge owns every open meaning boundary. Passing a mechanical check never certifies that creative output is good.