Per-agent principles · 15 of 15

Anti-pattern #1 — cookie-cutter AI aesthetic

Designer · S75 P0-1 · docs/agent-knowledge/designer/expertise/anti-patterns-catalog.md

8 specific defaults to reject. Every Designer dispatch must anti-pattern ≥3 with primary-literature rationale. Cookie-cutter pastel-on-white frequently fails WCAG 1.4.3 AA.

Anti-pattern #2 — lead-with-user-summary-as-target

Designer · S75 P0-1 · docs/agent-knowledge/designer/expertise/anti-patterns-catalog.md

Designer derives IA shape from user verbal phrasing rather than primary research. R34 violation; sibling C24 root.

Anti-pattern #8 — WCAG-as-post-hoc-patch

Designer · S75 P0-1 · docs/agent-knowledge/designer/expertise/anti-patterns-catalog.md

Accessibility checked at handoff time only. WCAG 2.2 AA is non-optional standing gate per Cluster 4.

Anti-pattern #10 — single-direction-proposal-skipping-divergent-half

Designer · S75 P0-1 · docs/agent-knowledge/designer/expertise/anti-patterns-catalog.md

Phase 5 task decomposition outputs single design direction without enumerating 2-3 alternatives considered + rejected (Buxton 2007 Double Diamond).

H-1 first-time-student simulation runs FIRST on every screen

Ux · S75 P0-1 · docs/agent-knowledge/ux/expertise/lens-rubric.md

Before any structural / heuristic check. If section is not obvious from on-screen alone, section FAILS. Krug 2014 first-law floor.

Anti-pattern #11 — soft-sign-off-after-R30-codification

Ux · S75 P0-1 · docs/agent-knowledge/ux/expertise/anti-patterns-catalog.md

Phrase-level PASS verdict instead of formal sign-off-block (reviewer + timestamp + scope + verdict). R30 codified after S75 C15 fired.

Anti-pattern #13 — decorative cross-class invocation

Ux · S75 P0-1 (L-3 Q4 disposition) · docs/agent-knowledge/ux/expertise/anti-patterns-catalog.md

Citing Researcher / Designer corpus literature decoratively without primary-literature anchor in cross-class claim = explicit failure.

Researcher anti-pattern — vendor-survey-instead-of-first-principles

Researcher · M-1 brief §1.4 · docs/agent-knowledge/researcher/expertise/anti-patterns-catalog.md

Researching agent landscape via LangChain / CrewAI marketing instead of grounding in agent-architecture primary literature. Symptom: brief reads as feature comparison.

Progressive elicitation (S43 origin)

Researcher · S43 · docs/agent-knowledge/researcher/principles/progressive-elicitation.md

When writing multi-section arcs, each section should add one visible element to the running artifact. The 3 C's pattern (Card → Conversation → Confirmation).

Session 2 retention (S43 origin)

Researcher · S43 · docs/agent-knowledge/researcher/principles/session-2-retention.md

When designing Session 2 of any course, the aha must escalate from S1 (not repeat it). The student's artifact is the commitment device.

Four infrastructure patterns for tutor_active sections

Tutor-Behavior · Cumulative · docs/agent-knowledge/tutor-behavior/principles/four-infrastructure-patterns.md

Every tutor_active section needs context_rule, narration_rule, named generation directives, and length-constrained teaching_point. The #1 structural cause of quality gaps.

Re-verify after fixing

Cc-Orchestrator · Standing · docs/agent-knowledge/orchestrator/principles/re-verify-after-fixing.md

After fixing code based on agent feedback, re-invoke the reviewing agent to verify the fix. Don't assume the fix is correct without independent verification.

Read seed data as the student

Cc-Orchestrator · S40 · docs/agent-knowledge/orchestrator/principles/read-seed-data-as-student.md

Seed data must be read as the target student would experience it, not as the author.

QA runtime verification

Qa · S46 · docs/agent-knowledge/orchestrator/principles/qa-runtime-verification.md

QA narrative journey must include runtime evidence (Playwright, screenshots, console logs). Seed data analysis alone insufficient.

Exhaustive testing not representative

Qa · S53 · docs/agent-knowledge/orchestrator/principles/exhaustive-not-representative-testing.md

Test plans must click every link, tab, and button — not a sample. QA's 17-item test missed broken links Jon found in 30 seconds.