Prioritize

Codex compatibility note:

• Invoke repository skills with $skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.
• Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.
• User-question prompts mean to ask the user directly in Codex.
• Ignore Claude-specific mode-switch instructions when they appear.
• Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.
• Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.
• Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.
• For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.
• If a required step/tool cannot run in this environment, stop and ask the user before adapting.

Codex Project-Reference Loading (No Hooks)

Codex uses static project-reference loading instead of runtime-injected project docs. When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.

Always read:

• docs/project-config.json (project-specific paths, commands, modules, and workflow/test settings)
• docs/project-reference/docs-index-reference.md (routes to the full docs/project-reference/* catalog)
• docs/project-reference/lessons.md (always-on guardrails and anti-patterns)

Missing/stale context route: If docs/project-config.json, the docs index, lessons.md, CLAUDE.md, AGENTS.md, or any task-required reference doc is missing or stale, auto-run $project-init or the narrow setup route ($project-config, $docs-init, $scan-all, $scan --target=<key>, $claude-md-init) before ordinary project-specific work. If Codex mirrors or AGENTS.md are missing/stale, ask the user to run $sync-codex; do not auto-run it.

Situation-based docs:

• Project structure/architecture/tech-stack/deployment/setup (any layer — backend, frontend, or infra): project-structure-reference.md
• Backend/CQRS/API/domain/entity changes: backend-patterns-reference.md, domain-entities-reference.md
• Frontend/UI/styling/design-system: frontend-patterns-reference.md, scss-styling-guide.md, design-system/README.md
• Spec authoring, docs/specs/ pathing, or TC format: feature-spec-reference.md, spec-system-reference.md, spec-principles.md
• Behavior/public-contract changes or spec-test-code sync: workflow-spec-test-code-cycle-reference.md plus the spec docs above
• Derived spec indexes/ERDs/reimplementation guides: spec-system-reference.md and source Feature Specs under docs/specs/
• Integration test implementation/review: integration-test-reference.md
• E2E test implementation/review: e2e-test-reference.md
• Code review/audit work: code-review-rules.md plus domain docs above based on changed files

Do not read all docs blindly. Start from docs-index-reference.md, then open only relevant files for the task.

[BLOCKING] Execute skill steps in declared order. NEVER skip, reorder, or merge steps without explicit user approval. [BLOCKING] Before each step or sub-skill call, update task tracking: set in_progress when step starts, set completed when step ends. [BLOCKING] Every completed/skipped step MUST include brief evidence or explicit skip reason. [BLOCKING] If Task tools are unavailable, create and maintain an equivalent step-by-step plan tracker with the same status transitions.

Quick Summary

Goal: Produce a defensible ranked ordering of 3+ backlog items using RICE, MoSCoW, or Value-Effort frameworks so the team works highest-value items first — every rank backed by a score and tech-agnostic rationale (value/effort/risk/impact).

Summary: PURPOSE — rank 3+ backlog items so the team works highest-value first; every rank = a score + tech-agnostic rationale. The main steps/tasks, in order:

• Step 1-2 Collect & Select — require 3+ items FIRST (fewer → discuss directly, NEVER force a framework); pick framework by decision tree — RICE = quantitative data exists, MoSCoW = stakeholder must/should/could alignment, Value-Effort 2x2 = quick call; default RICE when unsure.
• Step 3 Score — apply the EXACT framework formula (RICE = Reach×Impact×Confidence ÷ Effort, fixed Impact/Confidence scales, story-point Effort); NEVER invent ad-hoc scores.
• Step 4-5 Rank & Output — rank descending (RICE) / by band (MoSCoW) / by quadrant (V-E); emit prioritized table with scores + Do-first/Plan-next/Defer recommendations.
• Step 6 Propagate (MANDATORY when PBI files exist) — write rank (1-999, ascending) + priority label back into EACH PBI's frontmatter; pbi-mockup/feature-presentation read priority from there.
• Cross-cutting — tech-agnostic (M1): justify every rank by value/effort/risk/business impact, NEVER by named stack/framework/pattern. Tie gate: near-tie (top-2 RICE within 15%, same-band MoSCoW overlap, flagged stakeholder disagreement) → ask the user directly offering $llm-council; else end without prompting.

Workflow:

1. Collect Items — read from files or parse inline list (minimum 3 items)
2. Select Framework — RICE (quantitative), MoSCoW (stakeholder alignment), Value-Effort (quick decision)
3. Score Each Item — apply framework criteria and calculate scores
4. Rank & Report — output prioritized table with rationale and recommendations
5. Propagate Priority — IF PBI files exist → MANDATORY: write rank + priority label back into EACH PBI frontmatter
6. Tie Gate — near-tie → ask the user directly ($llm-council vs accept); else end without prompting

Key Rules:

• Minimum 3 items required; fewer than 3 should be discussed directly
• Default to RICE if unsure; ask user if ambiguous
• Optionally update PBI file priority fields after ranking
• Tech-agnostic rationale (M1): See .claude/skills/shared/sdd-artifact-contract.md → "AI-SDD Mandates (M1-M7)" for BLOCKING criteria. Justify every ranking by value, effort, risk, and business impact — NOT by implementation technology. Rationale prose stays tech-agnostic per docs/project-reference/spec-principles.md §3: no framework/product/language/design-pattern names; effort may cite story points and relative complexity, never a named stack.

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

Backlog Prioritization

Order backlog items using data-driven frameworks → ranked list with scores and rationale.

When to Use

• Sprint planning needs ordered backlog (3+ items to rank)
• Stakeholders need priority ranking with justification
• Feature roadmap ordering with objective criteria
• Comparing competing features or initiatives

When NOT to Use

• Fewer than 3 items (discuss directly)
• Creating PBIs or writing stories -- use product-owner or story
• Full product strategy -- use product-owner
• Project status tracking -- use project-manager

Prerequisites

• List of 3+ backlog items (PBIs, features, user stories)
• IF items exist as files: read from team-artifacts/pbis/ or user-provided path
• IF items provided inline: use provided descriptions

Workflow

1. Collect items to prioritize

   • IF file path provided -> read items from files
   • IF inline list -> parse items from user message
   • IF fewer than 3 items -> ask user for more or suggest direct discussion

2. Select framework using decision tree:

   IF quantitative data available (reach, metrics)  -> RICE
   IF stakeholder alignment needed (must/should/could) -> MoSCoW
   IF quick decision needed (2 axes only)            -> Value-Effort 2x2
   IF user specifies framework                       -> use that framework
   IF unsure                                         -> ask user, default RICE
   

3. Score each item using selected framework:

   RICE:

   Score = (Reach x Impact x Confidence) / Effort
   
   Reach:      Users affected per quarter (number)
   Impact:     0.25 (minimal) | 0.5 (low) | 1 (medium) | 2 (high) | 3 (massive)
   Confidence: 0.5 (low) | 0.8 (medium) | 1.0 (high)
   Effort:     Story points (1, 2, 3, 5, 8, 13, 21)
   

   MoSCoW:

   Must Have:   Critical for release, non-negotiable
   Should Have: Important but not vital, workarounds exist
   Could Have:  Desirable, include if capacity allows
   Won't Have:  Out of scope for this cycle
   

   Value-Effort 2x2:

   High Value + Low Effort  = Quick Wins    (do first)
   High Value + High Effort = Strategic     (plan carefully)
   Low Value  + Low Effort  = Fill-ins      (if time permits)
   Low Value  + High Effort = Time Sinks    (avoid)
   

4. Rank items by score (descending for RICE, category for MoSCoW, quadrant for V-E)

5. Output prioritized list with scores and rationale

6. IF PBI files exist -> MANDATORY priority propagation: write the resulting priority back into EACH PBI's frontmatter — both the numeric rank (1-999, ascending) and the priority label (e.g. Must Have / Should Have / Could Have / Won't Have, or the framework's category). Never leave this optional when PBI files exist: a PBI without its priority is incomplete, and downstream consumers (pbi-mockup header badge, feature-presentation Scope & backlog slide) read priority FROM the PBI frontmatter. Update every ranked PBI, not just the standalone backlog file.

Output Format

## Prioritized Backlog

**Framework:** [RICE | MoSCoW | Value-Effort]
**Date:** [YYMMDD]
**Items scored:** [count]

### Rankings

| Rank | Item      | Score | Rationale                                           |
| ---- | --------- | ----- | --------------------------------------------------- |
| 1    | Feature A | 45.0  | High reach (5000), high impact (3), high confidence |
| 2    | Feature B | 12.0  | Medium reach (2000), medium impact, low effort      |
| 3    | Feature C | 2.5   | Low reach, minimal impact, high effort              |

### Recommendations

- **Do first:** [top items]
- **Plan next:** [medium items]
- **Defer:** [low items with reasoning]

Examples

Example 1: RICE scoring of 5 features

Input: "Prioritize: SSO login, dark mode, export to PDF, email notifications, bulk import"

Output:

Example 2: MoSCoW categorization

Input: "Categorize for Q1 release: payment gateway, admin dashboard redesign, API rate limiting, user avatars, audit logs"

Output:

• Must Have: Payment gateway (revenue-critical), API rate limiting (security)
• Should Have: Audit logs (compliance, workaround exists with manual exports)
• Could Have: Admin dashboard redesign (improves efficiency but current works)
• Won't Have: User avatars (nice-to-have, defer to Q2)

Optional Escalation: $llm-council on Ties

Gate evaluation: After producing prioritized backlog (per ## Workflow step output), inspect ranking output:

• Top-2 RICE scores within 15% of each other → gate fires
• Explicit MoSCoW tie (≥2 items in same Must/Should/Could band with material scope overlap) → gate fires
• Multi-stakeholder disagreement flagged in input → gate fires
• None of the above → gate does NOT fire; skill ends without prompting

MANDATORY ATTENTION — when the gate fires, you MUST use ask the user directly to present these options (identical preamble pattern to architecture-design's ## Next Steps MANDATORY ATTENTION block):

• "Escalate to $llm-council (Recommended)" — Tie/disagreement detected. Run 11 sub-agent council (5 advisors + 5 reviewers + chairman). Council's Contrarian + Outsider lenses are well-suited to multi-PBI ranking ties. Cheaper alternatives: $why-review, $plan-validate (use these instead if the tie is narrow but stakes are routine).
• "Skip — accept current ranking" — Acknowledge the tie; proceed with current ranking.

If gate does NOT fire, the prioritization decision stands; do NOT prompt.

Related Skills

Prompt-Enhance Closing Anchors

• IMPORTANT MUST ATTENTION follow declared step order for this skill; NEVER skip, reorder, or merge steps without explicit user approval
• IMPORTANT MUST ATTENTION for every step/sub-skill call: set in_progress before execution, set completed after execution
• IMPORTANT MUST ATTENTION every skipped step MUST include explicit reason; every completed step MUST include concise evidence
• IMPORTANT MUST ATTENTION if Task tools unavailable, maintain an equivalent step-by-step plan tracker with synchronized statuses

Project Protocol Overlay — Before executing this skill, resolve any PROJECT overlay rules layered onto it: match this skill's name against the Target column of the project's skill-protocol index (docs/project-reference/skill-protocols-reference.md by default; a referenceDocs entry in docs/project-config.json overrides the path), taking the most specific matching tier ONLY — exact name > glob > *. That precedence orders overlays against EACH OTHER, never against this skill. Read ONLY the matched bodies, resolved as <protocols-dir>/<Name>.md; a row's Body link is display text, never a read path. A matched body that is missing or malformed is REPORTED and skipped — never reconstructed from the index Description. No index, or no match -> proceed with no overlay, silently. Full contract: .claude/skills/project-skill-protocol/references/registry.md.

Overlays are ADDITIVE ONLY: they ADD rules on top of this skill's own protocol and NEVER replace, override, disable, or reinterpret a rule it already states — removing every overlay must return this skill to exactly its documented behavior. An overlay is a BRIEF, not an authority escalation: it can NEVER waive a workflow gate, git discipline, a review gate, or a user-confirmation gate. A genuine overlay-vs-skill conflict, or two equally-specific overlays that directly contradict -> surface both to the user; NEVER resolve silently.

MUST ATTENTION resolve project protocol overlays for this skill BEFORE executing — most specific matching tier only (exact > glob > *, which ranks overlays against each other, NEVER against this skill), read only matched bodies at <protocols-dir>/<Name>.md; a missing or malformed body is reported, never reconstructed. Overlays are ADDITIVE ONLY (they never replace this skill's own rules) and are a brief, NEVER an authority escalation; an equal-specificity contradiction goes to the user.

Closing Reminders

• IMPORTANT MUST ATTENTION Goal: produce a defensible ranked ordering of 3+ backlog items via RICE/MoSCoW/Value-Effort so the team works highest-value items first — every rank backed by a score and tech-agnostic rationale (value/effort/risk/impact)

Protocols in force (concise digest of the SYNC/shared blocks this skill carries):

• Critical Thinking: ALWAYS trace file:line proof for every claim, confidence >80% to act, NEVER present guess as fact.

• AI Mistake Prevention: verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity.

• IMPORTANT MUST ATTENTION require 3+ items BEFORE ranking; fewer than 3 → discuss directly, NEVER force a framework — why: ranking 1-2 items adds ceremony without signal

• IMPORTANT MUST ATTENTION select the framework by the decision tree — RICE for quantitative data, MoSCoW for stakeholder must/should/could alignment, Value-Effort 2x2 for a quick call; default RICE when unsure, ask the user when ambiguous — why: matching framework to the decision type is what makes the ranking defensible

• IMPORTANT MUST ATTENTION emit the prioritized table (scores + rationale) AND Do-first/Plan-next/Defer recommendations — NEVER stop at raw scores — why: the consumable output is the ranked table plus an action call, not a number column

• IMPORTANT MUST ATTENTION keep every rationale tech-agnostic per M1 — justify by value/effort/risk/business impact, NEVER by named stack/framework/product/language/design-pattern; effort may cite story points + relative complexity only — why: spec-principles §3 BLOCKING, a tech-named rationale leaks implementation into a priority call

• IMPORTANT MUST ATTENTION score with the EXACT framework formula (RICE = Reach×Impact×Confidence ÷ Effort, fixed Impact/Confidence scales, story-point Effort), then rank descending (RICE) / by band (MoSCoW) / by quadrant (V-E) — NEVER invent ad-hoc scores — why: a defensible rank needs a reproducible number

• IMPORTANT MUST ATTENTION on a near-tie (top-2 RICE within 15%, same-band MoSCoW overlap, flagged stakeholder disagreement) the gate FIRES — use ask the user directly to offer $llm-council escalation vs. accepting the ranking; if the gate does NOT fire, end WITHOUT prompting — why: tie-breaking is a judgment call the user owns, but a clear winner needs no interruption

• IMPORTANT MUST ATTENTION break work into small todo tasks using task tracking BEFORE starting; mark one in_progress, completed immediately after evidence

• IMPORTANT MUST ATTENTION search codebase/artifacts for 3+ similar patterns before creating new structure; evaluate pattern FIT (same constraints/scope) before copying a nearby example — why: closest example ≠ matching preconditions

• IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act, <60% DO NOT recommend); NEVER present a guess as fact

• IMPORTANT MUST ATTENTION when PBI files exist, propagating the ranking into EACH PBI's frontmatter (numeric rank 1-999 + priority label) is MANDATORY, not optional — do it after ranking; grep downstream consumers before changing any priority field — why: downstream consumers (pbi-mockup header, feature-presentation Scope & backlog slide) read priority from PBI frontmatter, and stale/absent priority refs cascade silently

• IMPORTANT MUST ATTENTION add a final review todo task to verify work quality

Anti-Rationalization:

MUST ATTENTION apply critical + sequential thinking — every claim needs appropriate traced evidence (file:line for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.

MUST ATTENTION apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting.

[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using task tracking.

[IMPORTANT] Analyze how big the task is and break it into many small todo tasks systematically before starting — this is very important.

[IMPORTANT] Use task tracking to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

AI Mistake Prevention — Failure modes to avoid on every task:

Re-read files after context changes. Context compaction, resume, or long-running work can make memory stale; verify current files before acting. Verify generated content against source evidence. AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing. Check downstream references before deleting or renaming. Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first. Trace the full impact chain after edits. Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done. Verify ALL affected outputs, not just the first. One green check is not all green checks; validate every output surface the change can affect. Assume existing values are intentional — ask WHY before changing OR flagging one as a defect. Before changing or reporting a constant, limit, flag, cutoff, wording, or pattern, read nearby context and history, the CALLER's ordering, and 2+ sibling call sites of the same convention. A doc stating WHAT without WHY is missing rationale, not proof of a missing guard. Surface ambiguity before acting — don't pick silently. Multiple valid interpretations require an explicit question or stated assumption with risk. Assert the outcome your system owns, not the intermediate state your infrastructure owns. When verifying async work, assert the final business state — never the delivery/retry bookkeeping held in shared infrastructure that any co-running process can write. Such a check passes when run alone and flakes the moment anything else shares that infrastructure. Keep shared guidance role-relevant. Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.

Hookless Prompt Protocol Mirror (Auto-Synced)

Source: .claude/.ck.json + .claude/skills/shared/sync-inline-versions.md (:full blocks) + .claude/scripts/lib/hookless-prompt-protocol.cjs

[WORKFLOW-EXECUTION-PROTOCOL] [BLOCKING] Workflow Execution Protocol — MANDATORY IMPORTANT MUST CRITICAL. Do not skip for any reason.

Generic portability boundary: Reusable skills and protocol text stay project-neutral; project-specific conventions are discovered from docs/project-config.json and docs/project-reference/. Apply shared AI-SDD from shared/sdd-artifact-contract.md. Read docs/project-config.json and docs/project-reference/docs-index-reference.md, then open the project reference docs named there. For spec, test-case, behavior-change, public-contract, or docs/specs/ work, route through the local spec docs named by the docs index: feature-spec-reference.md, spec-system-reference.md, spec-principles.md, and workflow-spec-test-code-cycle-reference.md when specs/tests/code must stay synchronized. If either file or a required reference doc is missing or stale, auto-run $project-init (or the narrow lower-level route such as $project-config, $docs-init, $scan-all, or $scan --target=<key>) before ordinary project-specific work. Any supported AI tool may execute when this shared context and local docs are available.

1. DETECT: If the prompt starts with an explicit slash skill/workflow command, execute it directly. Otherwise match the prompt against the workflow catalog and skill list.
2. ANALYZE: Choose the best option: execute directly, invoke a skill, activate a standard workflow, or compose a custom step combination.
3. AUTO-SELECT: Pick the best option yourself. Do not ask the user to choose between direct execution, skill, standard workflow, or custom workflow.
4. ACTIVATE: For a selected workflow, call $start-workflow <workflowId>; for a selected skill, invoke that skill; for a custom workflow, sequence custom steps directly; for direct execution, proceed with the task.
5. CREATE TASKS: task tracking for ALL workflow/skill/custom steps before execution when the selected path has multiple steps.
6. PARALLELIZE: Before executing the task list, tag each task PAR (independent inputs + write set disjoint from every other PAR task) or SEQ (name the blocking dependency), group PAR tasks into waves, declare the wave plan, and spawn each wave's sub-agents in ONE message — all-return barrier per wave, fan-out one level deep unless a sub-agent's own definition authorizes further fan-out. Sequential-by-default is a defect when tasks are independent; do not parallelize shared write targets, output-consuming tasks, trivial single-file work, ordering a skill or workflow explicitly fixes, or user-approval gates.
7. EXECUTE: Advance per the Workflow Step Advancement & Parallel Phases rule in your context instructions — model-driven; a sub-agent completion advances a step identically to an inline call; a parallel-phase group is an all-return barrier (advance only after ALL members return, never serialize it)

Shared AI-SDD Protocol Markers

Source: .claude/skills/shared/sync-inline-versions.md

SYNC:ai-sdd-artifact-contract

AI-SDD Artifact Contract — Shared spec-driven development rules stay portable and source-owned.

1. Keep reusable AI-SDD principles in .claude; put repository-specific paths, commands, owners, products, and formats in project config/reference docs.
2. Preserve cycle: spec -> plan -> tasks -> implement -> verify -> update spec/docs.
3. Trace every requirement or invariant through decision, task, TC/test, source evidence, and docs/spec update.
4. Treat code-to-spec extraction as reference-only until accepted by the canonical spec owner.
5. Any supported AI tool may plan, implement, review, or verify with synced context; using multiple tools is optional.
6. Update .claude source first, then sync generated mirrors; do not manually edit .agents, .codex, or AGENTS.md. — why: mirrors are generated artifacts; hand-edits are overwritten on the next sync
7. If docs/project-config.json, root instruction files, or a required project-reference doc is missing or stale, auto-run $project-init or the narrow lower-level route before ordinary project-specific work.

Active reference: shared/sdd-artifact-contract.md in the active skills root.

SYNC:ai-sdd-artifact-contract:reminder

• MANDATORY Apply shared/sdd-artifact-contract.md; keep reusable AI-SDD in .claude and local rules in project docs.
• MANDATORY Code-to-spec extraction is reference-only until canonical acceptance; any supported AI tool may execute with synced context.
• MANDATORY Update .claude source before syncing generated mirrors; do not manually edit .agents, .codex, or AGENTS.md.
• MANDATORY Missing or stale project config, root instruction files, or required reference docs route project-specific work through $project-init or the narrow setup route automatically. [TASK-PLANNING] [MANDATORY] BEFORE executing any workflow or skill step, create/update task tracking for all planned steps, then keep it synchronized as each step starts/completes.

[LESSON-LEARNED-REMINDER] [BLOCKING] Task Planning & Continuous Improvement — MANDATORY. Do not skip.

Break work into small tasks (task tracking) before starting. Add final task: "Analyze AI mistakes & lessons learned".

Extract lessons — ROOT CAUSE ONLY, not symptom fixes:

1. Name the FAILURE MODE (reasoning/assumption failure), not symptom — "assumed API existed without reading source" not "used wrong enum value".
2. Generality test: does this failure mode apply to ≥3 contexts/codebases? If not, abstract one level up.
3. Write as a universal rule — strip project-specific names/paths/classes. Useful on any codebase.
4. Consolidate: multiple mistakes sharing one failure mode → ONE lesson.
5. Recurrence gate: "Would this recur in future session WITHOUT this reminder?" — No → skip $learn.
6. Auto-fix gate: "Could $code-review/$code-simplifier/$security-review/$lint catch this?" — Yes → improve review skill instead.
7. BOTH gates pass → ask user to run $learn. [CRITICAL-THINKING-MINDSET] Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination principle: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination. AI Attention principle (Primacy-Recency): Put the 3 most critical rules at both top and bottom of long prompts/protocols so instruction adherence survives long context windows. Goal-driven execution: Define success criteria first, loop until verified, and stop only when observable checks pass. Tests verify intent: Tests must protect business rules/invariants and fail when the protected intent breaks, not only mirror current behavior.

Common AI Mistake Prevention (System Lessons)

• Re-read files after context compaction. Edit requires prior Read in same context; compaction wipes read state. Re-read before editing.
• Grep for old terms after bulk replacements. AI over-trusts find/replace completeness. Grep full repo after bulk edits for missed refs in docs/configs/catalogs.
• Check downstream references before deleting. Deletions cascade doc/code staleness. Map referencing files before removal.
• After memory loss, check existing state before creating new. Compaction wipes prior-work memory. Query current state to resume — never blindly duplicate.
• Verify AI-generated content against actual code. AI hallucinates APIs, class names, method signatures. Grep to confirm existence before documenting/referencing.
• Trace full dependency chain after edits. Changing a definition misses downstream consumers. Trace the full chain.
• When renaming, grep ALL consumer file types. Some file types silently ignore missing refs (no compile error). Search code, templates, configs, generated files.
• Trace ALL code paths when verifying correctness. Code existing ≠ code executing. Trace early exits, error branches, conditional skips — not just happy path.
• Update docs that embed canonical data when source changes. Docs inlining derived data (workflows, schemas, configs) go stale silently. Update all embedding docs alongside source.
• Verify sub-agent results after context recovery. Background agents may finish while parent compacted — grep-verify output, don't trust assumed completion.
• Cross-check full target list against sub-agent assignments. Parallel sub-agents by category miss boundary items. Reconcile union of assignments against target list before proceeding.
• Sub-agents inherit knowledge only from their agent .md definition — use custom agent types, not built-in Explore. Tool adoption = permission + knowledge + enforcement (numbered workflow step).
• Persist sub-agent findings incrementally, not as a final batch. Long sub-agents hit cutoffs before final write — findings lost. Instruct append-per-section to report file.
• When debugging, ask "whose responsibility?" before fixing. Trace caller (wrong data) vs callee (wrong handling). Fix at responsible layer — never patch symptom site.
• Test failure → record a provisional verdict before trace/edit, then investigate. Use the full five-way taxonomy: SOURCE-WRONG (production violates intent), TEST-WRONG (assertion/setup is stale), TEST-NOT-OPTIMAL (valid but fragile or low-signal test), ENVIRONMENT-BLOCKED (external state prevents a verdict), or AMBIGUOUS (intent/evidence cannot choose safely). Then trace root cause and triangulate against the governing spec (docs/specs/** if one exists) AND source. NEVER weaken an assertion, add a skip, relax a timeout, or change source merely to force green.
• Grep ALL removed names after extraction/refactoring. Primary file "done" ≠ secondary files clean. Grep entire scope for every removed symbol before declaring complete.
• Assume existing values are intentional — ask WHY before changing OR flagging one as a defect. Pattern-matching as "wrong" skips context. Before changing or reporting any constant/limit/flag/cutoff: read comments, git blame, the CALLER's ordering (the guarantee that makes the value correct usually lives in code running immediately BEFORE the cited line), and 2+ sibling call sites of the same convention. A doc stating WHAT without WHY is missing rationale, not proof of a missing guard — and in a validation pass, an accurate file:line citation proves the transcription, never the defect.
• Verify ALL affected outputs, not just the first. One build green ≠ all green. Multi-stack changes (backend/frontend/tests/docs) require verifying EVERY output.
• Evaluate fit before copying a nearby pattern. Closest example ≠ matching preconditions — verify the new context shares the same constraints, base classes, scope, lifetime.
• Holistic-first debugging — resist nearest-attention trap. Don't dive into first plausible cause. List EVERY precondition (config, env vars, paths, DB, endpoints, creds, versions, DI, data). Verify each against evidence (grep/query — not reasoning). Ask "what would falsify this?" — if nothing, it's not a hypothesis. Most expensive failure: going deeper in "obvious" layer while bug sits in layer never questioned.
• Surgical changes — apply the diff test (context-aware). Two modes: (1) Bug fix → every line traces to the bug; no restyling; orphan cleanup only for imports YOUR changes made unused. (2) Review/enhancement → implement improvements AND announce as "Enhancement beyond main request: [what]". Never silently scope-creep. Diff test: "Would this line exist if I wasn't asked to do X?" — if no, delete or announce.
• Surface ambiguity before coding — don't pick silently. Multiple valid interpretations → present each with effort: "[Request] could mean (1) [N h], (2) [N h]. Which matters?" List scope/format/volume/constraints assumptions first. If simpler path exists, say so. Never silently pick.
• [MANDATORY FIRST ACTION] ALWAYS activate a suitable skill or workflow BEFORE responding. Match task against workflow catalog + skill list; invoke via skill invocation or $start-workflow <workflowId>. NEVER answer or write code before checking. Skip = protocol violation.
• Why-Review adversarial mindset — apply when reviewing any plan, decision, or design. Default SKEPTIC not VALIDATOR: steel-man a rejected alternative, invert each stated reason ("what does it sacrifice?"), stress-test top 2-3 assumptions, run pre-mortem ("ships, fails in 3 months — what breaks?"), surface 1-2 alternatives author missed. Section presence ≠ quality; quality = causal reasoning + concrete mitigations + evidence, not "it's better" or "monitor closely".
• Front-load report-write in sub-agent prompts for large reviews. Many-file sub-agents hit budget before final write — findings lost. Design prompts so: (1) report-write is first explicit deliverable, (2) append per-file/section (not batched), (3) scope bounded so reads don't exhaust budget. Truncated mid-sentence with no report file → spawn narrower scope, don't retry same prompt.
• After context compaction, re-verify all prior phase outcomes before continuing. Summaries describe intent, not environment state (git index, filesystem, processes). On resume, FIRST audit: git status, re-read modified files, verify filesystem. Every "completed" claim is an untested hypothesis until evidence confirms.
• OOM/memory: check row count before row size. Triage: (1) Unbounded query — no DB filter for trigger? Push filter to DB; eliminates OOM. (2) Large rows? Projection reduces proportionally. Row reduction > projection in ROI.
• Assert the outcome your system OWNS, never the intermediate state your INFRASTRUCTURE owns. When testing anything asynchronous (queue/broker delivery, retries, background jobs, caches, replication), assert the final business/entity state. NEVER assert the delivery bookkeeping — consume/send status, attempt counts, last-error, row existence or counts in a broker, scheduler, or outbox/inbox table. That bookkeeping lives in shared infrastructure that ANY co-running process (a peer worker, a second replica, a leftover local container) can write, usually under a deterministic shared key, so the assertion silently tests the developer's environment instead of the system: green when run alone, flaky the instant anything else shares that broker + database. Gate question

…(truncated)