Business Analyst

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.

Quick Summary

Goal: Refine requirements into actionable user stories with BDD acceptance criteria and business rule traceability.

Workflow:

1. Extract Business Rules — Locate feature docs, extract BR-{MOD}-XXX rules, reference in stories
2. Investigate Entities — Load feature docs, extract domain model and query patterns
3. Write User Stories — Use "As a / I want / So that" format, validate with INVEST criteria
4. Define Acceptance Criteria — BDD format (GIVEN/WHEN/THEN), gap analysis for missing scenarios

Key Rules:

• Always reference existing business rules from docs/specs/ before creating new ones
• User stories must pass INVEST criteria (Independent, Negotiable, Valuable, Estimable, Small, Testable)
• Include entity context and related domain model in every story
• MUST ATTENTION include story_points and complexity in all PBI/story outputs
• [BLOCKING] Tech-agnostic output: story/acceptance-criteria prose follows docs/project-reference/spec-principles.md §3 — no framework/product/language/design-pattern names; source paths, class names, and test identifiers appear ONLY in evidence fields (**Evidence**, IntegrationTest, [Source:]), frontmatter, and Mermaid.

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

• docs/project-reference/domain-entities-reference.md — Domain entity catalog, relationships, cross-service sync (read when task involves business entities/models)

Business Analyst Assistant

Help Business Analysts refine requirements into actionable user stories with clear acceptance criteria using BDD format.

Business Rules Extraction (Project Domain)

When refining domain-related PBIs, automatically extract and reference existing business rules.

Step 1: Locate Related Feature Docs

Dynamic Discovery:

1. Run: Glob("docs/specs/{module}/*.md") for feature docs
2. Or: Glob("docs/specs/{module}/**/*.md") for nested features

From PBI frontmatter or module detection:

1. Check module field
2. Identify related feature from related_features list
3. Read discovered feature documentation

Step 2: Extract Existing Business Rules

From feature doc "Business Rules" section:

• Format: BR-{MOD}-XXX: Description
• Example: BR-GRO-001: Goals must have measurable success criteria
• Note conflicting rules if found

Step 3: Add to User Story

Include section:

## Related Business Rules

**From Feature Docs:**

- BR-GRO-001: Goals must have measurable success criteria
- BR-GRO-005: Only goal owner and manager can edit progress

**New Business Rules (if applicable):**

- BR-GRO-042: {New rule description}

**Conflicts/Clarifications:**

- {Note any conflicts with existing rules}

Token Budget

Target 8-12K tokens total (validated decision: prefer completeness):

• Module README: 2K tokens
• Full feature doc sections: 3-5K tokens per feature
• Multi-module support: Load all detected modules (may increase total)

Entity Domain Investigation

When refining domain-related PBIs, investigate related entities using feature docs.

Step 1: Load Feature Doc

Glob("docs/specs/{module}/*.md")

Select file matching feature from PBI context.

Step 2: Extract Domain Model

From ## Domain Model section (Section 5):

• Entity inheritance: Entity : BaseClass
• Property types: Property: Type
• Navigation: NavigationProperty: List<Related>
• Computed: Property: Type (computed: logic)

Step 3: Correlate with Codebase

From ## File Locations section:

1. Read entity source file
2. Verify properties match documentation
3. Note any undocumented properties (flag for doc update)

Step 4: Identify Query Patterns

From ## Key Expressions section:

• Static expressions for common queries
• Validation rules with BR-* references

Step 5: Add to User Story

Include entity context:

## Entity Context

**Primary:** {Entity} - {description}
**Related:** {Entity1}, {Entity2}
**Key Queries:** {ExpressionName}
**Source:** {path}

This ensures implementation uses correct entities and patterns.

Core Capabilities

1. Requirements Refinement

• Transform vague requests into specific requirements
• Identify missing information and ambiguities
• Document assumptions and constraints

2. User Story Writing

Format

As a {user role/persona}
I want {goal/desire}
So that {benefit/value}

INVEST Criteria

• Independent: No dependencies on other stories
• Negotiable: Not a contract, can be refined
• Valuable: Delivers user value
• Estimable: Can be sized
• Small: Fits in one sprint
• Testable: Has clear acceptance criteria

3. Acceptance Criteria (BDD Format)

Scenario: {Descriptive title}
  Given {precondition/context}
    And {additional context}
  When {action/trigger}
    And {additional action}
  Then {expected outcome}
    And {additional verification}

For Project Domain:

1. Reference existing test case patterns from feature docs
2. Use TC-{FEATURE}-{NNN} format (e.g., TC-GM-001)
3. Include Evidence field: [Source: namespace/service/id] abstract-anchor format — never physical code coordinates or repository-root paths (stack-portable; see shared/tc-format.md)
4. Example from InvoiceManagement feature:

   TC-INV-001: Create invoice with valid data
   GIVEN user has permission to create invoices
   WHEN user submits invoice form with all required fields
   THEN invoice is created and appears in invoice list
   Evidence: [Source: operation/sales/CreateInvoice], [Source: component/sales/Invoice]
   

4. Business Rules Documentation

Rule Format

BR-{MOD}-{NNN}: {Rule name}
IF {condition}
THEN {action/result}
ELSE {alternative}
Evidence: [Source: rule/{service}/{RuleName}]

5. Gap Analysis

• Current state vs desired state mapping
• Identify process improvements
• Document integration requirements

Context Validation (Project Domain)

Before finalizing user story:

Cross-Reference Check

• Business rules don't conflict with existing BR-{MOD}-XXX rules
• Test case format matches existing TC-{FEATURE}-{NNN} patterns
• Entity names match those in feature docs
• Evidence format follows the abstract-anchor convention ([Source: namespace/service/id]) — no physical code coordinates or repository-root paths

Documentation Links

Add to user story:

## Reference Documentation

- Feature Doc: `docs/specs/{module}/{feature}.md`
- Related Entities: `docs/specs/{module}/*.md`
- Existing Test Cases: See feature doc Section 8 (Test Specifications)

If conflicts found, note in "Unresolved Questions" section.

Workflow Integration

Refining Ideas to PBIs

When user runs $refine {idea-file}:

1. Read idea artifact
2. Check for module field in frontmatter
3. Load business feature context if domain-related
4. Extract requirements
5. Extract existing BRs from feature docs
6. Identify acceptance criteria using TC patterns
7. Create PBI with GIVEN/WHEN/THEN format
8. Save to team-artifacts/pbis/

Creating User Stories

When user runs $story {pbi-file}:

1. Read PBI
2. Break into vertical slices
3. Write user stories with AC
4. Ensure INVEST criteria met
5. Include related BRs
6. Save to team-artifacts/pbis/stories/

Templates

User Story Template

---
id: US-{YYMMDD}-{NNN}
parent_pbi: '{PBI-ID}'
persona: '{Persona name}'
priority: P1 | P2 | P3
story_points: 1 | 2 | 3 | 5 | 8 | 13 | 21
complexity: Low | Medium | High | Very High
status: draft | ready | in_progress | done
module: '' # Project module (if applicable)
---

# User Story

**As a** {user role}
**I want** {goal}
**So that** {benefit}

## Acceptance Criteria

### Scenario 1: {Happy path title}

```gherkin
Given {context}
When {action}
Then {outcome}
```

### Scenario 2: {Edge case title}

```gherkin
Given {context}
When {action}
Then {outcome}
```

### Scenario 3: {Error case title}

```gherkin
Given {context}
When {invalid action}
Then {error handling}
```

## Related Business Rules

<!-- Auto-extracted from feature docs -->

- BR-{MOD}-XXX: {Description}

## Out of Scope

- {Explicitly excluded item}

## Notes

- {Implementation guidance}

Elicitation Techniques

5 Whys

1. Why? → {answer}
2. Why? → {answer}
3. Why? → {answer}
4. Why? → {answer}
5. Why? → {root cause}

SMART Criteria for Requirements

• Specific: Clear and unambiguous
• Measurable: Can verify completion
• Achievable: Technically feasible
• Relevant: Aligned with business goals
• Time-bound: Has a deadline or sprint

Role Context (path→role, canonical)

Applies to Writes under team-artifacts/pbis/ and team-artifacts/pbis/stories/.

• Active Role: business-analyst · Skill: business-analyst · Naming: {YYMMDD}-ba-{type}-{slug}.md
• Path team-artifacts/pbis/ → Template .claude/docs/team-artifacts/templates/pbi-template.md · Context: PBI CREATION — GIVEN/WHEN/THEN format required, INVEST criteria, numeric priority.
• Path team-artifacts/pbis/stories/ → Template .claude/docs/team-artifacts/templates/user-story-template.md · Context: USER STORY — As a... I want... So that... format, 3+ scenarios per story.
• Quality checklist: - [ ] User story format correct · - [ ] 3+ scenarios (positive, negative, edge) · - [ ] GIVEN/WHEN/THEN format · - [ ] INVEST criteria met

Output Conventions

File Naming

{YYMMDD}-ba-story-{slug}.md
{YYMMDD}-ba-requirements-{slug}.md

Requirement IDs

• Functional: FR-{MOD}-{NNN} (e.g., FR-GROW-001)
• Non-Functional: NFR-{MOD}-{NNN}
• Business Rule: BR-{MOD}-{NNN}

AC IDs

• AC-{NNN} per story/PBI

Test Case IDs (Project)

• TC-{FEATURE}-{NNN} (e.g., TC-GM-001)

Quality Checklist

Before completing BA artifacts:

• User story follows "As a... I want... So that..." format
• At least 3 scenarios: happy path, edge case, error case
• All scenarios use GIVEN/WHEN/THEN
• Out of scope explicitly listed
• Story meets INVEST criteria
• No solution-speak in requirements (only outcomes)
• Existing BRs referenced (if domain-related)
• TC format matches feature docs (if domain-related)
• Entity names use domain vocabulary

Post-Refinement Validation (MANDATORY)

Every refinement must end with a validation interview.

After completing user story or PBI refinement, conduct validation to:

1. Surface hidden assumptions
2. Confirm critical decisions
3. Identify potential concerns
4. Brainstorm with user on alternatives

Validation Interview Process

Use ask the user directly tool with 3-5 questions:

Document Validation Results

Add to user story/PBI:

## Validation Summary

**Validated:** {date}

### Confirmed Decisions

- {decision}: {user choice}

### Concerns Raised

- {concern}: {resolution}

### Action Items

- [ ] {follow-up if any}

When to Flag for Stakeholder Review

• Decision impacts other teams
• Scope change requested
• Technical risk identified
• Business rule conflict detected

This step is NOT optional - always validate before marking refinement complete.

[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.

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.

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.

Sequential Thinking Protocol — Structured multi-step reasoning for complex/ambiguous work. Use when planning, reviewing, debugging, or refining ideas where one-shot reasoning is unsafe.

Trigger when: complex problem decomposition · adaptive plans needing revision · analysis with course correction · unclear/emerging scope · multi-step solutions · hypothesis-driven debugging · cross-cutting trade-off evaluation.

Format (explicit mode — visible thought trail):

1. Thought N/M: [aspect] — one aspect per thought, state assumptions/uncertainty
2. Thought N/M [REVISION of Thought K]: ... — when prior reasoning invalidated; state Original / Why revised / Impact
3. Thought N/M [BRANCH A from Thought K]: ... — explore alternative; converge with decision rationale
4. Thought N/M [HYPOTHESIS]: ... then [VERIFICATION]: ... — test before acting
5. Thought N/N [FINAL] — only when verified, all critical aspects addressed, confidence >80%

Mandatory closers: Confidence % stated · Assumptions listed · Open questions surfaced · Next action concrete.

Stop conditions: confidence <80% on any critical decision → escalate by asking the user directly · ≥3 revisions on same thought → re-frame the problem · branch count >3 → split into sub-task.

Implicit mode: apply methodology internally without visible markers when adding markers would clutter the response (routine work where reasoning aids accuracy).

Deep-dive: see $sequential-thinking skill (.claude/skills/sequential-thinking/SKILL.md) for worked examples (API design, debugging, architecture), advanced techniques (spiral refinement, hypothesis testing, convergence), and meta-strategies (uncertainty handling, revision cascades).

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 sequential-thinking — multi-step Thought N/M, REVISION/BRANCH/HYPOTHESIS markers, confidence % closer; see $sequential-thinking skill.

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.

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

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

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

• Critical Thinking: traced file:line proof per claim, confidence >80% to act, never guess.

• Sequential Thinking: multi-step Thought N/M with REVISION/BRANCH/HYPOTHESIS markers and confidence closer.

• MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using task tracking BEFORE starting

• MANDATORY IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code

• MANDATORY IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act)

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

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

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 for every assertion: "would this hold no matter WHICH process did the work?" — if no, assert the converged data state instead. Corollary: process-local fault injection and in-process telemetry cannot gate work any process may perform — use them as stress amplifiers (arm → bounded window → disarm → assert convergence), never as preconditions.
• Keep domain concepts out of generic/shared/infrastructure layers. Reusable layer (shared library, framework, infra module) must reference NO consumer-specific domain concept — tenant/customer/product IDs, business entities, feature rules. Leak compiles + runs → passes review silently while coupling the "reusable" layer to one consumer. Keep shared type domain-free; push domain fields/logic down into the consumer via subclass/composition. — why: a layer coupled to one consumer's domain is no longer reusable.