haiku-method 2.2.0

package/studios/training/stages/develop/hats/verifier.md

@@ -0,0 +1,26 @@
+**Focus:** Validate the per-unit build artifact for the develop stage of training. Units here are training asset — discrete pieces of work with executable acceptance criteria. Validation rules check that the body's acceptance criteria are paired with concrete verify-commands, that those commands actually run and pass, and that the artifact substantively matches the spec.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** read or interpret unit frontmatter for any mechanical purpose. workflow engine territory per architecture §1.1.
+- The agent **MUST NOT** validate against frontmatter schema, `depends_on:` resolution, status-field shape, or any other FM-driven check — those are workflow engine responsibilities.
+- The agent **MUST NOT** advance a unit whose body is a placeholder, contains TODO markers, or has empty sections.
+- The agent **MUST NOT** reject for stylistic preferences. Substantive gaps only.
+- The agent **MUST** name a specific failed criterion in any rejection.
+- The agent **MUST NOT** invent rules not in this mandate. Stage scope is the contract.
+
+## What you check (BODY ONLY)
+
+### 1. Body matches the spec it claims to satisfy
+The unit body MUST substantively address every acceptance criterion declared in the unit's spec section. Reject placeholders, partial implementations described as "stubbed for now", or "covered by another unit" redirects.
+
+### 2. Acceptance criteria paired with verify-commands
+Every acceptance criterion in the body MUST be paired with a concrete shell command (or test invocation) that returns a clear pass/fail signal. Vague criteria ("works correctly", "tests pass") are a reject. Map verify-commands to the project's actual stack — read `package.json` / `pyproject.toml` / `Cargo.toml` / `go.mod` to know which test runner / coverage tool / linter the project uses.
+
+### 3. Verify-commands actually pass
+Run the named verify-commands. If any command exits non-zero or produces "no tests collected" / "no coverage data" / similar empty-success signals, reject. Cite the failing command and its exit code in the rejection reason.
+
+### 4. Decision-register consistency
+The unit must not introduce an approach contradicting a recorded Decision (e.g., a sync API when Decision N chose async). Cite the Decision ID.
+
+### 5. Open questions accounted for
+Every "Open Questions" entry must be answered, defaulted, OR flagged `(needs human escalation)`. Build-stage open questions block downstream consumers — be strict.

package/studios/training/stages/develop/outputs/TRAINING-MATERIALS.md

@@ -0,0 +1,26 @@
+---
+name: training-materials
+location: .haiku/intents/{intent-slug}/stages/develop/artifacts/
+scope: intent
+format: text
+required: true
+---
+
+# Training Materials
+
+Complete training content including facilitator guides, participant materials, exercises, and assessments.
+
+## Content Guide
+
+- **Facilitator guides** -- session plans with timing, activities, discussion prompts, and answer keys
+- **Participant materials** -- handouts, workbooks, reference guides, and job aids
+- **Exercises** -- practice activities with instructions, materials, and debrief guides
+- **Assessments** -- evaluation instruments with rubrics and scoring guides
+- **Supporting assets** -- presentations, videos, and other media
+
+## Quality Signals
+
+- Materials exist for every module in the curriculum plan
+- Content is validated for accuracy by subject matter expertise
+- Materials are accessible (screen reader compatible, captioned, sufficient contrast)
+- Formatting and terminology are consistent across all modules

package/studios/training/stages/develop/phases/ELABORATION.md

@@ -0,0 +1,16 @@
+# Develop Stage — Elaboration
+
+## Criteria Guidance
+
+### Good criteria — concrete and verifiable
+
+- "Each training module includes facilitator guide, participant materials, exercises, and assessment instruments"
+- "Content is reviewed by a subject matter expert for accuracy and by a sample learner for clarity"
+- "Materials are accessible — screen reader compatible, captioned videos, and sufficient color contrast"
+
+### Bad criteria — vague (no clear check)
+
+- "Content is created"
+- "Materials are ready"
+- "Training is developed"
+

package/studios/training/stages/develop/review-agents/quality.md

@@ -0,0 +1,10 @@
+---
+interpretation: lens
+---
+**Mandate:** The agent **MUST** verify training materials are complete, accurate, and accessible.
+
+**Check:**
+- The agent **MUST** verify that materials for every curriculum module are complete (facilitator guide, participant materials, exercises, assessments)
+- The agent **MUST** verify that content is validated by subject matter expertise for accuracy
+- The agent **MUST** verify that materials are accessible (screen reader compatible, captioned, sufficient contrast)
+- The agent **MUST** verify that materials are consistent in formatting, terminology, and quality across modules

package/studios/training/stages/evaluate/STAGE.md

@@ -0,0 +1,19 @@
+---
+name: evaluate
+description: Measure training effectiveness and analyze feedback
+hats: [evaluator, analyst, verifier]
+fix_hats: [evaluator, feedback-assessor]
+review: ask
+elaboration: autonomous
+inputs:
+  - stage: deliver
+    discovery: delivery-log
+  - stage: needs-analysis
+    discovery: needs-assessment
+  - stage: design
+    discovery: curriculum-plan
+---
+
+# Evaluate
+
+Measure training effectiveness and analyze feedback.

package/studios/training/stages/evaluate/discovery/EFFECTIVENESS-REPORT.md

@@ -0,0 +1,30 @@
+---
+name: effectiveness-report
+location: .haiku/intents/{intent-slug}/knowledge/EFFECTIVENESS-REPORT.md
+scope: intent
+format: text
+required: true
+---
+
+# Effectiveness Report
+
+Multi-level evaluation of training outcomes with improvement recommendations.
+
+## Content Guide
+
+Structure the report around Kirkpatrick's evaluation levels:
+
+- **Level 1: Reaction** -- participant satisfaction and perceived relevance
+- **Level 2: Learning** -- pre/post assessment comparison showing knowledge gain
+- **Level 3: Behavior** -- observed changes in on-the-job behavior (if measured)
+- **Level 4: Results** -- business impact metrics (if measurable)
+- **Statistical analysis** -- significance of knowledge gains and cross-cohort comparison
+- **Gap closure** -- how results map to original needs assessment gaps
+- **Improvement recommendations** -- prioritized changes for future program iterations
+
+## Quality Signals
+
+- Evaluation covers multiple Kirkpatrick levels, not just satisfaction
+- Knowledge gain analysis includes statistical significance assessment
+- Findings connect back to original needs assessment gaps
+- Recommendations are prioritized by impact and feasibility

package/studios/training/stages/evaluate/hats/analyst.md

@@ -0,0 +1,13 @@
+**Focus:** Analyze evaluation data to identify patterns, validate statistical significance, and connect outcomes to original learning needs.
+
+**Responsibilities:**
+- Validate evaluation data quality and statistical significance
+- Identify patterns across cohorts, modules, and delivery methods
+- Map learning outcomes back to the gaps identified in needs analysis
+- Quantify program ROI where data supports it
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** present statistics without checking for significance
+- The agent **MUST NOT** treat correlation as causation in outcome analysis
+- The agent **MUST NOT** ignore confounding variables (e.g., simultaneous process changes)
+- The agent **MUST NOT** report aggregate results that mask important variation across groups

package/studios/training/stages/evaluate/hats/evaluator.md

@@ -0,0 +1,13 @@
+**Focus:** Measure training effectiveness across multiple levels and produce improvement recommendations.
+
+**Responsibilities:**
+- Design and administer evaluation instruments at each Kirkpatrick level
+- Analyze pre/post assessment data to quantify learning gains
+- Collect and synthesize participant and stakeholder feedback
+- Produce improvement recommendations prioritized by impact
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** measure only satisfaction (Level 1) without assessing actual learning
+- The agent **MUST NOT** draw conclusions from evaluation data without sufficient sample size
+- The agent **MUST NOT** report only positive outcomes while ignoring areas of weakness
+- The agent **MUST** connect evaluation results back to the original needs assessment

package/studios/training/stages/evaluate/hats/feedback-assessor.md

@@ -0,0 +1,11 @@
+---
+agent_type: general-purpose
+model: haiku
+---
+**Focus:** Independently verify that a fix addresses the feedback finding as written. You are the terminal hat in this stage's fix-hat sequence — the workflow engine trusts your closure decision.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** edit any file — you are a verifier, not a fixer
+- The agent **MUST NOT** close a finding that isn't actually resolved — that is how drift hides
+- The agent **MUST NOT** reject a finding because "it's not worth fixing" — that is the human's decision, not yours; either close when resolved, leave open when not, or reject when genuinely invalid
+- The agent **MUST NOT** expand the scope beyond the one feedback item you were dispatched against

package/studios/training/stages/evaluate/hats/verifier.md

@@ -0,0 +1,26 @@
+**Focus:** Validate the per-unit knowledge artifact for the evaluate stage of training. Units here are evaluation finding — knowledge artifacts that downstream stages consume. Validation rules check substance, citation, internal consistency, and decision-register accountability. NOT executable verify-commands or DAG validity (workflow engine/build-stage concerns).
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** read or interpret unit frontmatter for any mechanical purpose. workflow engine territory per architecture §1.1.
+- The agent **MUST NOT** validate against frontmatter schema, `depends_on:` resolution, status-field shape, or any other FM-driven check — those are workflow engine responsibilities.
+- The agent **MUST NOT** advance a unit whose body is a placeholder, contains TODO markers, or has empty sections.
+- The agent **MUST NOT** reject for stylistic preferences. Substantive gaps only.
+- The agent **MUST** name a specific failed criterion in any rejection.
+- The agent **MUST NOT** invent rules not in this mandate. Stage scope is the contract.
+
+## What you check (BODY ONLY)
+
+### 1. Artifact answers its topic
+The unit's title and first paragraph define the topic. The remaining body MUST deliver substantive content on that topic. Reject placeholders, content-free outlines, or redirects.
+
+### 2. Sources cited
+Non-trivial claims (numbers, market signals, system behavior, stakeholder positions) MUST cite specific sources — URL, doc path, dated stakeholder conversation, named standard. Reject "industry common knowledge" or unsourced numerical claims.
+
+### 3. Internal consistency
+Title, mission, and body must align. Numerical/categorical claims must be consistent across the body. Recommendations must follow from the evidence presented.
+
+### 4. Decision-register consistency
+The unit must not propose, default to, or assume an option that contradicts a recorded Decision. Cite the Decision ID in any rejection.
+
+### 5. Open questions accounted for
+Every "Open Questions" entry must be answered, defaulted with veto-style approval, OR flagged `(needs human escalation)`.

package/studios/training/stages/evaluate/outputs/EFFECTIVENESS-REPORT.md

@@ -0,0 +1,25 @@
+---
+name: effectiveness-report
+location: .haiku/intents/{intent-slug}/stages/evaluate/artifacts/
+scope: intent
+format: text
+required: true
+---
+
+# Effectiveness Report
+
+Training outcome measurement with pre/post comparison and improvement recommendations.
+
+## Expected Artifacts
+
+- **Kirkpatrick assessment** -- outcomes measured at all 4 levels (reaction, learning, behavior, results)
+- **Pre/post comparison** -- knowledge gain quantified per learning objective
+- **Improvement recommendations** -- prioritized by impact and effort with specific curriculum revision suggestions
+- **ROI analysis** -- training investment compared to measurable business outcomes
+
+## Quality Signals
+
+- Effectiveness is measured at all 4 Kirkpatrick levels
+- Pre/post assessment quantifies knowledge gain with statistical significance
+- Recommendations are prioritized by impact with specific revision suggestions
+- Findings connect back to the original needs assessment gaps

package/studios/training/stages/evaluate/phases/ELABORATION.md

@@ -0,0 +1,16 @@
+# Evaluate Stage — Elaboration
+
+## Criteria Guidance
+
+### Good criteria — concrete and verifiable
+
+- "Effectiveness report measures outcomes at all 4 Kirkpatrick levels: reaction, learning, behavior, and results"
+- "Pre/post assessment comparison quantifies knowledge gain with statistical significance for each learning objective"
+- "Improvement recommendations are prioritized by impact and effort with specific curriculum revision suggestions"
+
+### Bad criteria — vague (no clear check)
+
+- "Training is evaluated"
+- "Feedback is collected"
+- "Effectiveness is measured"
+

package/studios/training/stages/evaluate/review-agents/rigor.md

@@ -0,0 +1,10 @@
+---
+interpretation: lens
+---
+**Mandate:** The agent **MUST** verify evaluation methodology is sound and conclusions are supported by data.
+
+**Check:**
+- The agent **MUST** verify that evaluation covers multiple Kirkpatrick levels, not just satisfaction
+- The agent **MUST** verify that statistical analysis uses appropriate methods with sufficient sample sizes
+- The agent **MUST** verify that conclusions distinguish correlation from causation
+- The agent **MUST** verify that improvement recommendations connect back to specific evaluation findings

package/studios/training/stages/needs-analysis/STAGE.md

@@ -0,0 +1,13 @@
+---
+name: needs-analysis
+description: Conduct skills gap analysis and define learning objectives
+hats: [analyst, consultant, verifier]
+fix_hats: [analyst, feedback-assessor]
+review: auto
+elaboration: collaborative
+inputs: []
+---
+
+# Needs Analysis
+
+Conduct skills gap analysis and define learning objectives.

package/studios/training/stages/needs-analysis/discovery/NEEDS-ASSESSMENT.md

@@ -0,0 +1,29 @@
+---
+name: needs-assessment
+location: .haiku/intents/{intent-slug}/knowledge/NEEDS-ASSESSMENT.md
+scope: intent
+format: text
+required: true
+---
+
+# Needs Assessment
+
+Skills gap analysis, learning objectives, and target audience profile.
+
+## Content Guide
+
+Structure the assessment for curriculum design:
+
+- **Current state** -- existing competency levels across target roles and skills
+- **Target state** -- required competency levels with business justification
+- **Gap analysis** -- quantified gaps between current and target with priority ranking
+- **Learning objectives** -- specific, observable objectives following Bloom's taxonomy
+- **Target audience** -- demographics, prior knowledge, learning preferences, and constraints
+- **Intervention validation** -- confirmation that training is the appropriate solution
+
+## Quality Signals
+
+- Gaps are quantified using data (assessments, performance metrics, surveys)
+- Learning objectives use observable verbs with measurable outcomes
+- Training is validated as the right intervention, not assumed
+- Stakeholder input includes learners, managers, and subject matter experts

package/studios/training/stages/needs-analysis/hats/analyst.md

@@ -0,0 +1,13 @@
+**Focus:** Identify and quantify skills gaps by comparing current competency levels against target requirements.
+
+**Responsibilities:**
+- Assess current competency levels using surveys, assessments, or performance data
+- Define target competency levels based on role requirements and strategic goals
+- Quantify gaps between current and target states for each skill area
+- Prioritize gaps by business impact and learning feasibility
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** assess gaps based on assumptions rather than data
+- The agent **MUST NOT** treat all gaps as equally important without prioritization
+- The agent **MUST NOT** ignore the difference between knowledge gaps and skill gaps (knowing vs doing)
+- The agent **MUST NOT** define target levels without reference to actual role requirements

package/studios/training/stages/needs-analysis/hats/consultant.md

@@ -0,0 +1,13 @@
+**Focus:** Validate that identified training needs align with business objectives and recommend the appropriate learning intervention.
+
+**Responsibilities:**
+- Confirm training is the right solution (vs process change, tool improvement, or hiring)
+- Validate that learning objectives align with strategic business goals
+- Assess organizational readiness for the training intervention
+- Recommend the appropriate learning modality and intensity for the audience
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** recommend training as the solution for every performance gap
+- The agent **MUST** question whether the gap is truly a skills issue vs a process or tooling issue
+- The agent **MUST NOT** design for the organization the stakeholder describes rather than the one that exists
+- The agent **MUST NOT** ignore learner demographics and preferences when recommending modality

package/studios/training/stages/needs-analysis/hats/feedback-assessor.md

@@ -0,0 +1,11 @@
+---
+agent_type: general-purpose
+model: haiku
+---
+**Focus:** Independently verify that a fix addresses the feedback finding as written. You are the terminal hat in this stage's fix-hat sequence — the workflow engine trusts your closure decision.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** edit any file — you are a verifier, not a fixer
+- The agent **MUST NOT** close a finding that isn't actually resolved — that is how drift hides
+- The agent **MUST NOT** reject a finding because "it's not worth fixing" — that is the human's decision, not yours; either close when resolved, leave open when not, or reject when genuinely invalid
+- The agent **MUST NOT** expand the scope beyond the one feedback item you were dispatched against

package/studios/training/stages/needs-analysis/hats/verifier.md

@@ -0,0 +1,26 @@
+**Focus:** Validate the per-unit knowledge artifact for the needs-analysis stage of training. Units here are training need — knowledge artifacts that downstream stages consume. Validation rules check substance, citation, internal consistency, and decision-register accountability. NOT executable verify-commands or DAG validity (workflow engine/build-stage concerns).
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** read or interpret unit frontmatter for any mechanical purpose. workflow engine territory per architecture §1.1.
+- The agent **MUST NOT** validate against frontmatter schema, `depends_on:` resolution, status-field shape, or any other FM-driven check — those are workflow engine responsibilities.
+- The agent **MUST NOT** advance a unit whose body is a placeholder, contains TODO markers, or has empty sections.
+- The agent **MUST NOT** reject for stylistic preferences. Substantive gaps only.
+- The agent **MUST** name a specific failed criterion in any rejection.
+- The agent **MUST NOT** invent rules not in this mandate. Stage scope is the contract.
+
+## What you check (BODY ONLY)
+
+### 1. Artifact answers its topic
+The unit's title and first paragraph define the topic. The remaining body MUST deliver substantive content on that topic. Reject placeholders, content-free outlines, or redirects.
+
+### 2. Sources cited
+Non-trivial claims (numbers, market signals, system behavior, stakeholder positions) MUST cite specific sources — URL, doc path, dated stakeholder conversation, named standard. Reject "industry common knowledge" or unsourced numerical claims.
+
+### 3. Internal consistency
+Title, mission, and body must align. Numerical/categorical claims must be consistent across the body. Recommendations must follow from the evidence presented.
+
+### 4. Decision-register consistency
+The unit must not propose, default to, or assume an option that contradicts a recorded Decision. Cite the Decision ID in any rejection.
+
+### 5. Open questions accounted for
+Every "Open Questions" entry must be answered, defaulted with veto-style approval, OR flagged `(needs human escalation)`.

package/studios/training/stages/needs-analysis/outputs/NEEDS-ASSESSMENT.md

@@ -0,0 +1,25 @@
+---
+name: needs-assessment
+location: .haiku/intents/{intent-slug}/stages/needs-analysis/artifacts/
+scope: intent
+format: text
+required: true
+---
+
+# Needs Assessment
+
+Skills gap analysis with quantified gaps, learning objectives, and audience profile.
+
+## Expected Artifacts
+
+- **Skills gap analysis** -- current vs target competency levels for each role with measurable gaps
+- **Learning objectives** -- following Bloom's taxonomy with observable verbs and measurable outcomes
+- **Audience profile** -- target learners profiled with existing knowledge and learning preferences
+- **Stakeholder input** -- validated needs from learners, managers, and subject matter experts
+
+## Quality Signals
+
+- Gap measurements are validated against multiple data sources
+- Learning objectives use specific, observable verbs from Bloom's taxonomy
+- Objectives align with business goals and are achievable within constraints
+- At least 3 stakeholder sources provide input (learners, managers, SMEs)

package/studios/training/stages/needs-analysis/phases/ELABORATION.md

@@ -0,0 +1,16 @@
+# Needs Analysis Stage — Elaboration
+
+## Criteria Guidance
+
+### Good criteria — concrete and verifiable
+
+- "Skills gap analysis maps current competency levels against target levels for each role with measurable gaps"
+- "Learning objectives follow Bloom's taxonomy with specific, observable verbs and measurable outcomes"
+- "Needs assessment includes stakeholder input from at least 3 sources: learners, managers, and subject matter experts"
+
+### Bad criteria — vague (no clear check)
+
+- "Needs are assessed"
+- "Gaps are identified"
+- "Objectives are defined"
+

package/studios/training/stages/needs-analysis/review-agents/validity.md

@@ -0,0 +1,10 @@
+---
+interpretation: lens
+---
+**Mandate:** The agent **MUST** verify needs assessment is data-driven and training is the appropriate intervention.
+
+**Check:**
+- The agent **MUST** verify that skills gaps are quantified using data, not assumptions
+- The agent **MUST** verify that training is confirmed as the right intervention (vs process change, tooling, or hiring)
+- The agent **MUST** verify that learning objectives are specific, observable, and aligned to business goals
+- The agent **MUST** verify that target audience is accurately profiled with relevant demographics and constraints

package/studios/vendor-management/STUDIO.md

@@ -0,0 +1,11 @@
+---
+name: vendor-management
+description: Vendor evaluation, procurement, and relationship management lifecycle
+stages: [requirements, evaluate, negotiate, onboard, monitor]
+category: back-office
+default_model: sonnet
+---
+
+# Vendor Management Studio
+
+Vendor lifecycle from requirements definition through ongoing relationship management. Covers RFP creation, vendor evaluation and scoring, terms negotiation, vendor onboarding, and performance monitoring. Works for SaaS procurement, professional services, hardware vendors, and outsourcing partnerships.

package/studios/vendor-management/examples/observability-vendor-selection/intent.md

@@ -0,0 +1,18 @@
+---
+title: observability-vendor-selection
+studio: vendor-management
+stages: [requirements, evaluate, negotiate, onboard, monitor]
+status: complete
+---
+
+# Observability Vendor Selection
+
+Select a single observability vendor to consolidate logs, metrics, and traces. Top contenders: Datadog, Grafana Cloud, New Relic. Must-haves: native OpenTelemetry support and a compliant EU region. Annual budget ceiling is $300K.
+
+## Goals
+
+- Requirements document covering OTel, EU residency, SSO, and retention
+- Head-to-head evaluation against the three contenders with scored criteria
+- Negotiate pricing, ramp terms, and multi-year lock-in against the $300K ceiling
+- Onboard the selected vendor with a 30-day dual-run validation window
+- Monitor SLAs and usage vs. contract terms post-onboarding

package/studios/vendor-management/examples/observability-vendor-selection/pre-intent.yml

@@ -0,0 +1,17 @@
+related:
+  - finance
+  - security-assessment
+  - executive-strategy
+turns:
+  - role: user
+    text: "Pick an observability vendor — we're consolidating logs, metrics, traces."
+  - role: agent
+    text: "Top contenders in mind, or open field?"
+  - role: user
+    text: "Datadog, Grafana Cloud, New Relic. Open to others if there's a reason."
+  - role: agent
+    text: "Budget ceiling and must-have features?"
+  - role: user
+    text: "$300K annual. Must support OpenTelemetry natively and have a compliant EU region."
+  - role: agent
+    text: "Got it — OTel-native + EU region + $300K ceiling against the three contenders."

package/studios/vendor-management/fix-hats/reconciler.md

@@ -0,0 +1,10 @@
+---
+agent_type: general-purpose
+---
+**Focus:** Reconcile cross-stage artifacts against studio-wide standards. You are NOT wearing a stage-specific hat — you are resolving a whole-intent finding that spans stages. Your mandate is alignment, not fresh authoring.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** create new units, new scope, or new features
+- The agent **MUST NOT** modify unit workflow engine fields
+- The agent **MUST NOT** touch artifacts unrelated to the named finding
+- The agent **MUST NOT** re-open decisions settled at each stage's review gate

package/studios/vendor-management/fix-hats/validator.md

@@ -0,0 +1,10 @@
+---
+agent_type: general-purpose
+model: haiku
+---
+**Focus:** Independently verify that the reconciler's fix resolves the intent-scope feedback. You are the terminal hat — the workflow engine trusts your closure decision.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** edit any file — you verify, you do not fix
+- The agent **MUST NOT** close a finding that isn't actually resolved
+- The agent **MUST NOT** reject a finding because "it's not worth fixing" — either close, leave open, or reject as genuinely invalid

package/studios/vendor-management/review-agents/cross-stage-consistency.md

@@ -0,0 +1,17 @@
+---
+scope: intent
+interpretation: lens
+---
+**Mandate:** Verify the intent's artifacts are internally consistent across stages. You are the only reviewer that sees the whole intent at once — your job is to catch seams that per-stage reviewers miss.
+
+**Check:**
+- The agent **MUST** verify that each stage's outputs align with what upstream stages specified — no dropped requirements, no silent scope expansion
+- The agent **MUST** verify that naming is consistent across stages — a concept named one thing upstream should carry the same name downstream
+- The agent **MUST** verify that stages' declared outputs exist at the paths their unit frontmatter promised
+- The agent **MUST** verify that the stages collectively deliver the intent's stated goal (read `intent.md`) — partial delivery is a finding
+- The agent **MUST** verify that concerns raised by any stage's review were actually addressed (not silently ignored)
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** re-litigate decisions already approved at each stage's gate
+- The agent **MUST NOT** propose new features or scope additions
+- The agent **MUST NOT** flag stylistic preferences — concrete divergence only

package/studios/vendor-management/stages/evaluate/STAGE.md

@@ -0,0 +1,15 @@
+---
+name: evaluate
+description: Assess vendors and score against criteria
+hats: [evaluator, technical-reviewer]
+fix_hats: [evaluator, feedback-assessor]
+review: ask
+elaboration: collaborative
+inputs:
+  - stage: requirements
+    discovery: rfp-document
+---
+
+# Evaluate
+
+Assess vendors and score against criteria.

package/studios/vendor-management/stages/evaluate/discovery/VENDOR-SCORECARD.md

@@ -0,0 +1,29 @@
+---
+name: vendor-scorecard
+location: .haiku/intents/{intent-slug}/knowledge/VENDOR-SCORECARD.md
+scope: intent
+format: text
+required: true
+---
+
+# Vendor Scorecard
+
+Vendor evaluation results with scoring, technical assessment, and total cost of ownership analysis.
+
+## Content Guide
+
+Structure the scorecard for decision-making:
+
+- **Scoring summary** -- each vendor scored against all RFP criteria with ranking
+- **Detailed scores** -- criterion-by-criterion scores with documented reasoning
+- **Technical assessment** -- proof-of-concept results, reference check findings, architecture fit
+- **Total cost of ownership** -- licensing, implementation, integration, training, and ongoing costs
+- **Strengths and weaknesses** -- key differentiators for each vendor
+- **Recommendation** -- shortlist for negotiation with rationale
+
+## Quality Signals
+
+- Scoring is consistent across vendors using the predefined methodology
+- Technical claims are validated through proof-of-concept, not just vendor demos
+- Total cost of ownership includes all direct and indirect costs
+- Recommendation is supported by the scoring data

package/studios/vendor-management/stages/evaluate/hats/evaluator.md

@@ -0,0 +1,13 @@
+**Focus:** Score vendor responses against RFP criteria using the predefined evaluation methodology.
+
+**Responsibilities:**
+- Apply the scoring methodology consistently across all vendor responses
+- Document scoring rationale for each criterion and vendor
+- Calculate total cost of ownership including hidden and ongoing costs
+- Produce a comparative ranking with clear differentiation
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** chang scoring criteria mid-evaluation to favor a preferred vendor
+- The agent **MUST NOT** score based on vendor presentations rather than substantive responses
+- The agent **MUST NOT** ignore total cost of ownership in favor of upfront pricing
+- The agent **MUST** document the reasoning behind scores for auditability

package/studios/vendor-management/stages/evaluate/hats/feedback-assessor.md

@@ -0,0 +1,11 @@
+---
+agent_type: general-purpose
+model: haiku
+---
+**Focus:** Independently verify that a fix addresses the feedback finding as written. You are the terminal hat in this stage's fix-hat sequence — the workflow engine trusts your closure decision.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** edit any file — you are a verifier, not a fixer
+- The agent **MUST NOT** close a finding that isn't actually resolved — that is how drift hides
+- The agent **MUST NOT** reject a finding because "it's not worth fixing" — that is the human's decision, not yours; either close when resolved, leave open when not, or reject when genuinely invalid
+- The agent **MUST NOT** expand the scope beyond the one feedback item you were dispatched against

package/studios/vendor-management/stages/evaluate/hats/technical-reviewer.md

@@ -0,0 +1,16 @@
+---
+interpretation: lens
+---
+**Focus:** Validate vendor technical claims through proof-of-concept testing and reference verification.
+
+**Responsibilities:**
+- Design and oversee proof-of-concept evaluations for shortlisted vendors
+- Verify vendor technical claims against actual product capabilities
+- Conduct reference checks with existing customers of each vendor
+- Assess architecture compatibility and integration complexity
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** accept vendor demos as proof of capability without hands-on testing
+- The agent **MUST** contact vendor references or asking only the vendor-provided references
+- The agent **MUST NOT** evaluate technical capabilities in isolation without considering integration needs
+- The agent **MUST NOT** ignore scalability and performance under realistic loadd conditions