haiku-method 2.2.0

package/studios/sales/stages/negotiation/outputs/NEGOTIATION-TERMS.md

@@ -0,0 +1,25 @@
+---
+name: negotiation-terms
+location: .haiku/intents/{intent-slug}/stages/negotiation/artifacts/
+scope: intent
+format: text
+required: true
+---
+
+# Negotiation Terms
+
+Agreed terms with objection handling, contract review, and stakeholder alignment.
+
+## Expected Artifacts
+
+- **Objection handling** -- each concern addressed with evidence-based responses and fallback positions
+- **Contract terms** -- redlines categorized by risk with accept/reject/counter recommendations
+- **Stakeholder alignment** -- each decision-maker's position and required actions to move forward
+- **Agreed terms** -- shared understanding of terms ready for final approval
+
+## Quality Signals
+
+- All raised objections are addressed with evidence-based responses
+- Contract redlines are categorized by risk level
+- Stakeholder positions are documented with required actions
+- Legal review has flagged risk items and confirmed acceptable terms

package/studios/sales/stages/negotiation/phases/ELABORATION.md

@@ -0,0 +1,16 @@
+# Negotiation Stage — Elaboration
+
+## Criteria Guidance
+
+### Good criteria — concrete and verifiable
+
+- "Objection handling document addresses each raised concern with evidence-based responses and fallback positions"
+- "Contract redlines are categorized by risk level with recommended accept/reject/counter for each"
+- "Stakeholder alignment matrix shows each decision-maker's current position and required actions to move them forward"
+
+### Bad criteria — vague (no clear check)
+
+- "Objections are handled"
+- "Terms are negotiated"
+- "Stakeholders are aligned"
+

package/studios/sales/stages/negotiation/review-agents/terms-review.md

@@ -0,0 +1,10 @@
+---
+interpretation: lens
+---
+**Mandate:** The agent **MUST** verify negotiated terms protect business interests while meeting prospect needs.
+
+**Check:**
+- The agent **MUST** verify that discount levels are within approved authority or have required approvals
+- The agent **MUST** verify that contract terms do not create unsustainable obligations (SLAs, custom work, exclusivity)
+- The agent **MUST** verify that payment terms are aligned with company policy
+- The agent **MUST** verify that legal risk areas (liability, indemnification, IP) are flagged for review

package/studios/sales/stages/proposal/STAGE.md

@@ -0,0 +1,19 @@
+---
+name: proposal
+description: Create tailored proposals, demos, and business cases
+hats: [proposal-writer, solution-architect, verifier]
+fix_hats: [proposal-writer, feedback-assessor]
+review: [ask, await]
+elaboration: collaborative
+inputs:
+  - stage: qualification
+    discovery: deal-brief
+gate-protocol:
+  timeout: 7d
+  timeout-action: escalate
+  escalation: comms
+---
+
+# Proposal
+
+Create tailored proposals, demos, and business cases.

package/studios/sales/stages/proposal/discovery/PROPOSAL-DOC.md

@@ -0,0 +1,31 @@
+---
+name: proposal-doc
+location: .haiku/intents/{intent-slug}/knowledge/PROPOSAL-DOC.md
+scope: intent
+format: text
+required: true
+---
+
+# Proposal Document
+
+The tailored proposal for the prospect. This output drives the negotiation stage and serves as the primary sales artifact.
+
+## Content Guide
+
+Structure the proposal around prospect value:
+
+- **Executive summary** — the prospect's challenge and the proposed outcome in their language
+- **Pain-to-solution mapping** — each identified pain point matched to a specific capability with expected impact
+- **Business case** — quantified ROI with stated assumptions, payback period, and sensitivity analysis
+- **Technical solution** — architecture overview, integration approach, and implementation plan
+- **Implementation approach** — phases, milestones, and resource requirements
+- **Pricing structure** — commercial terms aligned to value delivered
+- **Risk mitigation** — how identified risks are addressed
+- **Competitive differentiation** — why this solution over the alternatives
+
+## Quality Signals
+
+- A reader can identify which prospect this was written for without seeing the company name in the header
+- ROI calculations show their math and state their assumptions
+- Technical claims have been validated by the solution architect as feasible
+- The proposal addresses the decision criteria of each buying committee member

package/studios/sales/stages/proposal/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/sales/stages/proposal/hats/proposal-writer.md

@@ -0,0 +1,8 @@
+**Focus:** Craft a compelling, tailored proposal that connects the prospect's specific pain points to concrete solutions with quantified value. The proposal should readd as if it was written for this prospect alone, not adapted from a template.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** use boilerplate language that could apply to any prospect
+- The agent **MUST NOT** leadd with product features instead of prospect outcomes
+- The agent **MUST NOT** present ROI without stating assumptions or showing the math
+- The agent **MUST NOT** ignore the competitive alternatives the prospect is evaluating
+- The agent **MUST NOT** write for a technical audience when the economic buyer is non-technical (or vice versa)

package/studios/sales/stages/proposal/hats/solution-architect.md

@@ -0,0 +1,8 @@
+**Focus:** Validate technical feasibility, design the solution architecture for the prospect's environment, and ensure the proposal's technical claims are deliverable. Bridge the gap between what sales promises and what delivery can execute.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** approve technical claims in the proposal without validating feasibility
+- The agent **MUST NOT** design an ideal-state solution that ignores the prospect's existing infrastructure
+- The agent **MUST NOT** over-engineer the solution beyond what the prospect needs or can absorb
+- The agent **MUST** flag implementation risks or prerequisites that affect timeline
+- The agent **MUST NOT** treat every prospect environment as identical to the reference architecture

package/studios/sales/stages/proposal/hats/verifier.md

@@ -0,0 +1,26 @@
+**Focus:** Validate the per-unit design/synthesis artifact for the proposal stage of sales. Units here are proposal artifact — designed outputs that downstream stages execute against. Validation rules check substance, internal coherence with the brief, traceability to upstream inputs, and decision-register accountability. NOT executable verify-commands.
+
+**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 design brief
+The unit's title and first paragraph define the design problem. The remaining body MUST deliver a concrete designed artifact (specification, structure, interaction model, plan element, etc.) — not an outline, not a deferral, not a "we'll figure this out later".
+
+### 2. Trace to upstream inputs
+Every design choice that depends on upstream knowledge MUST cite the specific upstream artifact (knowledge unit, decision, requirement). Reject choices that conflict with — or float free of — what the upstream stages established.
+
+### 3. Internal coherence
+Sub-components / sections of the design must compose without contradiction. A design that says "single-tenant" in one section and "multi-tenant by default" in another is rejected. Cite the contradicting paragraphs.
+
+### 4. Decision-register consistency
+The unit must not propose an option contradicting a recorded Decision. Cite the Decision ID.
+
+### 5. Open questions accounted for
+Every "Open Questions" entry must be answered, defaulted, OR flagged `(needs human escalation)`. Design open questions left unresolved without an escalation flag are a reject — downstream stages cannot consume an under-specified design.

package/studios/sales/stages/proposal/outputs/PROPOSAL-DOC.md

@@ -0,0 +1,25 @@
+---
+name: proposal-doc
+location: .haiku/intents/{intent-slug}/stages/proposal/artifacts/
+scope: intent
+format: text
+required: true
+---
+
+# Proposal Document
+
+Tailored proposal with solution mapping, business case, and demo script.
+
+## Expected Artifacts
+
+- **Proposal** -- each prospect pain point mapped to a specific solution capability with expected impact
+- **Business case** -- quantified ROI with stated assumptions and sensitivity analysis
+- **Demo script** -- addresses the top prospect priorities from the deal brief
+- **Solution architecture** -- how the solution fits the prospect's technical environment
+
+## Quality Signals
+
+- Every prospect pain point maps to a specific solution capability
+- Business case includes quantified ROI with stated assumptions
+- Demo script addresses the top 3 prospect priorities
+- Proposal is tailored to the prospect, not generic

package/studios/sales/stages/proposal/phases/ELABORATION.md

@@ -0,0 +1,16 @@
+# Proposal Stage — Elaboration
+
+## Criteria Guidance
+
+### Good criteria — concrete and verifiable
+
+- "Proposal maps each prospect pain point to a specific solution capability with expected impact"
+- "Business case includes quantified ROI with stated assumptions and a sensitivity analysis"
+- "Demo script addresses the top 3 prospect priorities identified in the deal brief"
+
+### Bad criteria — vague (no clear check)
+
+- "Proposal is written"
+- "Business case looks compelling"
+- "Demo is ready"
+

package/studios/sales/stages/proposal/review-agents/accuracy.md

@@ -0,0 +1,10 @@
+---
+interpretation: lens
+---
+**Mandate:** The agent **MUST** verify the proposal accurately represents capabilities and pricing.
+
+**Check:**
+- The agent **MUST** verify that all claimed capabilities are real and available (no vaporware)
+- The agent **MUST** verify that pricing matches current rate cards and approved discount structures
+- The agent **MUST** verify that any timeline cited in the proposal matches the prospect's expectations and is internally consistent across sections (drift check, not feasibility — actual implementation feasibility belongs to the project-management/charter or software/design stages downstream)
+- The agent **MUST** verify that case studies and references are relevant to the prospect's industry and scale

package/studios/sales/stages/qualification/STAGE.md

@@ -0,0 +1,15 @@
+---
+name: qualification
+description: Qualify the opportunity against ICP, budget, authority, need, and timeline
+hats: [qualifier, deal-strategist, verifier]
+fix_hats: [qualifier, feedback-assessor]
+review: ask
+elaboration: collaborative
+inputs:
+  - stage: research
+    discovery: prospect-brief
+---
+
+# Qualification
+
+Qualify the opportunity against ICP, budget, authority, need, and timeline.

package/studios/sales/stages/qualification/discovery/DEAL-BRIEF.md

@@ -0,0 +1,31 @@
+---
+name: deal-brief
+location: .haiku/intents/{intent-slug}/knowledge/DEAL-BRIEF.md
+scope: intent
+format: text
+required: true
+---
+
+# Deal Brief
+
+Qualification assessment and deal strategy for the opportunity. This output drives the proposal stage and informs negotiation positioning.
+
+## Content Guide
+
+Structure the brief around deal viability and strategy:
+
+- **BANT assessment** — Budget (confirmed/estimated amount), Authority (decision-maker identified), Need (validated pain), Timeline (urgency drivers)
+- **ICP fit score** — weighted dimensions with justification for each rating
+- **Buying committee** — each member's role, stance, influence, and engagement plan
+- **Champion identification** — who internally advocates for the deal, their motivation
+- **Competitive positioning** — how to differentiate against identified alternatives
+- **Win plan** — engagement sequence, key milestones, and success criteria
+- **Risk assessment** — top risks to the deal with mitigation strategies
+- **Go/no-go recommendation** — qualified in or out, with justification
+
+## Quality Signals
+
+- BANT criteria are evidence-based, not assumed
+- The champion is a specific person with a documented reason to support the deal
+- Win plan has concrete next steps, not generic "build relationship"
+- Risks are specific to this deal, not boilerplate sales risks

package/studios/sales/stages/qualification/hats/deal-strategist.md

@@ -0,0 +1,8 @@
+**Focus:** Design the win plan — identify champions, map the political landscape, anticipate objections, and define the engagement strategy. Turn qualification data into an actionable path to close.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** create a strategy without identifying a specific internal champion
+- The agent **MUST NOT** ignore organizational politics and treating the deal as purely rational
+- The agent **MUST NOT** plan only for the happy path without contingencies for objections or delays
+- The agent **MUST NOT** copy a generic playbook without adapting to this prospect's specific dynamics
+- The agent **MUST** identify the biggest risk to the deal and how to mitigate it

package/studios/sales/stages/qualification/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/sales/stages/qualification/hats/qualifier.md

@@ -0,0 +1,8 @@
+**Focus:** Systematically evaluate the opportunity against qualification criteria — Budget, Authority, Need, Timeline (BANT), ICP fit, and buying readiness. Be honest about weak signals — a poorly qualified deal wastes everyone's effort.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** mark criteria as "met" without supporting evidence
+- The agent **MUST NOT** assume authority based on title alone without verifying decision-making power
+- The agent **MUST NOT** ignore disqualifying signals to keep the pipeline full
+- The agent **MUST** distinguish between stated need and validated need
+- The agent **MUST NOT** qualify based on what the prospect says they will do rather than what they have done

package/studios/sales/stages/qualification/hats/verifier.md

@@ -0,0 +1,26 @@
+**Focus:** Validate the per-unit knowledge artifact for the qualification stage of sales. Units here are qualification record — 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/sales/stages/qualification/outputs/DEAL-BRIEF.md

@@ -0,0 +1,25 @@
+---
+name: deal-brief
+location: .haiku/intents/{intent-slug}/stages/qualification/artifacts/
+scope: intent
+format: text
+required: true
+---
+
+# Deal Brief
+
+BANT qualification, ICP fit score, buying committee map, and deal strategy.
+
+## Expected Artifacts
+
+- **BANT qualification** -- budget, authority, need, and timeline scored with supporting evidence
+- **ICP fit score** -- at least 5 weighted dimensions with justification for each rating
+- **Buying committee** -- roles and influence levels mapped with named individuals
+- **Deal strategy** -- win plan with identified champions, blockers, and engagement approach
+
+## Quality Signals
+
+- BANT criteria are scored with evidence from discovery conversations
+- ICP fit score includes weighted dimensions with justification
+- Economic buyer is identified by name with decision-making authority documented
+- Win plan identifies champions and potential blockers

package/studios/sales/stages/qualification/phases/ELABORATION.md

@@ -0,0 +1,16 @@
+# Qualification Stage — Elaboration
+
+## Criteria Guidance
+
+### Good criteria — concrete and verifiable
+
+- "BANT criteria are each scored with supporting evidence from discovery conversations or research"
+- "ICP fit score includes at least 5 weighted dimensions with justification for each rating"
+- "Deal brief identifies the economic buyer by name and documents their decision-making authority"
+
+### Bad criteria — vague (no clear check)
+
+- "Prospect is qualified"
+- "BANT is filled out"
+- "Deal looks good"
+

package/studios/sales/stages/qualification/review-agents/rigor.md

@@ -0,0 +1,10 @@
+---
+interpretation: lens
+---
+**Mandate:** The agent **MUST** verify qualification assessment is honest and not inflated.
+
+**Check:**
+- The agent **MUST** verify that iCP fit scoring reflects actual evidence, not optimistic interpretation
+- The agent **MUST** verify that disqualification signals are surfaced, not buried
+- The agent **MUST** verify that budget and authority assessment is based on what the prospect said, not assumptions
+- The agent **MUST** verify that deal risk factors are identified and have mitigation plans

package/studios/sales/stages/research/STAGE.md

@@ -0,0 +1,13 @@
+---
+name: research
+description: Understand the prospect, their business, pain points, and competitive landscape
+hats: [prospect-researcher, industry-analyst, verifier]
+fix_hats: [prospect-researcher, feedback-assessor]
+review: auto
+elaboration: autonomous
+inputs: []
+---
+
+# Research
+
+Understand the prospect, their business, pain points, and competitive landscape.

package/studios/sales/stages/research/discovery/PROSPECT-BRIEF.md

@@ -0,0 +1,30 @@
+---
+name: prospect-brief
+location: .haiku/intents/{intent-slug}/knowledge/PROSPECT-BRIEF.md
+scope: intent
+format: text
+required: true
+---
+
+# Prospect Brief
+
+Document prospect research findings for the deal. This output feeds downstream stages (qualification, proposal, negotiation, close) as their foundational context.
+
+## Content Guide
+
+Structure the brief around understanding the prospect:
+
+- **Company overview** — what the company does, size, revenue, market position
+- **Key stakeholders** — names, titles, roles in buying decisions, influence level
+- **Technology environment** — current stack, known constraints, integration requirements
+- **Pain points** — identified challenges with supporting evidence
+- **Recent initiatives** — strategic shifts, new projects, leadership changes, earnings highlights
+- **Competitive landscape** — incumbents, alternatives being evaluated, switching costs
+- **Industry context** — market trends, regulatory pressures, competitive forces relevant to the sale
+
+## Quality Signals
+
+- Every pain point traces to a specific source (public filing, news article, conversation)
+- Stakeholders are mapped with roles and influence, not just listed
+- Competitive landscape reflects what the prospect actually uses, not generic industry alternatives
+- Findings are organized for consumption by the qualification stage, not as a raw dump

package/studios/sales/stages/research/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/sales/stages/research/hats/industry-analyst.md

@@ -0,0 +1,8 @@
+**Focus:** Evaluate the prospect's industry context, market position, competitive pressures, and regulatory environment. Identify trends and forces that create urgency or opportunity for the sale. Transform raw prospect research into strategic sales intelligence.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** produce generic industry reports not tailored to this specific prospect
+- The agent **MUST NOT** ignore the competitive landscape the prospect operates in
+- The agent **MUST NOT** miss regulatory or compliance pressures that drive purchasing decisions
+- The agent **MUST** connect industry trends to concrete sales opportunities
+- The agent **MUST NOT** treat all competitors as equal threats without analyzing relative positioning

package/studios/sales/stages/research/hats/prospect-researcher.md

@@ -0,0 +1,8 @@
+**Focus:** Investigate the prospect's business, financials, recent news, org structure, and technology stack. Build a comprehensive picture of who they are and what they care about. Depth over breadth — a shallow overview is not enough to sell.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** rely solely on the company's marketing materials for understanding their challenges
+- The agent **MUST NOT** list stakeholders without mapping their roles and influence in buying decisions
+- The agent **MUST NOT** ignore recent news, earnings calls, or strategic shifts
+- The agent **MUST NOT** produce a generic company summary that could apply to any similar company
+- The agent **MUST** document sources or how findings were obtained

package/studios/sales/stages/research/hats/verifier.md

@@ -0,0 +1,26 @@
+**Focus:** Validate the per-unit knowledge artifact for the research stage of sales. Units here are prospect-research note — 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/sales/stages/research/outputs/PROSPECT-BRIEF.md

@@ -0,0 +1,25 @@
+---
+name: prospect-brief
+location: .haiku/intents/{intent-slug}/stages/research/artifacts/
+scope: intent
+format: text
+required: true
+---
+
+# Prospect Brief
+
+Company overview, stakeholder map, pain points, and competitive landscape.
+
+## Expected Artifacts
+
+- **Company overview** -- strategic priorities with supporting evidence
+- **Key stakeholders** -- decision-makers and influencers mapped with roles
+- **Pain points** -- identified pain mapped to specific product capabilities
+- **Competitive landscape** -- incumbent vendors with strengths and weaknesses
+
+## Quality Signals
+
+- Top 3 strategic priorities are identified with supporting evidence
+- At least 3 incumbent vendors are analyzed with strengths and weaknesses
+- Pain points map to specific product capabilities
+- Market trends relevant to the prospect are identified

package/studios/sales/stages/research/phases/ELABORATION.md

@@ -0,0 +1,16 @@
+# Research Stage — Elaboration
+
+## Criteria Guidance
+
+### Good criteria — concrete and verifiable
+
+- "Prospect brief identifies the company's top 3 strategic priorities with supporting evidence"
+- "Competitive landscape covers at least 3 incumbent vendors with strengths and weaknesses"
+- "Pain point analysis maps each identified pain to a specific product capability"
+
+### Bad criteria — vague (no clear check)
+
+- "Research is complete"
+- "Prospect is understood"
+- "Competitive analysis is done"
+

package/studios/sales/stages/research/review-agents/relevance.md

@@ -0,0 +1,10 @@
+---
+interpretation: lens
+---
+**Mandate:** The agent **MUST** verify prospect research is relevant and actionable for the sales process.
+
+**Check:**
+- The agent **MUST** verify that pain points identified are specific to this prospect, not generic industry problems
+- The agent **MUST** verify that competitive landscape reflects what this prospect is actually evaluating
+- The agent **MUST** verify that budget, authority, need, and timeline signals are evidence-based
+- The agent **MUST** verify that industry context is current, not recycled from outdated sources

package/studios/sales/templates/new-prospect.md

@@ -0,0 +1,48 @@
+---
+name: new-prospect
+studio: sales
+description: Work a new prospect from research through close
+parameters:
+  - name: company
+    description: Prospect company name
+    required: true
+  - name: contact
+    description: Primary contact name and title
+    required: false
+  - name: source
+    description: Lead source (inbound, referral, outbound, event)
+    required: false
+units:
+  - name: "prospect-research"
+    stage: research
+    criteria:
+      - "{{ company }} business model and pain points documented"
+      - "Decision makers and buying process mapped"
+      - "Competitive landscape for this deal identified"
+  - name: "qualify"
+    stage: qualification
+    criteria:
+      - "ICP fit scored against standard criteria"
+      - "Budget, authority, need, and timeline assessed"
+      - "Go/no-go decision documented with rationale"
+  - name: "proposal"
+    stage: proposal
+    criteria:
+      - "Proposal tailored to {{ company }} pain points"
+      - "Pricing within approved discount structure"
+      - "Demo or proof of concept prepared if applicable"
+  - name: "negotiate"
+    stage: negotiation
+    criteria:
+      - "Terms reviewed by legal"
+      - "Objections documented with responses"
+      - "Final terms agreed by both parties"
+  - name: "close-deal"
+    stage: close
+    criteria:
+      - "Contract signed"
+      - "CS handoff context prepared (goals, timeline, contacts)"
+      - "Win/loss context documented"
+---
+
+Full sales cycle for a new prospect. CRM provider syncs deal state automatically.

package/studios/security-assessment/STUDIO.md

@@ -0,0 +1,11 @@
+---
+name: security-assessment
+description: Security assessment and penetration testing lifecycle for evaluating existing systems
+stages: [reconnaissance, enumeration, exploitation, post-exploitation, reporting]
+category: engineering
+default_model: sonnet
+---
+
+# Security Assessment Studio
+
+Security assessment lifecycle for penetration testing, vulnerability assessments, and security audits of existing systems. Follows the standard pentest methodology: passive/active reconnaissance, service enumeration, controlled exploitation, post-exploitation analysis, and formal reporting. Uses git persistence for auditable findings and reproducible test cases.

package/studios/security-assessment/examples/internal-app-pentest/intent.md

@@ -0,0 +1,17 @@
+---
+title: internal-app-pentest
+studio: security-assessment
+stages: [reconnaissance, enumeration, exploitation, post-exploitation, reporting]
+status: complete
+---
+
+# Internal Admin Dashboard Pentest
+
+Pre-launch pentest of the internal admin dashboard before it's opened to partner admins. Scope is the web app and the API it calls; infrastructure is excluded. Both authenticated and unauthenticated testing, with focus on the partner-admin role and privilege-escalation paths.
+
+## Goals
+
+- Recon and enumeration of all admin routes and API endpoints
+- Authenticated test as partner-admin — privilege escalation to super-admin
+- Unauthenticated surface testing for auth bypass and IDOR
+- Report with severity-ranked findings and remediation recommendations