haiku-method 2.2.0

package/studios/quality-assurance/stages/execute-tests/review-agents/evidence.md

@@ -0,0 +1,10 @@
+---
+interpretation: lens
+---
+**Mandate:** The agent **MUST** verify test execution is complete with evidence-backed results and properly documented defects.
+
+**Check:**
+- The agent **MUST** verify that all planned tests are executed or have documented justification for skip
+- The agent **MUST** verify that test results include evidence (screenshots, logs) for failures
+- The agent **MUST** verify that defect reports have reproduction steps, environment details, and severity classification
+- The agent **MUST** verify that test environment matched production conditions during execution

package/studios/quality-assurance/stages/plan/STAGE.md

@@ -0,0 +1,13 @@
+---
+name: plan
+description: Define test strategy and coverage planning
+hats: [strategist, planner, verifier]
+fix_hats: [strategist, feedback-assessor]
+review: ask
+elaboration: collaborative
+inputs: []
+---
+
+# Plan
+
+Define test strategy and coverage planning.

package/studios/quality-assurance/stages/plan/discovery/TEST-STRATEGY.md

@@ -0,0 +1,30 @@
+---
+name: test-strategy
+location: .haiku/intents/{intent-slug}/knowledge/TEST-STRATEGY.md
+scope: intent
+format: text
+required: true
+---
+
+# Test Strategy
+
+Overall test approach including scope, risk-based prioritization, and entry/exit criteria.
+
+## Content Guide
+
+Structure the strategy to guide all downstream QA stages:
+
+- **Test scope** -- what is being tested and what is excluded with rationale
+- **Quality objectives** -- quality dimensions to be assessed (functional, performance, security, usability)
+- **Risk-based prioritization** -- test areas ranked by business impact and failure probability
+- **Test approaches** -- methodologies for each quality dimension
+- **Entry criteria** -- conditions that must be met before testing can begin
+- **Exit criteria** -- measurable conditions that must be met for quality certification
+- **Resource requirements** -- environments, tools, data, and personnel
+
+## Quality Signals
+
+- Scope is aligned with product requirements and stakeholder quality priorities
+- Prioritization reflects actual business risk, not generic severity
+- Exit criteria are specific and measurable
+- Resource requirements are validated as feasible

package/studios/quality-assurance/stages/plan/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/quality-assurance/stages/plan/hats/planner.md

@@ -0,0 +1,13 @@
+**Focus:** Plan the execution logistics including resource allocation, environment needs, and scheduling.
+
+**Responsibilities:**
+- Allocate testing resources across test phases and activities
+- Identify environment and data requirements for each test phase
+- Create the test execution schedule with dependencies
+- Confirm resource availability and environment readiness
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** plan without confirming that test environments will be available
+- The agent **MUST** account for test data preparation and management effort
+- The agent **MUST NOT** schedul test phases without considering development delivery dependencies
+- The agent **MUST NOT** underestimat the effort required for test setup and teardown

package/studios/quality-assurance/stages/plan/hats/strategist.md

@@ -0,0 +1,13 @@
+**Focus:** Define the overall test strategy including scope, approach, risk-based prioritization, and resource requirements.
+
+**Responsibilities:**
+- Define test scope aligned with product requirements and quality objectives
+- Establish risk-based test prioritization with business impact assessment
+- Select test approaches and methodologies for each quality dimension
+- Define entry and exit criteria for each test phase
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** create a strategy that tries to test everything equally rather than prioritizing by risk
+- The agent **MUST NOT** define strategy without consulting stakeholders on quality priorities
+- The agent **MUST NOT** select test approaches based on team familiarity rather than effectiveness
+- The agent **MUST** define measurable exit criteria for each phase

package/studios/quality-assurance/stages/plan/hats/verifier.md

@@ -0,0 +1,26 @@
+**Focus:** Validate the per-unit knowledge artifact for the plan stage of quality-assurance. Units here are test-plan element — 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/quality-assurance/stages/plan/outputs/TEST-STRATEGY.md

@@ -0,0 +1,25 @@
+---
+name: test-strategy
+location: .haiku/intents/{intent-slug}/stages/plan/artifacts/
+scope: intent
+format: text
+required: true
+---
+
+# Test Strategy
+
+Scope, approach, risk-based priorities, and resource requirements for quality assurance.
+
+## Expected Artifacts
+
+- **Strategy document** -- scope, approach, and resource requirements with coverage targets
+- **Risk-based priorities** -- test areas ranked by business impact and failure probability
+- **Entry/exit criteria** -- defined for each test phase with measurable thresholds
+- **Resource plan** -- resource availability and sequencing validated against constraints
+
+## Quality Signals
+
+- Strategy covers all critical quality dimensions
+- Risk-based priorities are ranked with justification
+- Entry and exit criteria have measurable thresholds
+- Resource availability and sequencing are feasible

package/studios/quality-assurance/stages/plan/phases/ELABORATION.md

@@ -0,0 +1,16 @@
+# Plan Stage — Elaboration
+
+## Criteria Guidance
+
+### Good criteria — concrete and verifiable
+
+- "Test strategy defines scope, approach, and resource requirements with explicit coverage targets for each quality dimension"
+- "Risk-based prioritization ranks test areas by business impact and failure probability with justification"
+- "Entry and exit criteria are defined for each test phase with measurable thresholds"
+
+### Bad criteria — vague (no clear check)
+
+- "Strategy is defined"
+- "Plan is ready"
+- "Coverage is planned"
+

package/studios/quality-assurance/stages/plan/review-agents/coverage.md

@@ -0,0 +1,10 @@
+---
+interpretation: lens
+---
+**Mandate:** The agent **MUST** verify test strategy provides adequate coverage of quality dimensions and risks.
+
+**Check:**
+- The agent **MUST** verify that risk-based prioritization reflects actual business impact, not generic severity
+- The agent **MUST** verify that coverage targets are defined for each quality dimension
+- The agent **MUST** verify that entry and exit criteria are measurable with specific thresholds
+- The agent **MUST** verify that resource and environment requirements are feasible within constraints

package/studios/sales/STUDIO.md

@@ -0,0 +1,11 @@
+---
+name: sales
+description: Sales lifecycle from prospect research through deal close and handoff
+stages: [research, qualification, proposal, negotiation, close]
+category: go-to-market
+default_model: sonnet
+---
+
+# Sales Studio
+
+Sales cycle lifecycle for managing deals from initial prospect research through qualification, proposal creation, negotiation, and close. Works for enterprise sales, solution selling, and complex B2B deals.

package/studios/sales/examples/enterprise-lead-close/intent.md

@@ -0,0 +1,17 @@
+---
+title: enterprise-lead-close
+studio: sales
+stages: [research, qualification, proposal, negotiation, close]
+status: complete
+---
+
+# Acme Corp Enterprise Close
+
+Close the Acme Corp enterprise deal currently stuck in legal review. $480K ACV, 3-year term with an annual ramp. Sticking point is the DPA — customer wants unlimited liability on data breach; standard contract caps at annual fees.
+
+## Goals
+
+- Prepare counter-proposal on DPA liability with legal-approved fallback language
+- Escalate to customer's GC for a live negotiation call within the week
+- Close the gap to an agreed DPA without breaking the annual-fees liability cap
+- Countersigned contract before end of month

package/studios/sales/examples/enterprise-lead-close/pre-intent.yml

@@ -0,0 +1,17 @@
+related:
+  - customer-success
+  - marketing
+  - finance
+turns:
+  - role: user
+    text: "Close the Acme Corp deal — they're in legal review."
+  - role: agent
+    text: "What's the deal size and contract length?"
+  - role: user
+    text: "$480K ACV, 3-year term with an annual ramp."
+  - role: agent
+    text: "Main blockers in legal — redlines, DPA, indemnity?"
+  - role: user
+    text: "DPA. They want unlimited liability on data breach and we cap at annual fees."
+  - role: agent
+    text: "Got it — DPA unlimited-liability pushback is the live issue, going to negotiation with legal."

package/studios/sales/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/sales/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/sales/operations/crm-sync.md

@@ -0,0 +1,20 @@
+---
+name: crm-sync
+type: scheduled
+owner: agent
+schedule: "0 18 * * 5"
+runtime: node
+---
+
+**Purpose:** Ensure CRM data reflects actual deal state. Stale CRM data destroys forecast accuracy.
+
+**Procedure:**
+- Compare intent state with CRM records
+- Update deal stages, amounts, and close dates
+- Flag discrepancies between H·AI·K·U state and CRM
+- Sync contact interactions and meeting notes
+
+**Signals:**
+- End of week sync
+- After any deal stage transition
+- Before pipeline review meetings

package/studios/sales/operations/pipeline-review.md

@@ -0,0 +1,20 @@
+---
+name: pipeline-review
+type: scheduled
+owner: human
+frequency: "weekly"
+---
+
+**Purpose:** Review deal pipeline health, identify stalled deals, and ensure forecast accuracy.
+
+**Procedure:**
+- [ ] Review all deals in active stages (qualification through close)
+- [ ] Identify deals with no activity in the last 7 days
+- [ ] Verify deal stage matches actual progress (no inflated pipelines)
+- [ ] Update revenue forecast based on current pipeline state
+- [ ] Identify deals at risk and create action plans
+
+**Signals:**
+- Weekly sales meeting cadence
+- End of month/quarter approaching
+- Deals stalling in negotiation or proposal stages

package/studios/sales/operations/win-loss-log.md

@@ -0,0 +1,19 @@
+---
+name: win-loss-log
+type: reactive
+owner: human
+trigger: "deal closes (won or lost)"
+---
+
+**Purpose:** Capture win/loss context while it's fresh. Delayed capture loses the nuance.
+
+**Procedure:**
+- [ ] Record final outcome (won/lost/no-decision)
+- [ ] Document primary win/loss reason
+- [ ] Note competitive dynamics (who else was evaluated)
+- [ ] Capture buyer feedback if available
+- [ ] Identify what would change the outcome if replayed
+
+**Signals:**
+- Deal reaches close stage (won or lost)
+- Prospect goes dark after proposal/negotiation

package/studios/sales/reflections/conversion.md

@@ -0,0 +1,17 @@
+---
+name: conversion
+studio: sales
+---
+
+**Analyze:** Stage-to-stage conversion rates, time spent in each stage, drop-off points.
+
+**Look for:**
+- Which stage had the highest drop-off rate
+- Whether qualification criteria predicted deal success
+- Proposal-to-negotiation conversion (did proposals land?)
+- Average time in each stage vs deals that closed
+
+**Produce:**
+- Conversion funnel analysis
+- Stage duration benchmarks
+- Recommendations for qualification criteria or proposal approach changes

package/studios/sales/reflections/objection-patterns.md

@@ -0,0 +1,17 @@
+---
+name: objection-patterns
+studio: sales
+---
+
+**Analyze:** Objections encountered during proposal and negotiation, how they were handled, outcomes.
+
+**Look for:**
+- Recurring objections across deals (price, timing, competition, scope)
+- Objection handling approaches that worked vs failed
+- Objections that were anticipated in research vs surprised in negotiation
+- Whether qualification caught deal-breakers early
+
+**Produce:**
+- Objection taxonomy with frequency
+- Effective response patterns
+- Recommendations for earlier objection detection in qualification

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

@@ -0,0 +1,15 @@
+---
+name: close
+description: Execute the deal, handoff to customer success, and document learnings
+hats: [closer, handoff-coordinator, verifier]
+fix_hats: [closer, feedback-assessor]
+review: [external, await]
+elaboration: collaborative
+inputs:
+  - stage: negotiation
+    discovery: terms
+---
+
+# Close
+
+Execute the deal, handoff to customer success, and document learnings.

package/studios/sales/stages/close/discovery/HANDOFF-PACKAGE.md

@@ -0,0 +1,31 @@
+---
+name: handoff-package
+location: .haiku/intents/{intent-slug}/knowledge/HANDOFF-PACKAGE.md
+scope: intent
+format: text
+required: true
+---
+
+# Handoff Package
+
+The complete deal context for customer success. This output ensures continuity between sales and post-sales.
+
+## Content Guide
+
+Structure the handoff around what customer success needs to succeed:
+
+- **Deal summary** — what was sold, key terms, and contract references
+- **Relationship history** — how the deal progressed, key interactions, trust dynamics
+- **Stakeholder map** — key contacts with roles, preferences, communication style, and relationship health
+- **Agreed deliverables** — exactly what was promised, with timeline commitments
+- **Expectations set** — what the prospect believes they are getting, including any informal commitments
+- **Known risks** — concerns the prospect expressed, sensitivities, and potential friction points
+- **Implementation prerequisites** — what the prospect needs to have ready
+- **Win/loss analysis** — critical factors in the deal outcome, learnings for future deals
+
+## Quality Signals
+
+- Customer success can onboard the account without calling the sales team for context
+- Commitments made during sales are explicitly documented, not left to memory
+- Known risks are flagged proactively, not discovered during implementation
+- Win/loss analysis captures actionable learnings, not just "we won because we're great"

package/studios/sales/stages/close/hats/closer.md

@@ -0,0 +1,8 @@
+**Focus:** Drive the deal to execution — confirm all terms are agreed, secure signatures, verify purchase order and payment terms, and ensure nothing falls through the cracks between verbal agreement and executed contract.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** assume verbal agreement means the deal is done
+- The agent **MUST** confirm procurement process steps and timeline with the prospect
+- The agent **MUST NOT** leave follow-up items without assigned owners or deadlines
+- The agent **MUST NOT** fail to document the final agreed terms before requesting signature
+- The agent **MUST NOT** celebrat the close before the contract is fully executed and PO received

package/studios/sales/stages/close/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/close/hats/handoff-coordinator.md

@@ -0,0 +1,8 @@
+**Focus:** Package the complete deal context for customer success — relationship history, key contacts, agreed deliverables, expectations set during sales, and any commitments made. A clean handoff prevents the post-sale trust gap that kills renewals.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** hand off a name and contract without relationship context
+- The agent **MUST** document commitments or expectations set during the sales process
+- The agent **MUST NOT** omit known risks, concerns, or sensitivities the prospect expressed
+- The agent **MUST NOT** treat handoff as an afterthought instead of a critical deliverable
+- The agent **MUST** captur win/loss learnings while the deal context is still fresh

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

@@ -0,0 +1,26 @@
+**Focus:** Validate the per-unit operational artifact for the close stage of sales. Units here are close step — operational steps with concrete preconditions, actions, and post-condition checks. Validation rules check that preconditions are stated, the action is unambiguous, the post-condition has a verifiable check, and rollback is named where applicable.
+
+**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. Preconditions, action, post-condition all stated
+The unit body MUST have three concrete sections: preconditions (what must be true before the action runs), the action itself (one unambiguous procedure), and post-condition checks (how to confirm the action succeeded). Reject if any of the three is missing or vague.
+
+### 2. Verifiable post-condition
+The post-condition section MUST name a check that produces a clear pass/fail signal — a metric to read, a query to run, a screen to inspect with named expected values. "Verify by eye that things look good" is a reject.
+
+### 3. Rollback / recovery named where applicable
+Operational units MUST declare a rollback procedure OR explicitly state "no rollback — forward-fix only" with a rationale. Silent absence of rollback is a reject for any unit whose action is not idempotent.
+
+### 4. Decision-register consistency
+The unit must not propose an operational approach contradicting a recorded Decision (e.g., blue-green deploy when Decision N chose canary). Cite the Decision ID.
+
+### 5. Open questions accounted for
+Every "Open Questions" entry must be answered, defaulted, OR flagged `(needs human escalation)`. Operational open questions left to runtime are how outages happen.

package/studios/sales/stages/close/outputs/HANDOFF-PACKAGE.md

@@ -0,0 +1,25 @@
+---
+name: handoff-package
+location: .haiku/intents/{intent-slug}/stages/close/artifacts/
+scope: intent
+format: text
+required: true
+---
+
+# Handoff Package
+
+Deal execution record with customer success handoff and win/loss analysis.
+
+## Expected Artifacts
+
+- **Close documentation** -- signed agreements with signature, PO, and payment terms captured
+- **Handoff document** -- prospect history, key contacts, agreed deliverables, and timeline commitments
+- **Win/loss analysis** -- top critical factors in the deal outcome with evidence
+- **Implementation expectations** -- what was promised and agreed delivery timeline
+
+## Quality Signals
+
+- Signed agreements are documented with all material terms
+- Handoff includes full prospect context and relationship history
+- Win/loss analysis captures key learnings for future deals
+- Implementation expectations are clearly documented for customer success

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

@@ -0,0 +1,16 @@
+# Close Stage — Elaboration
+
+## Criteria Guidance
+
+### Good criteria — concrete and verifiable
+
+- "Close checklist confirms signature, PO, and payment terms are all captured with document references"
+- "Handoff document includes prospect history, key contacts, agreed deliverables, and timeline commitments"
+- "Win/loss analysis documents the 3 most critical factors in the deal outcome with evidence"
+
+### Bad criteria — vague (no clear check)
+
+- "Deal is closed"
+- "Handoff is done"
+- "Learnings are captured"
+

package/studios/sales/stages/close/review-agents/handoff-quality.md

@@ -0,0 +1,10 @@
+---
+interpretation: lens
+---
+**Mandate:** The agent **MUST** verify the deal close and customer success handoff are complete.
+
+**Check:**
+- The agent **MUST** verify that all contract terms are finalized and signed
+- The agent **MUST** verify that customer success team has received complete context (goals, timeline, contacts, risks)
+- The agent **MUST** verify that the right stakeholders for implementation kickoff are identified and named in the handoff packet (scheduling itself belongs to the receiving project-management or software stage, not sales)
+- The agent **MUST** verify that no verbal commitments exist that are not reflected in the contract

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

@@ -0,0 +1,15 @@
+---
+name: negotiation
+description: Handle objections, negotiate terms, and align stakeholders
+hats: [negotiator, legal-reviewer]
+fix_hats: [negotiator, feedback-assessor]
+review: [ask, await]
+elaboration: collaborative
+inputs:
+  - stage: proposal
+    discovery: proposal-doc
+---
+
+# Negotiation
+
+Handle objections, negotiate terms, and align stakeholders.

package/studios/sales/stages/negotiation/discovery/TERMS.md

@@ -0,0 +1,30 @@
+---
+name: terms
+location: .haiku/intents/{intent-slug}/knowledge/TERMS.md
+scope: intent
+format: text
+required: true
+---
+
+# Negotiation Terms
+
+The agreed terms and negotiation record for the deal. This output drives the close stage and serves as the authoritative record of what was negotiated.
+
+## Content Guide
+
+Structure the terms document around the negotiation outcome:
+
+- **Agreed terms** — final pricing, scope, timeline, and commercial conditions
+- **Objection log** — each objection raised, the response given, and the resolution
+- **Concession record** — what was conceded by each party and what was received in return
+- **Contract redlines** — categorized by risk level with accept/reject/counter status
+- **Stakeholder positions** — final alignment status of each decision-maker
+- **Outstanding items** — anything unresolved with owner, deadline, and escalation path
+- **Legal review summary** — flagged risks and their resolution status
+
+## Quality Signals
+
+- Every concession has a documented trade — nothing was given away for free
+- Contract terms are specific enough to execute without re-negotiation
+- Outstanding items have clear owners and deadlines, not vague "to be discussed"
+- The document reflects what was actually agreed, not what was proposed

package/studios/sales/stages/negotiation/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/negotiation/hats/legal-reviewer.md

@@ -0,0 +1,11 @@
+---
+interpretation: lens
+---
+**Focus:** Review contract terms, identify legal and commercial risks, categorize redlines by severity, and recommend accept/reject/counter positions for each. Protect the business without killing the deal over immaterial terms.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** treat all contract changes as equal risk without prioritizing
+- The agent **MUST NOT** reject standard prospect terms that pose no material risk
+- The agent **MUST** distinguish between legal risk and commercial risk
+- The agent **MUST NOT** review only the redlines without reading the full contract context
+- The agent **MUST NOT** escalate every issue instead of resolving routine items within authority

package/studios/sales/stages/negotiation/hats/negotiator.md

@@ -0,0 +1,8 @@
+**Focus:** Manage the negotiation process — handle objections with evidence, propose creative deal structures, protect value while finding mutually acceptable terms. Every concession should be traded, not given.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** conced on price without getting something in return (timeline, scope, reference, case study)
+- The agent **MUST NOT** respond to objections defensively instead of with evidence and reframing
+- The agent **MUST NOT** negotiate with someone who lacks decision-making authority
+- The agent **MUST NOT** los sight of the deal's total value by focusing only on headline price
+- The agent **MUST** have a documented walk-away point before entering negotiation