haiku-method 2.2.0

package/studios/ideation/examples/streaming-api-post/intent.md

@@ -0,0 +1,17 @@
+---
+title: streaming-api-post
+studio: ideation
+stages: [research, create, review, deliver]
+status: complete
+---
+
+# Streaming API Launch Post
+
+Blog post announcing the streaming API for backend engineers. Lead with the polling-layer-elimination insight; walk through a concrete migration example; close with SDK availability and documentation links.
+
+## Goals
+
+- Developer-focused voice — assume the reader runs polling loops today
+- One concrete code example showing before/after
+- Quantify the win (request volume, latency, cost)
+- Cross-link to SDK docs and migration guide

package/studios/ideation/examples/streaming-api-post/pre-intent.yml

@@ -0,0 +1,17 @@
+related:
+  - dev-evangelism
+  - marketing
+  - documentation
+turns:
+  - role: user
+    text: "Help me write a blog post about our new streaming API."
+  - role: agent
+    text: "Who's the audience — existing customers, prospects, or the broader dev community?"
+  - role: user
+    text: "Developer community. Mostly backend engineers running polling loops today."
+  - role: agent
+    text: "What's the key takeaway you want them to leave with?"
+  - role: user
+    text: "That our streaming API eliminates the need for a polling layer entirely."
+  - role: agent
+    text: "Got it — I have enough to outline and draft the post."

package/studios/ideation/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/ideation/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/ideation/operations/content-review.md

@@ -0,0 +1,19 @@
+---
+name: content-review
+type: scheduled
+owner: human
+frequency: "quarterly"
+---
+
+**Purpose:** Review published deliverables for accuracy and relevance. Content decays as the world changes.
+
+**Procedure:**
+- [ ] Review all deliverables produced by this intent
+- [ ] Check factual claims against current sources
+- [ ] Identify sections that reference outdated information
+- [ ] Flag content that needs updating or retirement
+
+**Signals:**
+- Quarterly review cadence
+- External changes that invalidate assumptions (market shifts, new research)
+- User feedback indicating outdated content

package/studios/ideation/operations/source-freshness.md

@@ -0,0 +1,19 @@
+---
+name: source-freshness
+type: scheduled
+owner: agent
+schedule: "0 9 1 */6 *"
+runtime: node
+---
+
+**Purpose:** Verify that sources cited in the deliverable are still accessible and current.
+
+**Procedure:**
+- Extract all URLs and citations from the deliverable
+- Check URL accessibility (resolve, verify 200 status)
+- Flag sources older than 2 years for relevance review
+- Report broken links and suggest replacements
+
+**Signals:**
+- Bi-annual schedule
+- After major industry events that may obsolete cited sources

package/studios/ideation/reflections/deliverable-quality.md

@@ -0,0 +1,16 @@
+---
+name: deliverable-quality
+studio: ideation
+---
+
+**Analyze:** Review findings from critic and fact-checker hats, revision count between draft and final.
+
+**Look for:**
+- Factual errors caught in review (should have been caught in research)
+- Structural issues that required reorganization
+- Whether the deliverable addressed the original intent or drifted
+
+**Produce:**
+- Quality delta between draft and final
+- Common error patterns to prevent in future intents
+- Recommendations for criteria specificity improvements

package/studios/ideation/reflections/research-quality.md

@@ -0,0 +1,16 @@
+---
+name: research-quality
+studio: ideation
+---
+
+**Analyze:** Breadth and depth of sources consulted, research gaps identified during creation.
+
+**Look for:**
+- Were multiple perspectives represented or was research one-sided?
+- Did the create stage uncover gaps the research stage missed?
+- Were assumptions validated or just carried forward?
+
+**Produce:**
+- Research thoroughness assessment
+- Gaps identified retrospectively
+- Recommendations for research methodology improvements

package/studios/ideation/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/ideation/stages/create/STAGE.md

@@ -0,0 +1,15 @@
+---
+name: create
+description: Generate the primary deliverable using research insights
+hats: [creator, editor, verifier]
+fix_hats: [creator, feedback-assessor]
+review: ask
+elaboration: collaborative
+inputs:
+  - stage: research
+    discovery: research-brief
+---
+
+# Create
+
+Generate the primary deliverable using research insights.

package/studios/ideation/stages/create/discovery/DRAFT-DELIVERABLE.md

@@ -0,0 +1,28 @@
+---
+name: draft-deliverable
+location: .haiku/intents/{intent-slug}/knowledge/DRAFT-DELIVERABLE.md
+scope: intent
+format: text
+required: true
+---
+
+# Draft Deliverable
+
+The primary draft output of the create stage. Structure depends on the intent type — it may be a document, plan, analysis, design brief, proposal, or any other form appropriate to the intent's goal.
+
+## Content Guide
+
+Regardless of form, the draft should:
+
+- **Address the problem statement** from the intent clearly and directly
+- **Incorporate research findings** — claims should trace back to the research brief
+- **Present a coherent argument or solution** — not a collection of fragments
+- **Identify areas of uncertainty** — where the draft makes assumptions or where evidence is thin
+- **Be substantive** — complete enough for meaningful adversarial review, not a skeleton
+
+## Quality Signals
+
+- A reader unfamiliar with the research can follow the argument
+- Research findings are woven in naturally, not dumped as a separate section
+- The draft takes a position rather than hedging everything
+- Uncertainties are flagged honestly rather than hidden

package/studios/ideation/stages/create/hats/creator.md

@@ -0,0 +1,8 @@
+**Focus:** Produce the primary output — document, design, plan, analysis, or whatever the intent calls for — using research insights as the foundation. Substance over polish at this stage.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** start from scratch and ignoring research findings
+- The agent **MUST NOT** produce a skeleton or outline without substance
+- The agent **MUST NOT** gold-plate prose before the argument is solid
+- The agent **MUST NOT** cherry-pick research that supports a predetermined conclusion
+- The agent **MUST NOT** leave sections as TODOs or placeholders

package/studios/ideation/stages/create/hats/editor.md

@@ -0,0 +1,8 @@
+**Focus:** Refine structure, improve clarity, strengthen arguments, and ensure coherence. The editor serves the creator's intent — sharpening, not rewriting.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** rewrite the draft from scratch instead of editing
+- The agent **MUST NOT** prioritize style over substance
+- The agent **MUST NOT** make changes that alter the creator's intended meaning
+- The agent **MUST NOT** introduce claims not supported by the research
+- The agent **MUST NOT** over-edit to the point of losing the original voice

package/studios/ideation/stages/create/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/ideation/stages/create/hats/verifier.md

@@ -0,0 +1,26 @@
+**Focus:** Validate the per-unit design/synthesis artifact for the create stage of ideation. Units here are idea 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/ideation/stages/create/outputs/DRAFT-DELIVERABLE.md

@@ -0,0 +1,25 @@
+---
+name: draft-deliverable
+location: .haiku/intents/{intent-slug}/stages/create/artifacts/
+scope: intent
+format: text
+required: true
+---
+
+# Draft Deliverable
+
+Primary deliverable draft addressing research findings with coherent argument or solution.
+
+## Expected Artifacts
+
+- **Draft** -- addresses key findings from research with coherent structure
+- **Thesis statements** -- each section has a clear thesis supported by evidence
+- **Counterarguments** -- main claims are tested against opposing perspectives
+- **Editor refinements** -- clarity and structure improvements applied
+
+## Quality Signals
+
+- Draft addresses all key questions from the research brief
+- Each section has a clear thesis supported by evidence
+- Counterarguments are presented for main claims
+- Draft has been refined for clarity and structure

package/studios/ideation/stages/create/phases/ELABORATION.md

@@ -0,0 +1,16 @@
+# Create Stage — Elaboration
+
+## Criteria Guidance
+
+### Good criteria — concrete and verifiable
+
+- "Draft addresses all 5 key questions from the research brief"
+- "Each section has a clear thesis statement supported by evidence from research"
+- "Draft presents counterarguments for its main claims"
+
+### Bad criteria — vague (no clear check)
+
+- "Draft is complete"
+- "Writing is good quality"
+- "Content is comprehensive"
+

package/studios/ideation/stages/create/review-agents/accuracy.md

@@ -0,0 +1,10 @@
+---
+interpretation: lens
+---
+**Mandate:** The agent **MUST** fact-check the deliverable against source material and known constraints.
+
+**Check:**
+- The agent **MUST** verify that factual claims are supported by cited sources or verifiable evidence
+- The agent **MUST** verify that numbers, dates, and technical details are correct
+- The agent **MUST** verify that no contradictions between different sections of the deliverable
+- The agent **MUST** verify that conclusions follow logically from the evidence presented

package/studios/ideation/stages/create/review-agents/quality.md

@@ -0,0 +1,10 @@
+---
+interpretation: lens
+---
+**Mandate:** The agent **MUST** verify the deliverable meets the standard defined in the intent and is grounded in the research.
+
+**Check:**
+- The agent **MUST** verify that claims and recommendations trace back to research findings
+- The agent **MUST** verify that the deliverable addresses the stated problem, not a tangential one
+- The agent **MUST** verify that structure is clear and navigable — a reader can find what they need
+- The agent **MUST** verify that no gaps where the research provided answers but the deliverable omits them

package/studios/ideation/stages/deliver/STAGE.md

@@ -0,0 +1,17 @@
+---
+name: deliver
+description: Finalize and package the deliverable for its audience
+hats: [publisher, verifier]
+fix_hats: [publisher, feedback-assessor]
+review: auto
+elaboration: autonomous
+inputs:
+  - stage: create
+    discovery: draft-deliverable
+  - stage: review
+    discovery: review-report
+---
+
+# Deliver
+
+Finalize and package the deliverable for its audience.

package/studios/ideation/stages/deliver/discovery/FINAL-DELIVERABLE.md

@@ -0,0 +1,28 @@
+---
+name: final-deliverable
+location: .haiku/intents/{intent-slug}/knowledge/FINAL-DELIVERABLE.md
+scope: intent
+format: text
+required: true
+---
+
+# Final Deliverable
+
+The finished, audience-ready output of the ideation workflow. This is the packaged result after review feedback has been incorporated.
+
+## Content Guide
+
+The final deliverable should:
+
+- **Incorporate all review feedback** — every critical and major finding from the review report addressed
+- **Match audience expectations** — formatting, tone, and detail level appropriate for the intended readers
+- **Include an executive summary** if the audience includes decision-makers or non-specialists
+- **Have clear structure** with navigable sections, consistent headings, and logical flow
+- **Attribute sources** from the research phase where claims are made
+
+## Quality Signals
+
+- A reader can understand the deliverable without reading the research brief or review report
+- Review findings are addressed substantively, not just acknowledged
+- The document stands alone as a complete, polished work product
+- Format matches the delivery method (document, presentation, proposal, etc.)

package/studios/ideation/stages/deliver/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/ideation/stages/deliver/hats/publisher.md

@@ -0,0 +1,8 @@
+**Focus:** Incorporate review feedback, finalize formatting, and ensure the deliverable is audience-ready. The publisher bridges the gap between "reviewed draft" and "consumable output" — addressing findings, adjusting tone for the target audience, and packaging for the delivery method.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** ignore critical or major review findings
+- The agent **MUST NOT** over-polish at the expense of substance (formatting a weak argument beautifully)
+- The agent **MUST NOT** chang content meaning during formatting or restructuring
+- The agent **MUST NOT** add new claims not present in the reviewed draft
+- The agent **MUST NOT** deliver without verifying all critical findings were addressed

package/studios/ideation/stages/deliver/hats/verifier.md

@@ -0,0 +1,26 @@
+**Focus:** Validate the per-unit operational artifact for the deliver stage of ideation. Units here are delivery action — 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/ideation/stages/deliver/outputs/FINAL-DELIVERABLE.md

@@ -0,0 +1,25 @@
+---
+name: final-deliverable
+location: .haiku/intents/{intent-slug}/stages/deliver/artifacts/
+scope: intent
+format: text
+required: true
+---
+
+# Final Deliverable
+
+Finalized and packaged deliverable with review findings incorporated.
+
+## Expected Artifacts
+
+- **Final version** -- all critical and major review findings addressed
+- **Audience formatting** -- deliverable formatted for the target audience
+- **Attribution** -- all sourced claims properly attributed
+- **Publication record** -- final version packaged and delivered
+
+## Quality Signals
+
+- All critical and major review findings are addressed in the final version
+- Deliverable is formatted appropriately for the target audience
+- Attribution is complete for all sourced claims
+- Final version is ready for distribution

package/studios/ideation/stages/deliver/phases/ELABORATION.md

@@ -0,0 +1,16 @@
+# Deliver Stage — Elaboration
+
+## Criteria Guidance
+
+### Good criteria — concrete and verifiable
+
+- "All critical and major review findings are addressed in the final version"
+- "Deliverable is formatted for the target audience (e.g., executive summary for leadership, technical detail for engineering)"
+- "Final version includes attribution for all sourced claims"
+
+### Bad criteria — vague (no clear check)
+
+- "Review feedback incorporated"
+- "Formatting is done"
+- "Deliverable is final"
+

package/studios/ideation/stages/deliver/review-agents/completeness.md

@@ -0,0 +1,10 @@
+---
+interpretation: lens
+---
+**Mandate:** The agent **MUST** verify the final package is complete and ready for its audience.
+
+**Check:**
+- The agent **MUST** verify that all sections referenced in the table of contents exist
+- The agent **MUST** verify that no placeholder text, TODO markers, or draft annotations remain
+- The agent **MUST** verify that formatting is consistent and publication-ready
+- The agent **MUST** verify that all links, references, and citations resolve correctly

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

@@ -0,0 +1,13 @@
+---
+name: research
+description: Gather context, explore prior art, and understand the problem space
+hats: [researcher, analyst, verifier]
+fix_hats: [researcher, feedback-assessor]
+review: auto
+elaboration: collaborative
+inputs: []
+---
+
+# Research
+
+Gather context, explore prior art, and understand the problem space.

package/studios/ideation/stages/research/discovery/RESEARCH-BRIEF.md

@@ -0,0 +1,30 @@
+---
+name: research-brief
+location: .haiku/intents/{intent-slug}/knowledge/RESEARCH-BRIEF.md
+scope: intent
+format: text
+required: true
+---
+
+# Research Brief
+
+Document research findings for the intent's problem space. This output feeds downstream stages (create, review, deliver) as their foundational context.
+
+## Content Guide
+
+Structure the brief around the questions the intent needs answered:
+
+- **Key questions explored** — what the research set out to understand
+- **Sources consulted** — where information came from, with retrieval dates
+- **Findings per question** — what was learned, organized by theme
+- **Competing approaches** — alternative solutions or perspectives with tradeoffs
+- **Identified patterns** — recurring themes across sources
+- **Knowledge gaps** — what remains unknown or uncertain
+- **Recommended areas for deeper investigation** — where further research would add value
+
+## Quality Signals
+
+- Every claim traces to a specific source
+- Contradictory evidence is presented, not hidden
+- Gaps are explicitly called out rather than papered over
+- Findings are organized for consumption by the create stage, not as a raw dump

package/studios/ideation/stages/research/hats/analyst.md

@@ -0,0 +1,7 @@
+**Focus:** Evaluate the researcher's findings, identify patterns, surface actionable insights, and assess gaps in coverage. Transform raw research into structured understanding.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** over-analyze without synthesizing into actionable takeaways
+- The agent **MUST NOT** ignore contradictory evidence that doesn't fit the emerging narrative
+- The agent **MUST NOT** treat all findings as equally important
+- The agent **MUST** identify what's still unknown or uncertain

package/studios/ideation/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/ideation/stages/research/hats/researcher.md

@@ -0,0 +1,8 @@
+**Focus:** Explore sources, gather data, and synthesize findings across the problem space. Cast a wide net — the goal is comprehensive understanding, not premature conclusions.
+
+**Anti-patterns (RFC 2119):**
+- The agent **MUST NOT** div into creation before research is complete
+- The agent **MUST NOT** rely on a single source or perspective
+- The agent **MUST** document where information came from
+- The agent **MUST NOT** summariz without preserving source detail
+- The agent **MUST NOT** stop research after finding the first plausible answer

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

@@ -0,0 +1,26 @@
+**Focus:** Validate the per-unit knowledge artifact for the research stage of ideation. Units here are investigated topic — 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/ideation/stages/research/outputs/RESEARCH-BRIEF.md

@@ -0,0 +1,25 @@
+---
+name: research-brief
+location: .haiku/intents/{intent-slug}/stages/research/artifacts/
+scope: intent
+format: text
+required: true
+---
+
+# Research Brief
+
+Synthesized research findings organized by theme with sourced claims.
+
+## Expected Artifacts
+
+- **Findings synthesis** -- key findings organized by theme with source citations
+- **Competing approaches** -- at least 3 approaches with pros/cons for each
+- **Pattern analysis** -- key patterns ranked by relevance
+- **Knowledge gaps** -- areas requiring further investigation with recommended next steps
+
+## Quality Signals
+
+- All claims cite a specific source with retrieval date
+- At least 3 competing approaches are covered with pros/cons
+- Patterns are ranked by relevance to the problem space
+- Knowledge gaps are identified with recommended next steps

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

@@ -0,0 +1,16 @@
+# Research Stage — Elaboration
+
+## Criteria Guidance
+
+### Good criteria — concrete and verifiable
+
+- "Research brief covers at least 3 competing approaches with pros/cons for each"
+- "All claims cite a specific source with retrieval date"
+- "Gap analysis identifies at least 2 areas requiring further investigation"
+
+### Bad criteria — vague (no clear check)
+
+- "Research is thorough"
+- "Sources are included"
+- "Analysis is complete"
+

package/studios/ideation/stages/research/review-agents/thoroughness.md

@@ -0,0 +1,10 @@
+---
+interpretation: lens
+---
+**Mandate:** The agent **MUST** verify research covers the problem space without significant blind spots.
+
+**Check:**
+- The agent **MUST** verify that multiple sources consulted, not just the first result
+- The agent **MUST** verify that conflicting information is acknowledged and reconciled, not ignored
+- The agent **MUST** verify that prior art is surveyed — the research does not reinvent known solutions
+- The agent **MUST** verify that assumptions are stated explicitly, not embedded silently