skillpacks 0.1.1 → 0.1.2

package/packs/business-ops/claude/scale-audit/ALIGNMENT-PAGE.md

@@ -9,6 +9,8 @@ When this skill produces durable deliverables (research, specs, plans, reports,
 
 The tier is set per skill via `visual_tier` in SKILL.md frontmatter (or detected by the upgrade script). The bundled ALIGNMENT-PAGE.md receives tier-appropriate rendering guidance from the generator.
 
+**Context intake.** This skill declares `context_intake: artifact_only` (Artifact-driven). Work from concrete artifacts, data, logs, or existing instructions by default; ask concise clarification questions only when the available artifacts are missing, contradictory, or unsafe to interpret.
+
 **Alignment lifecycle.** Alignment pages have three lifecycle states. `review` is the draft/pre-approval page: it contains the complete deliverable preview, evidence, required inline gate questions, section feedback controls, local section-feedback YAML only after a section feedback choice is selected, and one bottom `Compile Responses` control. `confirmed` is the post-approval page after the agent has consumed final compiled response YAML, made any approved user-requested edits, and written or updated the approved canonical artifacts. A confirmed page is finished and current for the completed alignment cycle, but it remains amendable when later research changes or extends the conclusions. `amended` is a future revision of a confirmed page: archive the previous confirmed page first, mark what changed, preserve the prior approval record, and highlight the new evidence, decisions, or scope that changed the earlier conclusion.
 
 **Central alignment index.** When a research-producing skill writes or updates an HTML alignment page, also maintain the repository's central alignment index. Look for `alignment/index.html` at the repository root; if the target repo documents a different central alignment-index path, use that path and report it. If the index does not exist, create it as a self-contained HTML page that works from `file://`, links to every active `alignment/*.html` page except itself, and includes the newly written page. Every index entry must include the page's alignment date in a muted meta span after the link, formatted `YYYY-MM-DD`, for example `<a href="page.html">Title</a> <span class="meta">2026-06-09</span>`. The alignment date is the review or confirmed date written inside the page itself; new pages use today's date. If the index exists, update it instead of blindly appending: preserve valid existing entries, metadata, and entry dates; remove duplicate entries for the same page path; keep links repo-relative; and include the new or updated page. When updating an existing index, add a date only to entries that are missing one, deriving it from the page's internal alignment date, or from file history when the page has no internal date. If a `new` marker is used, combine it with the date as `<span class="meta">new · YYYY-MM-DD</span>`, and remove stale `new` markers from entries that are no longer the latest addition.
@@ -57,7 +59,9 @@ The tier is set per skill via `visual_tier` in SKILL.md frontmatter (or detected
 
 **Report-only research gates.** For report-only or pre-approval research skills, the first `review` alignment page must explicitly contain proposed research scope, source plan, assumptions/confidence, recommended output path, proposed file changes, and approval gates before synthesized research begins and before any working packet, canonical research, spec, or task file is created or updated.
 
-**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, and research-scope approval gates. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Perform the synthesized research, run required source/code checks, and write only a non-canonical working packet. Flat mode uses `research/_working/preliminary-scale-audit-research.md`; product-path mode uses `research/{slug}/_working/preliminary-scale-audit-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, research-scope approval gates, and a `Stage 2 Preview / Expected Review Format` section that shows the future Stage 2 review shape before research starts. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Perform the synthesized research, run required source/code checks, and write only a non-canonical working packet. Flat mode uses `research/_working/preliminary-scale-audit-research.md`; product-path mode uses `research/{slug}/_working/preliminary-scale-audit-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the complete working-packet substance as structured HTML review UI: purpose-built sections, tables, matrices, gates, cards, and tier-appropriate charts or diagrams that preserve every packet section, finding, caveat, and decision detail without summary loss. Raw Markdown packet text may appear only as a supplemental source view after the rendered review UI; do not make a `Full Preliminary Packet` or `Full Working Packet` raw Markdown dump, giant `<pre><code>` block, link-only view, or source-only view the primary review surface. Include the evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+
+**Stage 2 review-page template.** Stage 1 scope-review pages must include a `Stage 2 Preview / Expected Review Format` section that previews the exact section sequence, table shapes, evidence treatment, visual density, and approval gates the user will see after research; make it specific enough for the user to flag preferred content formats, grouping, labels, visuals, and evidence density before the agent does heavy research. After scope approval and research, the Stage 2 review page must include these sections as structured HTML, not as raw Markdown dumps: `Research Scope Approved` status block with approved scope, source plan, output paths, and unresolved caveats; `Executive Findings` or a skill-specific top-findings section with confidence labels; `Evidence Matrix` mapping claim, evidence/source/path, inference, confidence, assumptions, and decision impact; `Working Packet Review` with the complete working-packet substance rendered as purpose-built HTML sections, lists, tables, matrices, cards, and tier-appropriate charts or diagrams; `Alternatives / Rejected or Lower-Confidence Findings`; `Source Coverage & Gaps`; `Assumptions / Confidence Register`; `Proposed Canonical Artifacts & File Changes`; a required `User Format Preferences` gate asking whether the layout, tables, grouping, visuals, labels, and evidence density match expectations; and a required `Final Artifact Approval` gate for Stage 3 readiness. Raw Markdown packet text, search logs, or source notes may appear only as supplemental source views after the rendered review UI and never replace the Stage 2 review sections.
 
 **Visual tier rendering.** This skill's alignment page uses the `visual` tier. Inline charts and diagrams are rendered via self-contained Canvas/SVG within the HTML file. Use the alignment chart snippet library (`scripts/alignment-chart-snippets.js`) as reference — copy needed chart functions directly into the page's `<script>` block. Charts must read CSS variables (`--chart-1` through `--chart-8`) for the data visualization palette. Every chart must include a `<table>` fallback, `aria-label` on canvas/SVG, and a "View as table" toggle. Data is embedded as inline JSON — no external fetches.
 

package/packs/business-ops/claude/scale-audit/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## v0.5 - 2026-06-12
+
+- Standardized active pack and skill install guidance on `npx skillpacks install <pack-or-skill>` instead of agent-native `/pack install` or `$pack install` recommendations.
+
 ## v0.4 - 2026-06-10
 
 - Added npm-aware install-route guidance for business-ops cross-pack recommendations, preserving `/pack install <pack>` inside Claude Code while offering `npx skillpacks install <pack>` from the project shell.

package/packs/business-ops/claude/scale-audit/SKILL.md

@@ -2,15 +2,15 @@
 name: scale-audit
 description: Evaluate codebase against enterprise ICP for production readiness, compliance, and multi-stakeholder journey coverage
 type: analysis
-version: v0.4
+version: v0.5
 argument-hint: "[optional: path-to-enterprise-icp-spec]"
-interview_depth: none
+context_intake: artifact_only
 visual_tier: visual
 ---
 
 ## Pack Availability Guard
 
-When recommending a skill from another pack, verify the target pack is installed via `.agents/project.json` `enabled_packs`. If it is not enabled, recommend `/pack install <pack>` inside Claude Code, or `npx skillpacks install <pack>` from the project shell. After install, tell Claude users to run `/reload-skills`, then `/clear` or restart if the skill remains invisible. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+When recommending a skill from another pack, verify the target pack is installed via `.agents/project.json` `enabled_packs`. If it is not enabled, recommend `npx skillpacks install <pack>` from the project shell. After install, tell Claude users to run `/reload-skills`, then `/clear` or restart if the skill remains invisible. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
 
 # Scale Audit — Enterprise Production Readiness
 

package/packs/business-ops/claude/scale-audit/archive/v0.4/SKILL.md

@@ -0,0 +1,202 @@
+---
+name: scale-audit
+description: Evaluate codebase against enterprise ICP for production readiness, compliance, and multi-stakeholder journey coverage
+type: analysis
+version: v0.4
+argument-hint: "[optional: path-to-enterprise-icp-spec]"
+interview_depth: none
+visual_tier: visual
+---
+
+## Pack Availability Guard
+
+When recommending a skill from another pack, verify the target pack is installed via `.agents/project.json` `enabled_packs`. If it is not enabled, recommend `/pack install <pack>` inside Claude Code, or `npx skillpacks install <pack>` from the project shell. After install, tell Claude users to run `/reload-skills`, then `/clear` or restart if the skill remains invisible. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+
+# Scale Audit — Enterprise Production Readiness
+
+Automated analysis that evaluates the current codebase against the enterprise discovery in `research/enterprise-icp.md`. Identifies what's missing for enterprise deals — per-stakeholder journey coverage, compliance, infrastructure, and operational readiness. No interview — this is the agent doing the work.
+
+## Prerequisites
+
+`research/enterprise-icp.md` (or `research/{slug}/enterprise-icp.md`) must exist. If it doesn't, tell the user to run `/enterprise-icp` first and stop.
+
+## Process
+
+### 0. Product-Path Scope Resolution
+
+Resolve research scope by product path before using code or app structure as a hint:
+
+1. If `$ARGUMENTS` names a non-archived `research/{slug}/` directory or a product-path ID whose `scope_path` points there, use that path. Treat `{slug}` as the product/app name, not the ICP, audience, or segment label.
+2. If `$ARGUMENTS` names only `research/_archive/{slug}/` or a manifest entry with `status: archived` or legacy `status: abandoned`, stop and warn that the path is archived; do not write or update scoped outputs there.
+3. Read `research/.progress.yaml` when present. Normalize legacy `active_path` to `active_paths` on read and write back `active_paths` on manifest updates. Treat legacy `abandoned` as `archived`; exclude `archived`, `abandoned`, `deferred`, `revisit_candidate`, `promoted`, and any `scope_path` under `research/_archive/` from active target selection.
+4. If active product paths exist in the manifest, use those paths. If multiple active paths exist, ask which one to target unless this skill explicitly supports cross-path output.
+5. If no active manifest target exists, list non-archived product directories under `research/`, excluding `research/_archive/` and dot directories. Auto-select only when exactly one exists; ask when multiple exist.
+6. If no product directories exist, use flat `research/` single-product mode.
+7. Detect monorepo/app/package structure only as a secondary hint. Suggest creating a missing `research/{slug}/` product path when code clearly exposes an app, but do not require code or monorepo detection before using `research/{slug}/`.
+
+When product path `{slug}` is active, read and write research under `research/{slug}/`, specs under `specs/{slug}/`, and treat top-level `research/*.md` files as flat-mode documents or cross-path summaries.
+
+### 1. Load Context
+
+- Read `research/enterprise-icp.md` (or `research/{slug}/enterprise-icp.md`) — stakeholder map, per-persona journeys, deal-killers, lifecycle, onboarding matrix
+- Read `research/icp.md` (or `research/{slug}/icp.md`) if it exists — carry forward startup context
+- Read `research/mvp-gap.md` (or `research/{slug}/mvp-gap.md`) if it exists — note unresolved startup gaps that become more critical at enterprise scale
+- Read CLAUDE.md, README, package config, existing specs
+- Read `tasks/roadmap.md`, `tasks/todo.md`, `tasks/manual-todo.md`, `tasks/record-todo.md`, and `tasks/recurring-todo.md` (if they exist) for work in progress or advisory records
+
+### 2. Analyse the Codebase
+
+Read source files thoroughly — auth system, data layer, API design, infrastructure config (Docker, k8s, terraform, CI/CD), monitoring/logging setup, environment configuration, security implementation. Build a complete picture of production readiness.
+
+### 3. Evaluate Against Enterprise ICP
+
+#### Per-Persona Journey Coverage
+For each stakeholder identified in `research/enterprise-icp.md`:
+- **End users**: Can they complete their core workflows? Does the UX scale to enterprise complexity?
+- **Team admin**: Is there an admin panel? Seat management? Permission configuration? Usage analytics?
+- **IT / Security**: Can they complete a security review? Are audit logs available? Is SSO configurable? Can they answer a vendor security questionnaire?
+- **Procurement**: Is there an enterprise pricing page? Contract-friendly terms? Volume licensing?
+- **Executive sponsor**: Is there ROI reporting? Usage dashboards? Success metrics?
+
+#### Onboarding Gap Analysis
+For each onboarding path from `research/enterprise-icp.md`:
+- Self-serve: Does it exist? Is it frictionless?
+- Team: Can an admin onboard a team? Bulk invite? Role assignment?
+- SSO-provisioned: Is SCIM supported? JIT provisioning? Auto-deprovisioning?
+- Migration: Data import tools? Competitor mapping? Migration guides?
+- Training: In-app guidance? Documentation? API reference?
+
+#### Compliance Readiness
+- **SOC 2**: Audit logging, access controls, change management, incident response procedures
+- **GDPR**: Data deletion/export, consent management, data processing records, DPA template
+- **HIPAA** (if applicable): BAA template, PHI handling, encryption, access audit trail
+- **General security**: Encryption at rest and in transit, secrets management, vulnerability scanning, dependency auditing
+
+#### Infrastructure Readiness
+- **Multi-tenancy**: Data isolation model (shared DB with tenant ID? Separate schemas? Separate DBs?)
+- **Horizontal scaling**: Can the system scale to enterprise load? Connection pooling? Queue-based processing?
+- **Disaster recovery**: Backup strategy, recovery time objectives, failover capability
+- **Observability**: Structured logging, metrics collection, distributed tracing, alerting
+- **CI/CD maturity**: Automated testing, staging environment, deployment rollback, feature flags
+- **Environment parity**: Dev/staging/production consistency
+
+#### Operational Readiness
+- **Incident response**: Runbooks, on-call setup, status page, incident communication
+- **SLA monitoring**: Uptime tracking, latency monitoring, error rate dashboards
+- **Support workflow**: Ticketing, escalation paths, customer communication channels
+- **Customer success**: Health scoring, usage analytics, renewal tracking
+
+#### Unresolved Startup Gaps
+If `research/mvp-gap.md` exists, check each unresolved gap:
+- Is it still unresolved?
+- Does it become more critical at enterprise scale?
+- Flag any startup gaps that are now enterprise deal-killers.
+
+### 4. Prioritise
+
+Tag each gap with:
+- **`hard-blocker`** — No enterprise deal closes without this. Non-negotiable.
+- **`soft-blocker`** — Most enterprise deals will require this. Can sometimes be worked around in early deals.
+- **`differentiator`** — Not required but gives competitive advantage in enterprise sales.
+
+Estimate effort for each: S / M / L / XL.
+
+### 5. Populate Next Steps
+
+Before writing, check which files exist to populate the `## Next Steps` section contextually. Include a **Recommended** item and 2–4 other applicable options. Choose the recommendation by the first matching condition:
+
+1. IF any `hard-blocker` lacks flow/design shape or a full implementation spec: `/user-flow-map [top blocker]` — map the highest-priority enterprise blocker into concrete screen flow, decisions, branches, states, and recovery paths before UI/layout planning.
+2. IF enterprise stakeholder journey context is missing: `/journey-map enterprise` — map enterprise stakeholder journeys before sequencing build work.
+3. IF startup gaps escalated and `research/mvp-gap.md` is missing or stale: `/mvp-gap` — re-evaluate startup readiness first.
+4. IF enterprise SLA or compliance gaps lack closure metrics: `/metrics` — define metrics covering enterprise SLAs.
+5. OTHERWISE: `/roadmap` — sequence the already-specced enterprise work into implementation phases.
+
+Only recommend `/roadmap` as the primary next step when every hard-blocker already has a full spec or is already tracked in `tasks/roadmap.md`, `tasks/todo.md`, `tasks/manual-todo.md`, `tasks/record-todo.md`, or `tasks/recurring-todo.md`.
+
+## Output
+
+### `specs/scale-audit.md` (or `specs/{slug}/scale-audit.md`)
+
+```markdown
+# Enterprise Scale Audit
+
+> Evaluated against: research/enterprise-icp.md (or research/{slug}/enterprise-icp.md)
+> Date: [current date]
+> Codebase state: [brief summary of what exists]
+
+## Summary
+[2-3 sentences: overall enterprise readiness and most critical gaps]
+
+## Hard Blockers
+- **[Gap title]** — [What's missing, which stakeholder it blocks, and why]. Effort: S/M/L/XL
+  _Start with:_ `/user-flow-map [topic]`
+- ...
+
+## Soft Blockers
+- **[Gap title]** — [What's missing and impact]. Effort: S/M/L/XL
+  _Start with:_ `/user-flow-map [topic]`
+- ...
+
+## Differentiators
+- **[Gap title]** — [What's missing and competitive advantage]. Effort: S/M/L/XL
+  _Start with:_ `/user-flow-map [topic]`
+- ...
+
+## Stakeholder Coverage Matrix
+| Stakeholder | Journey Covered? | Key Gaps |
+|-------------|-----------------|----------|
+| End users   | Partial/Yes/No  | ...      |
+| Team admin  | Partial/Yes/No  | ...      |
+| IT/Security | Partial/Yes/No  | ...      |
+| Procurement | Partial/Yes/No  | ...      |
+| Exec sponsor| Partial/Yes/No  | ...      |
+
+## Compliance Matrix
+| Standard | Status | Key Gaps |
+|----------|--------|----------|
+| SOC 2    | Not started/Partial/Ready | ... |
+| GDPR     | Not started/Partial/Ready | ... |
+| HIPAA    | N/A/Not started/Partial/Ready | ... |
+
+## Recommended Build Sequence
+[Ordered list: hard blockers first, then soft blockers, then differentiators.
+ Within each tier, order by: most deals unblocked per unit of effort.
+ Note dependencies — what must exist before other things can be built.]
+
+## Unresolved Startup Gaps (Escalated)
+[Gaps from research/mvp-gap.md that are now more critical at enterprise scale]
+
+## Next Steps
+
+**Recommended:** [first matching command from step 5] — [reason grounded in this audit]
+
+Other options:
+- [conditional items from step 5 — only include items whose conditions are met]
+```
+
+## Task Classification
+
+When this skill produces follow-up work, file it by execution semantics:
+
+- Immediately actionable implementation or documentation work goes in `tasks/todo.md`.
+- Human-only external actions tied to automated steps go in `tasks/manual-todo.md` with `_(blocks: Step N.X)_` or `_(after: Step N.X)_`; repo edits, SDK wiring, generated assets, local commands, tests, audits, and authenticated CLI/API work stay in `tasks/todo.md`.
+- One-time condition-gated records, baselines, or future measurements go in `tasks/record-todo.md` with source, condition, non-blocking reason, evidence, and promotion rule.
+- Cadence-based reviews, playtests, adoption checks, investor updates, retros, or docs-health checks go in `tasks/recurring-todo.md` with cadence, owner/agent, next due, evidence path, and escalation conditions.
+- Do not put non-blocking records or recurring obligations in `tasks/todo.md` unless they have been explicitly promoted into current execution work.
+
+## Constraints
+
+- **Do not make code changes.** Analysis only.
+- **Every gap must cite evidence** — missing middleware, absent SCIM endpoint, no audit log table, etc.
+- **Distinguish "first enterprise deal" from "100th enterprise deal."** Early enterprise sales can tolerate workarounds; at scale they can't. Be clear about which gaps matter when.
+- **Include `/user-flow-map` prompts** for each gap that lacks flow/design shape or a full spec. Use `/ux-variations --layout-mode` only when flow and UI requirements already exist but layout alternatives are missing.
+- **Do not duplicate work already tracked** in `tasks/roadmap.md`, `tasks/todo.md`, `tasks/manual-todo.md`, `tasks/record-todo.md`, or `tasks/recurring-todo.md`.
+- **If the codebase is minimal**, be honest about it — don't fabricate detailed infrastructure gaps for a prototype.
+
+## Alignment Page
+
+When this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page following `ALIGNMENT-PAGE.md` in this skill's directory. Output: `alignment/scale-audit-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/business-ops/codex/assumption-tracker/ALIGNMENT-PAGE.md

@@ -9,6 +9,8 @@ When this skill produces durable deliverables (research, specs, plans, reports,
 
 The tier is set per skill via `visual_tier` in SKILL.md frontmatter (or detected by the upgrade script). The bundled ALIGNMENT-PAGE.md receives tier-appropriate rendering guidance from the generator.
 
+**Context intake.** This skill declares `context_intake: artifact_only` (Artifact-driven). Work from concrete artifacts, data, logs, or existing instructions by default; ask concise clarification questions only when the available artifacts are missing, contradictory, or unsafe to interpret.
+
 **Alignment lifecycle.** Alignment pages have three lifecycle states. `review` is the draft/pre-approval page: it contains the complete deliverable preview, evidence, required inline gate questions, section feedback controls, local section-feedback YAML only after a section feedback choice is selected, and one bottom `Compile Responses` control. `confirmed` is the post-approval page after the agent has consumed final compiled response YAML, made any approved user-requested edits, and written or updated the approved canonical artifacts. A confirmed page is finished and current for the completed alignment cycle, but it remains amendable when later research changes or extends the conclusions. `amended` is a future revision of a confirmed page: archive the previous confirmed page first, mark what changed, preserve the prior approval record, and highlight the new evidence, decisions, or scope that changed the earlier conclusion.
 
 **Central alignment index.** When a research-producing skill writes or updates an HTML alignment page, also maintain the repository's central alignment index. Look for `alignment/index.html` at the repository root; if the target repo documents a different central alignment-index path, use that path and report it. If the index does not exist, create it as a self-contained HTML page that works from `file://`, links to every active `alignment/*.html` page except itself, and includes the newly written page. Every index entry must include the page's alignment date in a muted meta span after the link, formatted `YYYY-MM-DD`, for example `<a href="page.html">Title</a> <span class="meta">2026-06-09</span>`. The alignment date is the review or confirmed date written inside the page itself; new pages use today's date. If the index exists, update it instead of blindly appending: preserve valid existing entries, metadata, and entry dates; remove duplicate entries for the same page path; keep links repo-relative; and include the new or updated page. When updating an existing index, add a date only to entries that are missing one, deriving it from the page's internal alignment date, or from file history when the page has no internal date. If a `new` marker is used, combine it with the date as `<span class="meta">new · YYYY-MM-DD</span>`, and remove stale `new` markers from entries that are no longer the latest addition.
@@ -57,7 +59,9 @@ The tier is set per skill via `visual_tier` in SKILL.md frontmatter (or detected
 
 **Report-only research gates.** For report-only or pre-approval research skills, the first `review` alignment page must explicitly contain proposed research scope, source plan, assumptions/confidence, recommended output path, proposed file changes, and approval gates before synthesized research begins and before any working packet, canonical research, spec, or task file is created or updated.
 
-**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, and research-scope approval gates. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Perform the synthesized research, run required source/code checks, and write only a non-canonical working packet. Flat mode uses `research/_working/preliminary-assumption-tracker-research.md`; product-path mode uses `research/{slug}/_working/preliminary-assumption-tracker-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, research-scope approval gates, and a `Stage 2 Preview / Expected Review Format` section that shows the future Stage 2 review shape before research starts. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Perform the synthesized research, run required source/code checks, and write only a non-canonical working packet. Flat mode uses `research/_working/preliminary-assumption-tracker-research.md`; product-path mode uses `research/{slug}/_working/preliminary-assumption-tracker-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the complete working-packet substance as structured HTML review UI: purpose-built sections, tables, matrices, gates, cards, and tier-appropriate charts or diagrams that preserve every packet section, finding, caveat, and decision detail without summary loss. Raw Markdown packet text may appear only as a supplemental source view after the rendered review UI; do not make a `Full Preliminary Packet` or `Full Working Packet` raw Markdown dump, giant `<pre><code>` block, link-only view, or source-only view the primary review surface. Include the evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+
+**Stage 2 review-page template.** Stage 1 scope-review pages must include a `Stage 2 Preview / Expected Review Format` section that previews the exact section sequence, table shapes, evidence treatment, visual density, and approval gates the user will see after research; make it specific enough for the user to flag preferred content formats, grouping, labels, visuals, and evidence density before the agent does heavy research. After scope approval and research, the Stage 2 review page must include these sections as structured HTML, not as raw Markdown dumps: `Research Scope Approved` status block with approved scope, source plan, output paths, and unresolved caveats; `Executive Findings` or a skill-specific top-findings section with confidence labels; `Evidence Matrix` mapping claim, evidence/source/path, inference, confidence, assumptions, and decision impact; `Working Packet Review` with the complete working-packet substance rendered as purpose-built HTML sections, lists, tables, matrices, cards, and tier-appropriate charts or diagrams; `Alternatives / Rejected or Lower-Confidence Findings`; `Source Coverage & Gaps`; `Assumptions / Confidence Register`; `Proposed Canonical Artifacts & File Changes`; a required `User Format Preferences` gate asking whether the layout, tables, grouping, visuals, labels, and evidence density match expectations; and a required `Final Artifact Approval` gate for Stage 3 readiness. Raw Markdown packet text, search logs, or source notes may appear only as supplemental source views after the rendered review UI and never replace the Stage 2 review sections.
 
 **Risk-validation gates.** Render assumption/risk evidence coverage, confidence, candidate verdicts or mitigations, output-location/change-scope decisions, coverage checkpoint, and post-approval route as gates. Durable tracker outputs remain canonical markdown artifacts and must also be fully rendered in the alignment page. Apply the shared artifact-destination/proposed-file-changes de-duplication rule: combine them into one visual gate when they ask only the same path-destination question, and render separate gates when destination approval differs from downstream mutation scope, timing, or allowed files.
 

package/packs/business-ops/codex/assumption-tracker/SKILL.md

@@ -4,7 +4,7 @@ description: Extract and risk-rank assumptions from research docs — living reg
 type: analysis
 version: v0.2
 argument-hint: "[optional: focus area e.g. \"pricing\", \"ICP\", \"channel\"]"
-interview_depth: none
+context_intake: artifact_only
 visual_tier: visual
 ---
 

package/packs/business-ops/codex/burn-rate/ALIGNMENT-PAGE.md

@@ -9,6 +9,8 @@ When this skill produces durable deliverables (research, specs, plans, reports,
 
 The tier is set per skill via `visual_tier` in SKILL.md frontmatter (or detected by the upgrade script). The bundled ALIGNMENT-PAGE.md receives tier-appropriate rendering guidance from the generator.
 
+**Context intake.** This skill declares `context_intake: scoped` (Scoped intake). Ask only the focused questions needed to scope the research or analysis, then validate critical findings before building review artifacts.
+
 **Alignment lifecycle.** Alignment pages have three lifecycle states. `review` is the draft/pre-approval page: it contains the complete deliverable preview, evidence, required inline gate questions, section feedback controls, local section-feedback YAML only after a section feedback choice is selected, and one bottom `Compile Responses` control. `confirmed` is the post-approval page after the agent has consumed final compiled response YAML, made any approved user-requested edits, and written or updated the approved canonical artifacts. A confirmed page is finished and current for the completed alignment cycle, but it remains amendable when later research changes or extends the conclusions. `amended` is a future revision of a confirmed page: archive the previous confirmed page first, mark what changed, preserve the prior approval record, and highlight the new evidence, decisions, or scope that changed the earlier conclusion.
 
 **Central alignment index.** When a research-producing skill writes or updates an HTML alignment page, also maintain the repository's central alignment index. Look for `alignment/index.html` at the repository root; if the target repo documents a different central alignment-index path, use that path and report it. If the index does not exist, create it as a self-contained HTML page that works from `file://`, links to every active `alignment/*.html` page except itself, and includes the newly written page. Every index entry must include the page's alignment date in a muted meta span after the link, formatted `YYYY-MM-DD`, for example `<a href="page.html">Title</a> <span class="meta">2026-06-09</span>`. The alignment date is the review or confirmed date written inside the page itself; new pages use today's date. If the index exists, update it instead of blindly appending: preserve valid existing entries, metadata, and entry dates; remove duplicate entries for the same page path; keep links repo-relative; and include the new or updated page. When updating an existing index, add a date only to entries that are missing one, deriving it from the page's internal alignment date, or from file history when the page has no internal date. If a `new` marker is used, combine it with the date as `<span class="meta">new · YYYY-MM-DD</span>`, and remove stale `new` markers from entries that are no longer the latest addition.
@@ -57,7 +59,9 @@ The tier is set per skill via `visual_tier` in SKILL.md frontmatter (or detected
 
 **Report-only research gates.** For report-only or pre-approval research skills, the first `review` alignment page must explicitly contain proposed research scope, source plan, assumptions/confidence, recommended output path, proposed file changes, and approval gates before synthesized research begins and before any working packet, canonical research, spec, or task file is created or updated.
 
-**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, and research-scope approval gates. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Perform the synthesized research, run required source/code checks, and write only a non-canonical working packet. Flat mode uses `research/_working/preliminary-burn-rate-research.md`; product-path mode uses `research/{slug}/_working/preliminary-burn-rate-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, research-scope approval gates, and a `Stage 2 Preview / Expected Review Format` section that shows the future Stage 2 review shape before research starts. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Perform the synthesized research, run required source/code checks, and write only a non-canonical working packet. Flat mode uses `research/_working/preliminary-burn-rate-research.md`; product-path mode uses `research/{slug}/_working/preliminary-burn-rate-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the complete working-packet substance as structured HTML review UI: purpose-built sections, tables, matrices, gates, cards, and tier-appropriate charts or diagrams that preserve every packet section, finding, caveat, and decision detail without summary loss. Raw Markdown packet text may appear only as a supplemental source view after the rendered review UI; do not make a `Full Preliminary Packet` or `Full Working Packet` raw Markdown dump, giant `<pre><code>` block, link-only view, or source-only view the primary review surface. Include the evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+
+**Stage 2 review-page template.** Stage 1 scope-review pages must include a `Stage 2 Preview / Expected Review Format` section that previews the exact section sequence, table shapes, evidence treatment, visual density, and approval gates the user will see after research; make it specific enough for the user to flag preferred content formats, grouping, labels, visuals, and evidence density before the agent does heavy research. After scope approval and research, the Stage 2 review page must include these sections as structured HTML, not as raw Markdown dumps: `Research Scope Approved` status block with approved scope, source plan, output paths, and unresolved caveats; `Executive Findings` or a skill-specific top-findings section with confidence labels; `Evidence Matrix` mapping claim, evidence/source/path, inference, confidence, assumptions, and decision impact; `Working Packet Review` with the complete working-packet substance rendered as purpose-built HTML sections, lists, tables, matrices, cards, and tier-appropriate charts or diagrams; `Alternatives / Rejected or Lower-Confidence Findings`; `Source Coverage & Gaps`; `Assumptions / Confidence Register`; `Proposed Canonical Artifacts & File Changes`; a required `User Format Preferences` gate asking whether the layout, tables, grouping, visuals, labels, and evidence density match expectations; and a required `Final Artifact Approval` gate for Stage 3 readiness. Raw Markdown packet text, search logs, or source notes may appear only as supplemental source views after the rendered review UI and never replace the Stage 2 review sections.
 
 **Visual tier rendering.** This skill's alignment page uses the `visual` tier. Inline charts and diagrams are rendered via self-contained Canvas/SVG within the HTML file. Use the alignment chart snippet library (`scripts/alignment-chart-snippets.js`) as reference — copy needed chart functions directly into the page's `<script>` block. Charts must read CSS variables (`--chart-1` through `--chart-8`) for the data visualization palette. Every chart must include a `<table>` fallback, `aria-label` on canvas/SVG, and a "View as table" toggle. Data is embedded as inline JSON — no external fetches.
 

package/packs/business-ops/codex/burn-rate/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## v0.5 - 2026-06-12
+
+- Standardized active pack and skill install guidance on `npx skillpacks install <pack-or-skill>` instead of agent-native `/pack install` or `$pack install` recommendations.
+
 ## v0.4 - 2026-06-10
 
 - Added npm-aware install-route guidance for business-ops cross-pack recommendations, preserving `$pack install <pack>` inside Codex while offering `npx skillpacks install <pack>` from the project shell.

package/packs/business-ops/codex/burn-rate/SKILL.md

@@ -2,8 +2,8 @@
 name: burn-rate
 description: "Estimate monthly burn rate from infrastructure signals and calculate payback period against revenue projections"
 type: analysis
-version: v0.4
-interview_depth: light
+version: v0.5
+context_intake: scoped
 visual_tier: visual
 ---
 
@@ -70,11 +70,11 @@ Present analysis and ask for factual corrections, missing internal figures, or h
 2. Populate `## Next Steps` (3-5 items, "Pick one:" framing) — conditionally suggest the following based on what exists and what conflicts were found:
    - `$scale-audit` — same pack, always valid
    - `$reconcile-research` — same pack, always valid
-   - IF no `research/monetization.md`: check `.agents/project.json.enabled_packs` for `business-growth` — if `business-growth` is not enabled, recommend `$pack install business-growth` inside Codex, or `npx skillpacks install business-growth` from the project shell, first; if `business-growth` is enabled, recommend `$monetization` — Build pricing strategy informed by actual infrastructure costs
-   - IF `research/monetization.md` exists but unit economics differ: check `.agents/project.json.enabled_packs` for `business-growth` — if `business-growth` is not enabled, recommend `$pack install business-growth` inside Codex, or `npx skillpacks install business-growth` from the project shell, first; if `business-growth` is enabled, recommend `$monetization` — Update unit economics with infrastructure-grounded costs
-   - IF no `research/gtm.md`: check `.agents/project.json.enabled_packs` for `business-growth` — if `business-growth` is not enabled, recommend `$pack install business-growth` inside Codex, or `npx skillpacks install business-growth` from the project shell, first; if `business-growth` is enabled, recommend `$gtm` — Build go-to-market plan with cost-aware pricing
-   - IF no `research/metrics.md`: check `.agents/project.json.enabled_packs` for `business-growth` — if `business-growth` is not enabled, recommend `$pack install business-growth` inside Codex, or `npx skillpacks install business-growth` from the project shell, first; if `business-growth` is enabled, recommend `$metrics` — Define metrics to track burn rate health (cost per customer, infrastructure efficiency)
-   - IF codebase exists and optimization opportunities found: check `.agents/project.json.enabled_packs` for `product-design` — if `product-design` is not enabled, recommend `$pack install product-design` inside Codex, or `npx skillpacks install product-design` from the project shell, first; if `product-design` is enabled, recommend `$brainstorm` — Explore cost optimization as a feature priority
+   - IF no `research/monetization.md`: check `.agents/project.json.enabled_packs` for `business-growth` — if `business-growth` is not enabled, recommend `npx skillpacks install business-growth` from the project shell, first; if `business-growth` is enabled, recommend `$monetization` — Build pricing strategy informed by actual infrastructure costs
+   - IF `research/monetization.md` exists but unit economics differ: check `.agents/project.json.enabled_packs` for `business-growth` — if `business-growth` is not enabled, recommend `npx skillpacks install business-growth` from the project shell, first; if `business-growth` is enabled, recommend `$monetization` — Update unit economics with infrastructure-grounded costs
+   - IF no `research/gtm.md`: check `.agents/project.json.enabled_packs` for `business-growth` — if `business-growth` is not enabled, recommend `npx skillpacks install business-growth` from the project shell, first; if `business-growth` is enabled, recommend `$gtm` — Build go-to-market plan with cost-aware pricing
+   - IF no `research/metrics.md`: check `.agents/project.json.enabled_packs` for `business-growth` — if `business-growth` is not enabled, recommend `npx skillpacks install business-growth` from the project shell, first; if `business-growth` is enabled, recommend `$metrics` — Define metrics to track burn rate health (cost per customer, infrastructure efficiency)
+   - IF codebase exists and optimization opportunities found: check `.agents/project.json.enabled_packs` for `product-design` — if `product-design` is not enabled, recommend `npx skillpacks install product-design` from the project shell, first; if `product-design` is enabled, recommend `$brainstorm` — Explore cost optimization as a feature priority
 
 ## Deliverables
 

package/packs/business-ops/codex/burn-rate/archive/v0.4/SKILL.md

@@ -0,0 +1,112 @@
+---
+name: burn-rate
+description: "Estimate monthly burn rate from infrastructure signals and calculate payback period against revenue projections"
+type: analysis
+version: v0.4
+interview_depth: light
+visual_tier: visual
+---
+
+# Burn Rate — Infrastructure-Grounded Cost & Runway Analysis
+
+Invoke as `$burn-rate`.
+
+Analyzes infrastructure, third-party services, and team costs to estimate monthly burn rate, then calculates payback period and break-even against revenue projections. Bridges `$monetization` (unit economics) and `$scale-audit` (infrastructure readiness) with dollar-denominated cost projections.
+
+Default stance: assume the user does not know infrastructure pricing or SaaS cost structure in detail. Cost estimates must stand on detected services, cited pricing research, and explicit assumptions before asking the user for missing internal numbers.
+
+## Prerequisites
+
+- **Hard**: None — can run on any codebase.
+- **Soft**: Read if they exist — `research/monetization.md`, `research/metrics.md`, `research/gtm.md`, `research/icp.md`, `CLAUDE.md`, `README`.
+
+## Process
+
+### 0. Product-Path Scope Resolution
+
+Resolve research scope by product path before using code or app structure as a hint:
+
+1. If `$ARGUMENTS` names a non-archived `research/{slug}/` directory or a product-path ID whose `scope_path` points there, use that path. Treat `{slug}` as the product/app name, not the ICP, audience, or segment label.
+2. If `$ARGUMENTS` names only `research/_archive/{slug}/` or a manifest entry with `status: archived` or legacy `status: abandoned`, stop and warn that the path is archived; do not write or update scoped outputs there.
+3. Read `research/.progress.yaml` when present. Normalize legacy `active_path` to `active_paths` on read and write back `active_paths` on manifest updates. Treat legacy `abandoned` as `archived`; exclude `archived`, `abandoned`, `deferred`, `revisit_candidate`, `promoted`, and any `scope_path` under `research/_archive/` from active target selection.
+4. If active product paths exist in the manifest, use those paths. If multiple active paths exist, ask which one to target unless this skill explicitly supports cross-path output.
+5. If no active manifest target exists, list non-archived product directories under `research/`, excluding `research/_archive/` and dot directories. Auto-select only when exactly one exists; ask when multiple exist.
+6. If no product directories exist, use flat `research/` single-product mode.
+7. Detect monorepo/app/package structure only as a secondary hint. Suggest creating a missing `research/{slug}/` product path when code clearly exposes an app, but do not require code or monorepo detection before using `research/{slug}/`.
+
+When product path `{slug}` is active, read and write research under `research/{slug}/`, specs under `specs/{slug}/`, and treat top-level `research/*.md` files as flat-mode documents or cross-path summaries.
+
+### 1. Load Context & Detect Costs
+
+1. Read infrastructure files — containers, IaC, k8s, CI/CD, serverless, PaaS, cloud configs.
+2. Read dependency files for third-party service SDKs (payments, auth, monitoring, AI/ML, email, search, etc.).
+3. Read environment templates (`.env.example`, etc.) for API keys implying paid services.
+4. Read existing research docs for revenue projections, unit economics, customer counts.
+5. Build a cost inventory across: **Compute**, **Database**, **Storage**, **Third-party services**, **CI/CD**, **DNS/Domain**.
+6. For each detected service: search current pricing (min 4 queries), estimate monthly cost, note assumptions, assign confidence (High/Medium/Low).
+
+### 2. Interview — Fill Gaps
+
+Ask 2-3 focused questions:
+- Present detected infrastructure with estimated costs and cited pricing assumptions. Ask the user to correct factual inaccuracies or add missing internal costs, not to estimate from intuition.
+- Ask about team size, fully-loaded cost per person, and non-infra costs (marketing, tools, legal).
+- If revenue data not found in research docs, ask for current or projected MRR and cash on hand.
+
+### 3. Calculate & Present
+
+Compute with all assumptions visible:
+- **Monthly Burn Rate** — infrastructure + team + other, broken down by category with percentages.
+- **Runway** — cash on hand / monthly burn (only if cash position provided).
+- **Payback Period** — total investment / monthly net revenue (or "N/A — pre-revenue").
+- **Break-even Point** — three scenarios (conservative 50%, base, optimistic 150% growth). Skip if pre-revenue with no projections.
+- **Cost per Customer** — infrastructure and total cost per customer (only if count known).
+- **Cost Optimization Opportunities** — over-provisioned resources, cheaper alternatives, free tier headroom, reserved discounts.
+
+Present analysis and ask for factual corrections, missing internal figures, or hard constraints before writing.
+
+### 4. Downstream Impact & Next Steps
+
+1. Check if `research/monetization.md` exists and conflicts with burn rate findings (stale margins, divergent unit economics). Classify as None/Minor/Major.
+2. Populate `## Next Steps` (3-5 items, "Pick one:" framing) — conditionally suggest the following based on what exists and what conflicts were found:
+   - `$scale-audit` — same pack, always valid
+   - `$reconcile-research` — same pack, always valid
+   - IF no `research/monetization.md`: check `.agents/project.json.enabled_packs` for `business-growth` — if `business-growth` is not enabled, recommend `$pack install business-growth` inside Codex, or `npx skillpacks install business-growth` from the project shell, first; if `business-growth` is enabled, recommend `$monetization` — Build pricing strategy informed by actual infrastructure costs
+   - IF `research/monetization.md` exists but unit economics differ: check `.agents/project.json.enabled_packs` for `business-growth` — if `business-growth` is not enabled, recommend `$pack install business-growth` inside Codex, or `npx skillpacks install business-growth` from the project shell, first; if `business-growth` is enabled, recommend `$monetization` — Update unit economics with infrastructure-grounded costs
+   - IF no `research/gtm.md`: check `.agents/project.json.enabled_packs` for `business-growth` — if `business-growth` is not enabled, recommend `$pack install business-growth` inside Codex, or `npx skillpacks install business-growth` from the project shell, first; if `business-growth` is enabled, recommend `$gtm` — Build go-to-market plan with cost-aware pricing
+   - IF no `research/metrics.md`: check `.agents/project.json.enabled_packs` for `business-growth` — if `business-growth` is not enabled, recommend `$pack install business-growth` inside Codex, or `npx skillpacks install business-growth` from the project shell, first; if `business-growth` is enabled, recommend `$metrics` — Define metrics to track burn rate health (cost per customer, infrastructure efficiency)
+   - IF codebase exists and optimization opportunities found: check `.agents/project.json.enabled_packs` for `product-design` — if `product-design` is not enabled, recommend `$pack install product-design` inside Codex, or `npx skillpacks install product-design` from the project shell, first; if `product-design` is enabled, recommend `$brainstorm` — Explore cost optimization as a feature priority
+
+## Deliverables
+
+- `research/burn-rate.md` (or `research/{slug}/burn-rate.md`) — Full analysis: infrastructure cost breakdown, team/operational costs, total burn rate, revenue projections, payback/break-even scenarios, runway, cost per customer, optimization opportunities, assumptions, downstream impact, and next steps.
+- `research/burn-rate-interview.md` (or `research/{slug}/burn-rate-interview.md`) — Raw interview log with detected infrastructure, questions, responses, and key figures.
+
+Create the `research/` (or `research/{slug}/`) directory if it doesn't exist.
+
+## Task Classification
+
+When this skill produces follow-up work, file it by execution semantics:
+
+- Immediately actionable implementation or documentation work goes in `tasks/todo.md`.
+- Human-only external actions tied to automated steps go in `tasks/manual-todo.md` with `_(blocks: Step N.X)_` or `_(after: Step N.X)_`; repo edits, SDK wiring, generated assets, local commands, tests, audits, and authenticated CLI/API work stay in `tasks/todo.md`.
+- One-time condition-gated records, baselines, or future measurements go in `tasks/record-todo.md` with source, condition, non-blocking reason, evidence, and promotion rule.
+- Cadence-based reviews, playtests, adoption checks, investor updates, retros, or docs-health checks go in `tasks/recurring-todo.md` with cadence, owner/agent, next due, evidence path, and escalation conditions.
+- Do not put non-blocking records or recurring obligations in `tasks/todo.md` unless they have been explicitly promoted into current execution work.
+
+## Constraints
+
+- Every cost estimate must trace to a detected service or user-provided figure.
+- State all assumptions (tier, instance size, usage level) with confidence levels.
+- Present full analysis to user before writing output files.
+- Do not overwrite existing `research/burn-rate.md` without asking.
+- Minimum 4 web search queries for pricing data before presenting estimates.
+- Do not prescribe architecture changes — note optimization opportunities only.
+- Do not contradict existing `research/monetization.md` — reconcile differences.
+
+## Alignment Page
+
+When this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page following `ALIGNMENT-PAGE.md` in this skill's directory. Output: `alignment/burn-rate-{topic}.html`.
+
+## Default Shipping Contract
+
+Follow the shared shipping contract convention in CLAUDE.md.

package/packs/business-ops/codex/cohort-review/ALIGNMENT-PAGE.md

@@ -9,6 +9,8 @@ When this skill produces durable deliverables (research, specs, plans, reports,
 
 The tier is set per skill via `visual_tier` in SKILL.md frontmatter (or detected by the upgrade script). The bundled ALIGNMENT-PAGE.md receives tier-appropriate rendering guidance from the generator.
 
+**Context intake.** This skill declares `context_intake: artifact_only` (Artifact-driven). Work from concrete artifacts, data, logs, or existing instructions by default; ask concise clarification questions only when the available artifacts are missing, contradictory, or unsafe to interpret.
+
 **Alignment lifecycle.** Alignment pages have three lifecycle states. `review` is the draft/pre-approval page: it contains the complete deliverable preview, evidence, required inline gate questions, section feedback controls, local section-feedback YAML only after a section feedback choice is selected, and one bottom `Compile Responses` control. `confirmed` is the post-approval page after the agent has consumed final compiled response YAML, made any approved user-requested edits, and written or updated the approved canonical artifacts. A confirmed page is finished and current for the completed alignment cycle, but it remains amendable when later research changes or extends the conclusions. `amended` is a future revision of a confirmed page: archive the previous confirmed page first, mark what changed, preserve the prior approval record, and highlight the new evidence, decisions, or scope that changed the earlier conclusion.
 
 **Central alignment index.** When a research-producing skill writes or updates an HTML alignment page, also maintain the repository's central alignment index. Look for `alignment/index.html` at the repository root; if the target repo documents a different central alignment-index path, use that path and report it. If the index does not exist, create it as a self-contained HTML page that works from `file://`, links to every active `alignment/*.html` page except itself, and includes the newly written page. Every index entry must include the page's alignment date in a muted meta span after the link, formatted `YYYY-MM-DD`, for example `<a href="page.html">Title</a> <span class="meta">2026-06-09</span>`. The alignment date is the review or confirmed date written inside the page itself; new pages use today's date. If the index exists, update it instead of blindly appending: preserve valid existing entries, metadata, and entry dates; remove duplicate entries for the same page path; keep links repo-relative; and include the new or updated page. When updating an existing index, add a date only to entries that are missing one, deriving it from the page's internal alignment date, or from file history when the page has no internal date. If a `new` marker is used, combine it with the date as `<span class="meta">new · YYYY-MM-DD</span>`, and remove stale `new` markers from entries that are no longer the latest addition.
@@ -57,7 +59,9 @@ The tier is set per skill via `visual_tier` in SKILL.md frontmatter (or detected
 
 **Report-only research gates.** For report-only or pre-approval research skills, the first `review` alignment page must explicitly contain proposed research scope, source plan, assumptions/confidence, recommended output path, proposed file changes, and approval gates before synthesized research begins and before any working packet, canonical research, spec, or task file is created or updated.
 
-**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, and research-scope approval gates. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Perform the synthesized research, run required source/code checks, and write only a non-canonical working packet. Flat mode uses `research/_working/preliminary-cohort-review-research.md`; product-path mode uses `research/{slug}/_working/preliminary-cohort-review-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the full preliminary packet, evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+**Staged research workflow.** Heavy report-first research uses a scope-first three-stage approval workflow. Stage 1 is minimal scope discovery only: inspect enough repository, user, and source context to propose research scope, source plan, assumptions, output paths, and approval questions. Build the `review` alignment page before synthesized research. The page must render the proposed scope, available source categories, known context, assumptions/confidence, proposed working-packet and canonical output paths, research-scope approval gates, and a `Stage 2 Preview / Expected Review Format` section that shows the future Stage 2 review shape before research starts. Stop for final compiled response YAML approval of the research scope. Do not synthesize findings, rank candidates, recommend a path, or create working packets, canonical research, spec, or task files in Stage 1. Stage 2 starts only after final compiled response YAML approves the research scope with no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Perform the synthesized research, run required source/code checks, and write only a non-canonical working packet. Flat mode uses `research/_working/preliminary-cohort-review-research.md`; product-path mode uses `research/{slug}/_working/preliminary-cohort-review-research.md`. Existing raw evidence or search-log outputs may remain as supporting evidence when the skill contract already requires them, but synthesized deliverables stay in the working packet. Update the same `review` alignment page so it renders the complete working-packet substance as structured HTML review UI: purpose-built sections, tables, matrices, gates, cards, and tier-appropriate charts or diagrams that preserve every packet section, finding, caveat, and decision detail without summary loss. Raw Markdown packet text may appear only as a supplemental source view after the rendered review UI; do not make a `Full Preliminary Packet` or `Full Working Packet` raw Markdown dump, giant `<pre><code>` block, link-only view, or source-only view the primary review surface. Include the evidence matrix, assumptions/confidence register, source coverage gaps, proposed canonical file changes, and artifact approval gates. Partial compiled responses revise the working packet and review page, then remain in Stage 2. Stage 3 consumes final compiled response YAML for artifact approval only when it has `approval_status: ready-for-agent-review` and no unresolved `needs-clarification`, unresolved `down` feedback, or other unresolved negative feedback. Apply approved edits first, archive the working packet to `docs/history/archive/YYYY-MM-DD/HHMMSS/<original-working-path>`, remove the active working packet, write the approved canonical artifacts to the unchanged output paths, and convert the page to `confirmed` with the approval record preserved.
+
+**Stage 2 review-page template.** Stage 1 scope-review pages must include a `Stage 2 Preview / Expected Review Format` section that previews the exact section sequence, table shapes, evidence treatment, visual density, and approval gates the user will see after research; make it specific enough for the user to flag preferred content formats, grouping, labels, visuals, and evidence density before the agent does heavy research. After scope approval and research, the Stage 2 review page must include these sections as structured HTML, not as raw Markdown dumps: `Research Scope Approved` status block with approved scope, source plan, output paths, and unresolved caveats; `Executive Findings` or a skill-specific top-findings section with confidence labels; `Evidence Matrix` mapping claim, evidence/source/path, inference, confidence, assumptions, and decision impact; `Working Packet Review` with the complete working-packet substance rendered as purpose-built HTML sections, lists, tables, matrices, cards, and tier-appropriate charts or diagrams; `Alternatives / Rejected or Lower-Confidence Findings`; `Source Coverage & Gaps`; `Assumptions / Confidence Register`; `Proposed Canonical Artifacts & File Changes`; a required `User Format Preferences` gate asking whether the layout, tables, grouping, visuals, labels, and evidence density match expectations; and a required `Final Artifact Approval` gate for Stage 3 readiness. Raw Markdown packet text, search logs, or source notes may appear only as supplemental source views after the rendered review UI and never replace the Stage 2 review sections.
 
 **Risk-validation gates.** Render assumption/risk evidence coverage, confidence, candidate verdicts or mitigations, output-location/change-scope decisions, coverage checkpoint, and post-approval route as gates. Durable tracker outputs remain canonical markdown artifacts and must also be fully rendered in the alignment page. Apply the shared artifact-destination/proposed-file-changes de-duplication rule: combine them into one visual gate when they ask only the same path-destination question, and render separate gates when destination approval differs from downstream mutation scope, timing, or allowed files.
 

package/packs/business-ops/codex/cohort-review/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## v0.4 - 2026-06-12
+
+- Standardized active pack and skill install guidance on `npx skillpacks install <pack-or-skill>` instead of agent-native `/pack install` or `$pack install` recommendations.
+
 ## v0.3 - 2026-06-10
 
 - Added npm-aware install-route guidance for business-ops cross-pack recommendations, preserving `$pack install <pack>` inside Codex while offering `npx skillpacks install <pack>` from the project shell.

package/packs/business-ops/codex/cohort-review/SKILL.md

@@ -2,15 +2,15 @@
 name: cohort-review
 description: Post-launch metrics & funnel analysis — cohort retention, channel performance, and progress against targets from $metrics
 type: analysis
-version: v0.3
+version: v0.4
 argument-hint: "[file path to data, pasted data, or empty to be prompted]"
-interview_depth: none
+context_intake: artifact_only
 visual_tier: visual
 ---
 
 ## Pack Availability Guard
 
-When recommending a skill from another pack, verify the target pack is installed via `.agents/project.json` `enabled_packs`. If it is not enabled, recommend `$pack install <pack>` inside Codex, or `npx skillpacks install <pack>` from the project shell. After install, tell Codex users to start a fresh Codex CLI session if the `$` skill list remains stale. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
+When recommending a skill from another pack, verify the target pack is installed via `.agents/project.json` `enabled_packs`. If it is not enabled, recommend `npx skillpacks install <pack>` from the project shell. After install, tell Codex users to start a fresh Codex CLI session if the `$` skill list remains stale. Global skills are always valid. Skills from this same pack are valid because the current skill is already running from that pack.
 
 # Cohort Review — Post-Launch Metrics & Funnel Analysis