cc-devflow 4.5.6 → 4.5.8

package/docs/examples/full-design-blocked/README.md

@@ -4,7 +4,7 @@
 
 - Example version: `1.0.0`
 - Last reviewed: `2026-04-17`
-- Bound skills: `cc-roadmap@5.0.0`, `cc-plan@3.7.7`, `cc-do@1.6.2`, `cc-check@1.10.1`
+- Bound skills: `cc-roadmap@5.2.0`, `cc-plan@3.8.2`, `cc-do@1.6.3`, `cc-check@1.10.1`
 
 This example shows a requirement that **looked executable**, but `cc-check` correctly stopped it and sent it back to `cc-plan`.
 

package/docs/examples/full-design-blocked/ROADMAP.md

@@ -3,7 +3,7 @@
 ## Roadmap Meta
 
 - Roadmap version: `roadmap.v2`
-- Skill version: `5.0.0`
+- Skill version: `5.2.0`
 - Status: `active`
 - Last updated: `2026-04-16`
 - Owner / decider: `product-owner`
@@ -27,6 +27,21 @@
 - Adoption / trust bottleneck: admins will not trust bulk invite if seat usage and audit logs drift
 - Known unknowns: how duplicate users, seat limits, and partial imports should behave
 
+## AI Leverage Route Lens
+
+- Real user / operator: workspace admin onboarding 20-200 collaborators
+- Status quo workaround: paste individual invite emails or coordinate in external spreadsheets
+- Human-team effort for full scope: multiple weeks across product, engineering, billing, and support review
+- CC / agent effort for full scope: several hours once row semantics are approved, but unbounded before that
+- AI compression ratio: high after semantics freeze, low while the product contract is ambiguous
+- Complete-lake boundary: row classification, admin upload flow, billing-seat checks, and audit mapping after rule approval
+- Ocean boundary: SCIM, background retries, rollback wizard, and unspecified billing semantics
+- Scope recommendation: `sharp-wedge`
+- First success signal: admins can predict duplicate, invalid, and over-limit outcomes
+- Kill signal: duplicate and seat-limit semantics remain unresolved
+- Verdict: `sharp-wedge`
+- Missing evidence before ready-for-cc-plan: none recorded at route handoff; cc-check later reopened duplicate, invalid-row, partial-success, and seat-limit semantics
+
 ## Route Options
 
 | Shape | Why this could work | Why this may fail | Decision |

package/docs/examples/full-design-blocked/changes/REQ-002-bulk-invite-import/planning/design.md

@@ -4,7 +4,7 @@
 
 - Requirement version: `REQ-002.v2`
 - Design version: `design.v2`
-- CC-Plan skill version: `3.7.7`
+- CC-Plan skill version: `3.8.2`
 - Requirement ID: `REQ-002`
 - Design mode: `full-design`
 - Why not `tiny-design`: the feature crosses import parsing, invite rules, billing limits, duplicate handling, and audit logging
@@ -120,12 +120,43 @@
 - Deferred questions:
   - whether partial success needs an explicit rollback option
 
+## AI Leverage Decision Lens
+
+- Real user / operator: workspace admin onboarding larger teams
+- Status quo workaround: paste invite emails one by one or track them in spreadsheets
+- Human-team effort for full scope: multiple weeks across product, engineering, billing, and support review
+- CC / agent effort for full scope: several hours once row semantics are approved, but unbounded before that
+- AI compression ratio: high after semantics freeze, low while the product contract is ambiguous
+- Complete-lake boundary: row classification, admin upload flow, billing-seat checks, and audit mapping after rule approval
+- Ocean boundary: SCIM, background retries, rollback wizard, and unspecified billing semantics
+- Scope recommendation: `sharp-wedge`
+- Cost model: medium agent time after rule approval, high human review time until semantics are approved, high failure cost if billing or audit outcomes drift
+- Verdict: `sharp-wedge`
+- Missing evidence or pivot reason: none at plan approval; cc-check later reopened duplicate, invalid-row, partial-success, and seat-limit semantics before retry or cc-act
+
+## External Best-Practice Validation
+
+- Needed: Yes
+- Decision status: declined
+- Decision question: `D2`
+- Privacy guard: generalized terms only; no project names, private requirements, customer names, secrets, logs, or proprietary concepts
+- Generalized search terms:
+  - `bulk invite CSV import validation best practices`
+- Sources checked:
+- Conventional wisdom:
+- Current discourse:
+- Repo-fit verdict: skipped
+- Changes to options / tasks:
+  - keep the design blocked until row-outcome semantics are approved from internal evidence
+- Skipped reason: user kept the example repo-local for the blocked design
+
 ## Decision Questions
 
 | ID | Gate | Known evidence | Recommendation | User choice | Impact on `cc-do` | Status |
 |----|------|----------------|----------------|-------------|-------------------|--------|
 | D1 | approach-approval | Best-effort upload would let duplicate, invalid, and seat-limit semantics drift during execution | Choose Option B and freeze a rule matrix first | Option B | Keep execution blocked until row outcomes are modeled | answered |
-| D2 | ambiguity-blocker | Duplicate and seat-limit outcomes are still not explicit enough for tests or audit mapping | Answer the row-outcome matrix before task generation | pending | `cc-do` must not start implementation until this is answered | asked |
+| D2 | external-best-practice | Bulk CSV import semantics could benefit from generalized external practice, but this example stays repo-local | Stay repo-local for this blocked example | Stay repo-local | `cc-do` still must not start implementation until row outcomes are answered from internal evidence | answered |
+| D3 | review-blocker | Duplicate and seat-limit outcomes are still not explicit enough for final requirement proof | Answer the row-outcome matrix before retry or cc-act | pending | `cc-do` retry and `cc-act` must stay blocked until this is answered | asked |
 
 ## Design
 
@@ -176,7 +207,9 @@
 - Feasibility scan: pass
 - Source alignment: pass; roadmap still prioritizes trust over speed
 - PRD brief scan: pass for actors and stories; blocked on duplicate and seat-limit semantics
-- Decision question scan: blocked; `D2` is still unanswered
+- AI Leverage Decision Lens scan: pass at plan approval as a sharp wedge; cc-check later blocked final proof because product semantics were still unbounded evidence risk
+- External best-practice scan: pass; declined and recorded before task generation
+- Decision question scan: blocked; `D3` is still unanswered
 - UI / interaction review summary: result states are acceptable if semantics are frozen first
 - DX review summary: execution still needs a single row-outcome matrix
 - Auto-decided items: