cc-codeconductor 1.4.2 → 1.5.1

package/presets/cursor/skills/spring-boot-feature/SKILL.md

@@ -1,6 +1,6 @@
 ---
 id: spring-boot-feature
-name: Spring Boot Feature Creation
+name: spring-boot-feature
 description: >
   Guides the creation of complete Spring Boot features following a structured,
   layer-by-layer workflow: entity, repository, service, controller, and tests.
@@ -43,10 +43,8 @@ outputs:
 quality:
   reviewed_by: codeconductor-core
   version: 0.1.0
-paths:
-  - "**/*.kt"
-  - "**/build.gradle.kts"
 ---
+
 # Spring Boot Feature Creation
 
 When asked to create a feature, follow these steps **in order**. Do not skip

package/presets/cursor/skills/spring-boot-kotlin/SKILL.md

@@ -1,6 +1,6 @@
 ---
 id: spring-boot-kotlin
-name: Spring Boot + Kotlin
+name: spring-boot-kotlin
 description: >
   Provides expert knowledge of Spring Boot conventions, Kotlin idioms, and MVC
   patterns for backend API development.

package/presets/cursor/skills/spring-boot-testing-strategy/SKILL.md

@@ -1,6 +1,6 @@
 ---
 id: spring-boot-testing-strategy
-name: Spring Boot Testing Strategy
+name: spring-boot-testing-strategy
 description: >
   Provides expert knowledge of the testing pyramid, test design principles, MockK patterns, and integration testing conventions for Spring Boot + Kotlin projects.
 

package/presets/cursor/skills/sqlalchemy/SKILL.md

@@ -1,6 +1,6 @@
 ---
 id: sqlalchemy
-name: SQLAlchemy
+name: sqlalchemy
 description: >
   SQLAlchemy 2.x patterns for async FastAPI projects: models, sessions, queries,
   bulk operations, transactions, and Alembic migrations.

package/presets/cursor/skills/tailwind-responsive-auditor/SKILL.md

@@ -1,6 +1,6 @@
 ---
 id: tailwind-responsive-auditor
-name: Tailwind Responsive Auditor
+name: tailwind-responsive-auditor
 description: >
   Audits Tailwind CSS usage ensuring mobile-first responsive utilities and clean classes.
 user-invokable: true

package/presets/cursor/skills/tdd-mutation-tester/SKILL.md

@@ -1,6 +1,6 @@
 ---
 id: tdd-mutation-tester
-name: TDD Mutation Tester
+name: tdd-mutation-tester
 description: >
   Performs simple mutation testing to verify test coverage and assertions.
 user-invokable: true

package/presets/gemini/commands/cc/api-contract.toml

@@ -9,11 +9,10 @@ API contract request: {{args}}
 
 Command: `api-contract` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command api-contract "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command api-contract "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile api-contract --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command api-contract --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile api-contract --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command api-contract --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command api-contract --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
 
 ---
 

package/presets/gemini/commands/cc/backlog.toml

@@ -14,11 +14,10 @@ deliver implementation — that is `/cc-openspec`.
 
 Command: `backlog` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command backlog "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command backlog "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile backlog --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command backlog --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile backlog --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command backlog --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command backlog --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
 
 ---
 

package/presets/gemini/commands/cc/clarify.toml

@@ -9,11 +9,10 @@ Clarify request: {{args}}
 
 Command: `clarify` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command clarify "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command clarify "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile clarify --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command clarify --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile clarify --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command clarify --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command clarify --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
 
 ---
 

package/presets/gemini/commands/cc/council.toml

@@ -10,11 +10,10 @@ Task request: {{args}}
 Command: `council` (fixed for this workflow — do not infer from user text)
 command: council
 
-1. Run: `npx cc-codeconductor ccep parse --command council "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command council "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile council --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command council --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile council --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command council --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command council --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
 
 ---
 

package/presets/gemini/commands/cc/db-migration.toml

@@ -9,11 +9,10 @@ Migration request: {{args}}
 
 Command: `db-migration` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command db-migration "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command db-migration "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile db-migration --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command db-migration --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile db-migration --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command db-migration --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command db-migration --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
    Canonical delivery order is test-before-implement whenever both phases apply.
 
 ---

package/presets/gemini/commands/cc/explore.toml

@@ -9,11 +9,10 @@ Explore request: {{args}}
 
 Command: `explore` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command explore "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command explore "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile explore --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command explore --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile explore --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command explore --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command explore --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
 
 ---
 

package/presets/gemini/commands/cc/feature.toml

@@ -33,11 +33,10 @@ unavailable visual or emulator checks remain pending rather than claimed complet
 
 Command: `feature` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command feature "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command feature "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile feature --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command feature --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile feature --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command feature --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command feature --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
    Canonical delivery order is test-before-implement whenever both phases apply.
 
 ---

package/presets/gemini/commands/cc/fix.toml

@@ -41,11 +41,10 @@ unavailable visual or emulator checks remain pending rather than claimed complet
 
 Command: `fix` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command fix "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command fix "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile fix --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command fix --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile fix --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command fix --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command fix --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
    Canonical delivery order is test-before-implement whenever both phases apply.
 
 ---

package/presets/gemini/commands/cc/handoff.toml

@@ -9,11 +9,10 @@ Handoff request: {{args}}
 
 Command: `handoff` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command handoff "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command handoff "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile handoff --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command handoff --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile handoff --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command handoff --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command handoff --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
 
 ---
 
@@ -32,6 +31,10 @@ pass/fail (not log dumps), open questions, the next `/cc:` command, plus links
 to the Delivery Ledger and verification evidence when they exist. Do not repeat
 the original request or transcript.
 
+If a Delivery Ledger exists, run `npx cc-codeconductor odd handoff --id <ledger-id> --output json`
+and use its `handoff` envelope as the source for these fields. Secret redaction
+still applies.
+
 Do not edit source or tests.
 
 ---

package/presets/gemini/commands/cc/iterative.toml

@@ -11,11 +11,10 @@ Iterative request: {{args}}
 
 Command: `iterative` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command iterative "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command iterative "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile iterative --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command iterative --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile iterative --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command iterative --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command iterative --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
    Canonical delivery order is test-before-implement whenever both phases apply.
 
 ---

package/presets/gemini/commands/cc/odd.toml

@@ -6,11 +6,12 @@ prompt = """
 ## Step 0 — CCEP Bootstrap
 
 ```bash
-bun run dev ccep parse --command odd "{{args}}"
-bun run dev ccep resolve --command odd "{{args}}"
-bun run dev ccep profile --command odd
+bun run dev ccep profile odd --output json
+bun run dev ccep compile --command odd --phase <phase-id> "{{args}}" --view prompt --output json
 ```
 
+Pass each subagent only the compiled `prompt` for its phase.
+
 Create a ledger only after authorization and tracked coordination. Read-only and small work do not create state.
 
 When ODD has verification evidence, include its RDD receipt in the ledger

package/presets/gemini/commands/cc/openspec.toml

@@ -37,11 +37,10 @@ unavailable visual or emulator checks remain pending rather than claimed complet
 
 Command: `openspec` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command openspec "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command openspec "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile openspec --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command openspec --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile openspec --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command openspec --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command openspec --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
    Canonical delivery order is test-before-implement whenever both phases apply.
 
 ---
@@ -152,7 +151,7 @@ For each pending TaskCard, run:
 npx cc-codeconductor openspec next
 ```
 
-Invoke the agent named on the card with **isolated** context (`/clear` between phases unless continuation is required):
+Invoke the agent named on the card as a subagent with **isolated** context (subagents already start fresh; do not `/clear` the main session between phases):
 
 | Phase | Agent | Role |
 |-------|-------|------|
@@ -208,5 +207,5 @@ Report completion: Task Cards executed, scorecard verdict, change folder path, f
 
 ## Skill
 
-Apply `.claude/skills/openspec/SKILL.md` for backlog format rules and state transitions.
+Apply `.gemini/skills/openspec/SKILL.md` for backlog format rules and state transitions.
 """

package/presets/gemini/commands/cc/pagespeed.toml

@@ -11,11 +11,10 @@ Produces a prioritized report in the current working directory.
 
 Command: `pagespeed` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command pagespeed "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command pagespeed "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile pagespeed --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command pagespeed --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile pagespeed --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command pagespeed --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command pagespeed --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
 
 ---
 
@@ -66,9 +65,8 @@ the following steps in order:
    the output filename: `{YYYY-MM-DD}_pagespeed-{hostname}-claude.md`.
 
 2. **Collect** — Call the PageSpeed Insights API for the requested strategy
-   (`mobile`, `desktop`, or `both`). Prefer the Bun scripts in
-   `~/.claude/skills/pagespeed-perf/scripts/run.ts` if Bun is available.
-   Otherwise, use `WebFetch` to call the PSI endpoint directly.
+   (`mobile`, `desktop`, or `both`) using `WebFetch` to call the PSI endpoint
+   directly.
 
 3. **Analyze** — Extract Core Web Vitals (LCP, INP, CLS, FCP, TTFB, TBT),
    identify the LCP element, enumerate third-party scripts by blocking time,

package/presets/gemini/commands/cc/prototype.toml

@@ -9,11 +9,10 @@ Prototype request: {{args}}
 
 Command: `prototype` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command prototype "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command prototype "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile prototype --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command prototype --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile prototype --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command prototype --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command prototype --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
 
 ---
 

package/presets/gemini/commands/cc/refactor.toml

@@ -34,11 +34,10 @@ If coverage is insufficient:
 
 Command: `refactor` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command refactor "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command refactor "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile refactor --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command refactor --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile refactor --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command refactor --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command refactor --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
 
 ---
 

package/presets/gemini/commands/cc/review.toml

@@ -40,11 +40,10 @@ unavailable visual or emulator checks remain pending rather than claimed complet
 
 Command: `review` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command review "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command review "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile review --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command review --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile review --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command review --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command review --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
 
 ---
 
@@ -110,6 +109,37 @@ Evaluate the diff against the following checklist:
 
 ---
 
+## Severity Rubric
+
+Classify every finding using these concrete anchors — not general judgment —
+so the same finding gets the same category on any run.
+
+**CRITICAL** (always):
+
+- Unauthenticated access to a protected resource
+- Injection (SQL, command, XSS) reachable from untrusted input
+- A secret or credential present in the diff
+- A destructive operation with no confirmation
+- The build or test suite is broken
+- A direct contradiction of an explicit acceptance criterion
+
+**WARNING**:
+
+- Missing test for a new branch or edge case
+- An error is silently swallowed — no log, no propagation
+- A change outside the declared scope
+- Inconsistent with an established pattern already in the module
+- Missing input validation in an internal function (not exposed at a trust boundary)
+
+**SUGGESTION**:
+
+- Style or naming
+- Minor readability
+- Speculative refactor that wasn't requested
+- Non-blocking micro-optimization
+
+---
+
 ## Step 3 — Review Report
 
 Produce a structured Review Report with findings in three categories:

package/presets/gemini/commands/cc/scorecard.toml

@@ -11,11 +11,10 @@ Scope: {{args}}
 
 Command: `scorecard` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command scorecard "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command scorecard "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile scorecard --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command scorecard --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile scorecard --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command scorecard --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command scorecard --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
 
 ---
 

package/presets/gemini/commands/cc/security.toml

@@ -44,11 +44,10 @@ payloads, malware, or attack procedures.
 
 Command: `security` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command security "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command security "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile security --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command security --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile security --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command security --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command security --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
    Canonical delivery order is test-before-implement whenever both phases apply.
 
 ---
@@ -59,7 +58,7 @@ If `graphify-out/graph.json` exists, run `graphify query "{{args}}"` (and
 `graphify path` / `graphify explain` when needed). Then invoke `repo-explorer`
 to map modules, conventions, and impact radius. Do not write code in this step.
 Record a Repo Map artifact before intake. Load the matching `security-*` skill
-for the named domain (see `.claude/skills/security-*/SKILL.md`). Keep the OWASP
+for the named domain (see `.gemini/skills/security-*/SKILL.md`). Keep the OWASP
 `security` skill for application-security reviews.
 
 ---

package/presets/gemini/commands/cc/spec-mutation.toml

@@ -18,11 +18,10 @@ Describe what behavior you want to implement. Include:
 
 Command: `spec-mutation` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command spec-mutation "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command spec-mutation "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile spec-mutation --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command spec-mutation --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile spec-mutation --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command spec-mutation --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command spec-mutation --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
    Canonical delivery order is test-before-implement whenever both phases apply.
 
 ---

package/presets/gemini/commands/cc/tdd-cycle.toml

@@ -18,11 +18,10 @@ Describe what behavior you want to implement. Include:
 
 Command: `tdd-cycle` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command tdd-cycle "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command tdd-cycle "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile tdd-cycle --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command tdd-cycle --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile tdd-cycle --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command tdd-cycle --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command tdd-cycle --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
    Canonical delivery order is test-before-implement whenever both phases apply.
 
 ---

package/presets/gemini/commands/cc/test-plan.toml

@@ -21,11 +21,10 @@ proceeding.
 
 Command: `test-plan` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command test-plan "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command test-plan "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile test-plan --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command test-plan --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile test-plan --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command test-plan --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command test-plan --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
 
 ---
 

package/presets/gemini/commands/cc/triage.toml

@@ -9,11 +9,10 @@ Triage request: {{args}}
 
 Command: `triage` (fixed for this workflow — do not infer from user text)
 
-1. Run: `npx cc-codeconductor ccep parse --command triage "{{args}}" --output json`
-2. Run: `npx cc-codeconductor ccep resolve --command triage "{{args}}" --output json`
-3. Run: `npx cc-codeconductor ccep profile triage --output json`
-4. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command triage --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
-5. Delegate to subagents using compiled CCEP prompts — never forward raw `{{args}}` to planners.
+1. Run: `npx cc-codeconductor ccep profile triage --output json` to get the phases and their roles.
+2. For each delegated phase, run: `npx cc-codeconductor ccep compile --command triage --phase <phase-id> "{{args}}" --view prompt --output json`
+3. After planner/intake JSON is available, run: `npx cc-codeconductor ccep evaluate --command triage --input <planner.json> --output json`. If `stop` is true, show questions or risks and wait for human input.
+4. Pass each subagent only the compiled `prompt` for its phase — never forward raw `{{args}}` to planners.
 
 ---