claude-code-pilot 3.0.0 → 3.1.1

package/src/commands/{python-review.md → ccp/python-review.md}

@@ -1,4 +1,5 @@
 ---
+name: ccp:python-review
 description: Comprehensive Python code review for PEP 8 compliance, type hints, security, and Pythonic idioms. Invokes the python-reviewer agent.
 ---
 
@@ -17,7 +18,7 @@ This command invokes the **python-reviewer** agent for comprehensive Python-spec
 
 ## When to Use
 
-Use `/python-review` when:
+Use `/ccp:python-review` when:
 - After writing or modifying Python code
 - Before committing Python changes
 - Reviewing pull requests with Python code
@@ -77,7 +78,7 @@ pytest --cov=app --cov-report=term-missing
 ## Example Usage
 
 ```text
-User: /python-review
+User: /ccp:python-review
 
 Agent:
 # Python Code Review Report
@@ -171,10 +172,10 @@ Run: `black app/routes/user.py app/services/auth.py`
 
 ## Integration with Other Commands
 
-- Use `/tdd` first to ensure tests pass
-- Use `/code-review` for non-Python specific concerns
-- Use `/python-review` before committing
-- Use `/build-fix` if static analysis tools fail
+- Use `/ccp:tdd` first to ensure tests pass
+- Use `/ccp:code-review` for non-Python specific concerns
+- Use `/ccp:python-review` before committing
+- Use `/ccp:build-fix` if static analysis tools fail
 
 ## Framework-Specific Reviews
 

package/src/commands/{quality-gate.md → ccp/quality-gate.md}

@@ -1,10 +1,15 @@
+---
+name: ccp:quality-gate
+description: "Run the CCP quality pipeline on demand for a file or project scope"
+---
+
 # Quality Gate Command
 
 Run the CCP quality pipeline on demand for a file or project scope.
 
 ## Usage
 
-`/quality-gate [path|.] [--fix] [--strict]`
+`/ccp:quality-gate [path|.] [--fix] [--strict]`
 
 - default target: current directory (`.`)
 - `--fix`: allow auto-format/fix where configured

package/src/commands/{refactor-clean.md → ccp/refactor-clean.md}

@@ -1,3 +1,8 @@
+---
+name: ccp:refactor-clean
+description: "Safely identify and remove dead code with test verification"
+---
+
 # Refactor Clean
 
 Safely identify and remove dead code with test verification at every step.

package/src/commands/{resume-session.md → ccp/resume-session.md}

@@ -1,11 +1,12 @@
 ---
+name: ccp:resume-session
 description: Load the most recent session file from ~/.claude/sessions/ and resume work with full context from where the last session ended.
 ---
 
 # Resume Session Command
 
 Load the last saved session state and orient fully before doing any work.
-This command is the counterpart to `/save-session`.
+This command is the counterpart to `/ccp:save-session`.
 
 ## When to Use
 
@@ -17,10 +18,10 @@ This command is the counterpart to `/save-session`.
 ## Usage
 
 ```
-/resume-session                                                      # loads most recent file in ~/.claude/sessions/
-/resume-session 2024-01-15                                           # loads most recent session for that date
-/resume-session ~/.claude/sessions/2024-01-15-session.tmp           # loads a specific legacy-format file
-/resume-session ~/.claude/sessions/2024-01-15-abc123de-session.tmp  # loads a current short-id session file
+/ccp:resume-session                                                      # loads most recent file in ~/.claude/sessions/
+/ccp:resume-session 2024-01-15                                           # loads most recent session for that date
+/ccp:resume-session ~/.claude/sessions/2024-01-15-session.tmp           # loads a specific legacy-format file
+/ccp:resume-session ~/.claude/sessions/2024-01-15-abc123de-session.tmp  # loads a current short-id session file
 ```
 
 ## Process
@@ -34,7 +35,7 @@ If no argument provided:
 3. If the folder does not exist or has no matching files, tell the user:
    ```
    No session files found in ~/.claude/sessions/
-   Run /save-session at the end of a session to create one.
+   Run /ccp:save-session at the end of a session to create one.
    ```
    Then stop.
 
@@ -107,7 +108,7 @@ Note the gap — "⚠️ This session is from N days ago (threshold: 7 days). Th
 Read it and follow the same briefing process — the format is the same regardless of source.
 
 **Session file is empty or malformed:**
-Report: "Session file found but appears empty or unreadable. You may need to create a new one with /save-session."
+Report: "Session file found but appears empty or unreadable. You may need to create a new one with /ccp:save-session."
 
 ---
 
@@ -152,4 +153,4 @@ Ready to continue. What would you like to do?
 - Never modify the session file when loading it — it's a read-only historical record
 - The briefing format is fixed — do not skip sections even if they are empty
 - "What Not To Retry" must always be shown, even if it just says "None" — it's too important to miss
-- After resuming, the user may want to run `/save-session` again at the end of the new session to create a new dated file
+- After resuming, the user may want to run `/ccp:save-session` again at the end of the new session to create a new dated file

package/src/commands/ccp/review.md

@@ -0,0 +1,37 @@
+---
+name: ccp:review
+description: Request cross-AI peer review of phase plans from external AI CLIs
+argument-hint: "--phase N [--gemini] [--claude] [--codex] [--all]"
+allowed-tools:
+  - Read
+  - Write
+  - Bash
+  - Glob
+  - Grep
+---
+
+<objective>
+Invoke external AI CLIs (Gemini, Claude, Codex) to independently review phase plans.
+Produces a structured REVIEWS.md with per-reviewer feedback that can be fed back into
+planning via /ccp:plan-phase --reviews.
+
+**Flow:** Detect CLIs → Build review prompt → Invoke each CLI → Collect responses → Write REVIEWS.md
+</objective>
+
+<execution_context>
+@~/.claude/pilot/workflows/review.md
+</execution_context>
+
+<context>
+Phase number: extracted from $ARGUMENTS (required)
+
+**Flags:**
+- `--gemini` — Include Gemini CLI review
+- `--claude` — Include Claude CLI review (uses separate session)
+- `--codex` — Include Codex CLI review
+- `--all` — Include all available CLIs
+</context>
+
+<process>
+Execute the review workflow from @~/.claude/pilot/workflows/review.md end-to-end.
+</process>

package/src/commands/{rules-distill.md → ccp/rules-distill.md}

@@ -1,8 +1,9 @@
 ---
+name: ccp:rules-distill
 description: "Scan skills to extract cross-cutting principles and distill them into rules"
 ---
 
-# /rules-distill — Distill Principles from Skills into Rules
+# /ccp:rules-distill — Distill Principles from Skills into Rules
 
 Scan installed skills, extract cross-cutting principles, and distill them into rules.
 

package/src/commands/{rust-build.md → ccp/rust-build.md}

@@ -1,4 +1,5 @@
 ---
+name: ccp:rust-build
 description: Fix Rust build errors, borrow checker issues, and dependency problems incrementally. Invokes the rust-build-resolver agent for minimal, surgical fixes.
 ---
 
@@ -16,7 +17,7 @@ This command invokes the **rust-build-resolver** agent to incrementally fix Rust
 
 ## When to Use
 
-Use `/rust-build` when:
+Use `/ccp:rust-build` when:
 - `cargo build` or `cargo check` fails with errors
 - `cargo clippy` reports warnings
 - Borrow checker or lifetime errors block compilation
@@ -45,7 +46,7 @@ if command -v cargo-audit >/dev/null; then cargo audit; else echo "cargo-audit n
 ## Example Session
 
 ````text
-User: /rust-build
+User: /ccp:rust-build
 
 Agent:
 # Rust Build Resolution
@@ -177,9 +178,9 @@ The agent will stop and report if:
 
 ## Related Commands
 
-- `/rust-test` - Run tests after build succeeds
-- `/rust-review` - Review code quality
-- `/verify` - Full verification loop
+- `/ccp:rust-test` - Run tests after build succeeds
+- `/ccp:rust-review` - Review code quality
+- `/ccp:verify` - Full verification loop
 
 ## Related
 

package/src/commands/{rust-review.md → ccp/rust-review.md}

@@ -1,4 +1,5 @@
 ---
+name: ccp:rust-review
 description: Comprehensive Rust code review for ownership, lifetimes, error handling, unsafe usage, and idiomatic patterns. Invokes the rust-reviewer agent.
 ---
 
@@ -17,7 +18,7 @@ This command invokes the **rust-reviewer** agent for comprehensive Rust-specific
 
 ## When to Use
 
-Use `/rust-review` when:
+Use `/ccp:rust-review` when:
 - After writing or modifying Rust code
 - Before committing Rust changes
 - Reviewing pull requests with Rust code
@@ -71,7 +72,7 @@ if command -v cargo-audit >/dev/null; then cargo audit; else echo "cargo-audit n
 ## Example Usage
 
 ````text
-User: /rust-review
+User: /ccp:rust-review
 
 Agent:
 # Rust Code Review Report
@@ -131,10 +132,10 @@ Recommendation: Block merge until CRITICAL issue is fixed
 
 ## Integration with Other Commands
 
-- Use `/rust-test` first to ensure tests pass
-- Use `/rust-build` if build errors occur
-- Use `/rust-review` before committing
-- Use `/code-review` for non-Rust-specific concerns
+- Use `/ccp:rust-test` first to ensure tests pass
+- Use `/ccp:rust-build` if build errors occur
+- Use `/ccp:rust-review` before committing
+- Use `/ccp:code-review` for non-Rust-specific concerns
 
 ## Related
 

package/src/commands/{rust-test.md → ccp/rust-test.md}

@@ -1,4 +1,5 @@
 ---
+name: ccp:rust-test
 description: Enforce TDD workflow for Rust. Write tests first, then implement. Verify 80%+ coverage with cargo-llvm-cov.
 ---
 
@@ -17,7 +18,7 @@ This command enforces test-driven development methodology for Rust code using `#
 
 ## When to Use
 
-Use `/rust-test` when:
+Use `/ccp:rust-test` when:
 - Implementing new Rust functions, methods, or traits
 - Adding test coverage to existing Rust code
 - Fixing bugs (write failing test first)
@@ -36,7 +37,7 @@ REPEAT  -> Next test case
 ## Example Session
 
 ````text
-User: /rust-test I need a function to validate user registration
+User: /ccp:rust-test I need a function to validate user registration
 
 Agent:
 # TDD Session: Registration Validator
@@ -298,9 +299,9 @@ cargo test --no-fail-fast
 
 ## Related Commands
 
-- `/rust-build` - Fix build errors
-- `/rust-review` - Review code after implementation
-- `/verify` - Run full verification loop
+- `/ccp:rust-build` - Fix build errors
+- `/ccp:rust-review` - Review code after implementation
+- `/ccp:verify` - Run full verification loop
 
 ## Related
 

package/src/commands/{save-session.md → ccp/save-session.md}

@@ -1,4 +1,5 @@
 ---
+name: ccp:save-session
 description: Save current session state to a dated file in ~/.claude/sessions/ so work can be resumed in a future session with full context.
 ---
 
@@ -270,6 +271,6 @@ Then test with Postman — the response should include a `Set-Cookie` header.
 - Each session gets its own file — never append to a previous session's file
 - The "What Did NOT Work" section is the most critical — future sessions will blindly retry failed approaches without it
 - If the user asks to save mid-session (not just at the end), save what's known so far and mark in-progress items clearly
-- The file is meant to be read by Claude at the start of the next session via `/resume-session`
+- The file is meant to be read by Claude at the start of the next session via `/ccp:resume-session`
 - Use the canonical global session store: `~/.claude/sessions/`
 - Prefer the short-id filename form (`YYYY-MM-DD-<short-id>-session.tmp`) for any new session file

package/src/commands/ccp/secure-phase.md

@@ -0,0 +1,35 @@
+---
+name: ccp:secure-phase
+description: Retroactively verify threat mitigations for a completed phase
+argument-hint: "[phase number]"
+allowed-tools:
+  - Read
+  - Write
+  - Edit
+  - Bash
+  - Glob
+  - Grep
+  - Task
+  - AskUserQuestion
+---
+<objective>
+Verify threat mitigations for a completed phase. Three states:
+- (A) SECURITY.md exists — audit and verify mitigations
+- (B) No SECURITY.md, PLAN.md with threat model exists — run from artifacts
+- (C) Phase not executed — exit with guidance
+
+Output: updated SECURITY.md.
+</objective>
+
+<execution_context>
+@~/.claude/pilot/workflows/secure-phase.md
+</execution_context>
+
+<context>
+Phase: $ARGUMENTS — optional, defaults to last completed phase.
+</context>
+
+<process>
+Execute @~/.claude/pilot/workflows/secure-phase.md.
+Preserve all workflow gates.
+</process>

package/src/commands/{sessions.md → ccp/sessions.md}

@@ -1,10 +1,15 @@
+---
+name: ccp:sessions
+description: "Manage Claude Code session history - list, load, alias, and edit sessions"
+---
+
 # Sessions Command
 
 Manage Claude Code session history - list, load, alias, and edit sessions stored in `~/.claude/sessions/`.
 
 ## Usage
 
-`/sessions [list|load|alias|info|help] [options]`
+`/ccp:sessions [list|load|alias|info|help] [options]`
 
 ## Actions
 
@@ -13,11 +18,11 @@ Manage Claude Code session history - list, load, alias, and edit sessions stored
 Display all sessions with metadata, filtering, and pagination.
 
 ```bash
-/sessions                              # List all sessions (default)
-/sessions list                         # Same as above
-/sessions list --limit 10              # Show 10 sessions
-/sessions list --date 2026-02-01       # Filter by date
-/sessions list --search abc            # Search by session ID
+/ccp:sessions                              # List all sessions (default)
+/ccp:sessions list                         # Same as above
+/ccp:sessions list --limit 10              # Show 10 sessions
+/ccp:sessions list --date 2026-02-01       # Filter by date
+/ccp:sessions list --search abc            # Search by session ID
 ```
 
 **Script:**
@@ -53,10 +58,10 @@ for (const s of result.sessions) {
 Load and display a session's content (by ID or alias).
 
 ```bash
-/sessions load <id|alias>             # Load session
-/sessions load 2026-02-01             # By date (for no-id sessions)
-/sessions load a1b2c3d4               # By short ID
-/sessions load my-alias               # By alias name
+/ccp:sessions load <id|alias>             # Load session
+/ccp:sessions load 2026-02-01             # By date (for no-id sessions)
+/ccp:sessions load a1b2c3d4               # By short ID
+/ccp:sessions load my-alias               # By alias name
 ```
 
 **Script:**
@@ -116,8 +121,8 @@ if (session.metadata.lastUpdated) {
 Create a memorable alias for a session.
 
 ```bash
-/sessions alias <id> <name>           # Create alias
-/sessions alias 2026-02-01 today-work # Create alias named "today-work"
+/ccp:sessions alias <id> <name>           # Create alias
+/ccp:sessions alias 2026-02-01 today-work # Create alias named "today-work"
 ```
 
 **Script:**
@@ -130,7 +135,7 @@ const sessionId = process.argv[1];
 const aliasName = process.argv[2];
 
 if (!sessionId || !aliasName) {
-  console.log('Usage: /sessions alias <id> <name>');
+  console.log('Usage: /ccp:sessions alias <id> <name>');
   process.exit(1);
 }
 
@@ -156,8 +161,8 @@ if (result.success) {
 Delete an existing alias.
 
 ```bash
-/sessions alias --remove <name>        # Remove alias
-/sessions unalias <name>               # Same as above
+/ccp:sessions alias --remove <name>        # Remove alias
+/ccp:sessions unalias <name>               # Same as above
 ```
 
 **Script:**
@@ -167,7 +172,7 @@ const aa = require((process.env.CCP_CLAUDE_DIR||require('path').join(require('os
 
 const aliasName = process.argv[1];
 if (!aliasName) {
-  console.log('Usage: /sessions alias --remove <name>');
+  console.log('Usage: /ccp:sessions alias --remove <name>');
   process.exit(1);
 }
 
@@ -186,7 +191,7 @@ if (result.success) {
 Show detailed information about a session.
 
 ```bash
-/sessions info <id|alias>              # Show session details
+/ccp:sessions info <id|alias>              # Show session details
 ```
 
 **Script:**
@@ -233,7 +238,7 @@ if (aliases.length > 0) {
 Show all session aliases.
 
 ```bash
-/sessions aliases                      # List all aliases
+/ccp:sessions aliases                      # List all aliases
 ```
 
 **Script:**
@@ -279,22 +284,22 @@ $ARGUMENTS:
 
 ```bash
 # List all sessions
-/sessions list
+/ccp:sessions list
 
 # Create an alias for today's session
-/sessions alias 2026-02-01 today
+/ccp:sessions alias 2026-02-01 today
 
 # Load session by alias
-/sessions load today
+/ccp:sessions load today
 
 # Show session info
-/sessions info today
+/ccp:sessions info today
 
 # Remove alias
-/sessions alias --remove today
+/ccp:sessions alias --remove today
 
 # List all aliases
-/sessions aliases
+/ccp:sessions aliases
 ```
 
 ## Notes

package/src/commands/{setup-pm.md → ccp/setup-pm.md}

@@ -1,4 +1,5 @@
 ---
+name: ccp:setup-pm
 description: Configure your preferred package manager (npm/pnpm/yarn/bun)
 disable-model-invocation: true
 ---

package/src/commands/{setup-refresh.md → ccp/setup-refresh.md}

@@ -1,4 +1,5 @@
 ---
+name: ccp:setup-refresh
 description: "Re-scan codebase and update CLAUDE.md, rules, directory CLAUDE.md files, and architecture docs after major changes"
 ---
 
@@ -23,10 +24,10 @@ Present differences.
    - Scan for recognized directories: `src/`, `test/`, `tests/`, `lib/`, `app/`, `api/`, `scripts/`, `docs/`
    - For each existing recognized directory with a CLAUDE.md file:
      - Read the file's first line
-     - If it contains `<!-- Generated by /setup -- customize freely, /setup:refresh will regenerate if this comment is present -->`: regenerate using the same stack-aware templates from /setup Stage 4
+     - If it contains `<!-- Generated by /ccp:setup -- customize freely, /ccp:setup:refresh will regenerate if this comment is present -->`: regenerate using the same stack-aware templates from /ccp:setup Stage 4
      - If the marker is absent: skip (print: "Skipping {dir}/CLAUDE.md -- customized by user")
    - For each recognized directory WITHOUT a CLAUDE.md file:
-     - Generate a new one using the same stack-aware templates from /setup Stage 4
+     - Generate a new one using the same stack-aware templates from /ccp:setup Stage 4
    - Show summary of changes:
      ```
      Directory CLAUDE.md refresh:
@@ -40,7 +41,7 @@ Present differences.
 
 Show diff before writing.
 
-Note: MCP detection is NOT re-run during refresh. Binaries rarely change. Re-run `/setup` to re-detect MCP tools.
+Note: MCP detection is NOT re-run during refresh. Binaries rarely change. Re-run `/ccp:setup` to re-detect MCP tools.
 
 ## Step 3 — Commit