docs: Standardize command references to unified /plan syntax

- Fix agent count discrepancy (24 → 21) in README.md
- Fix skills count discrepancy (18 → 16) in AGENTS.md
- Replace /saveplan with /plan --save across all docs
- Replace /loadplan with /plan --load across all docs
- Replace /dash with /plan --status in sync.md
- Fix setperms.md title mismatch (/init-tools → /setperms)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

AGENTS.md

@@ -5,7 +5,7 @@
 This is **claude-mods** - a collection of custom extensions for Claude Code:
 - **21 expert agents** for specialized domains (React, Python, AWS, etc.)
 - **10 slash commands** for workflows (/sync, /plan, /review, /atomise, etc.)
-- **18 skills** for CLI tool integration (git-workflow, code-stats, tool-discovery, etc.)
+- **16 skills** for CLI tool integration (git-workflow, code-stats, tool-discovery, etc.)
 
 ## Installation
 

README.md

@@ -10,7 +10,7 @@ Claude Code is powerful out of the box, but it has gaps. This toolkit fills them
 
 - **Session continuity** — TodoWrite tasks vanish when sessions end. We fix that with `/plan --save` and `/plan --load`, implementing Anthropic's [recommended pattern](https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents) for long-running agents.
 
-- **Expert-level knowledge on demand** — 24 specialized agents covering React, TypeScript, Python, AWS, PostgreSQL, and more. Each agent is deeply researched with real-world patterns, not generic advice.
+- **Expert-level knowledge on demand** — 21 specialized agents covering React, TypeScript, Python, AWS, PostgreSQL, and more. Each agent is deeply researched with real-world patterns, not generic advice.
 
 - **Modern CLI tools** — Stop using `grep`, `find`, and `cat`. Our rules automatically prefer `ripgrep`, `fd`, `eza`, and `bat` — 10-100x faster and token-efficient.
 

commands/explain.md

@@ -47,7 +47,7 @@ $ARGUMENTS
     │
     └─→ Step 5: Integrate
           ├─ Offer to save to ARCHITECTURE.md (if significant)
-          └─ Link to /saveplan if working on related task
+          └─ Link to /plan --save if working on related task
 ```
 
 ## Execution Steps
@@ -304,7 +304,7 @@ command -v tokei >/dev/null 2>&1 || echo "ℹ tokei not installed - skipping sta
 |---------|--------------|
 | `/review` | Review after understanding |
 | `/test` | Generate tests for explained code |
-| `/saveplan` | Save progress if working on related task |
+| `/plan --save` | Save progress if working on related task |
 | `/plan` | Add architectural insights to project plan |
 
 ## Persistence

commands/review.md

@@ -58,7 +58,7 @@ $ARGUMENTS
     │
     └─→ Step 6: Integration
           ├─ Auto-create TodoWrite for CRITICAL issues
-          ├─ Link to /saveplan for tracking
+          ├─ Link to /plan --save for tracking
           └─ Suggest follow-up: /test, /explain
 ```
 
@@ -260,7 +260,7 @@ The expert produces a structured review:
 
 - Run `/test src/auth/` to verify security fix
 - Run `/explain src/auth/login.ts` for deeper understanding
-- Use `/saveplan` to track these issues
+- Use `/plan --save` to track these issues
 ```
 
 ### Step 6: Integration
@@ -278,7 +278,7 @@ TodoWrite:
 **Link to session management:**
 ```
 Issues have been added to your task list.
-Run /saveplan to persist before ending session.
+Run /plan --save to persist before ending session.
 ```
 
 ## Severity System
@@ -423,7 +423,7 @@ command -v delta >/dev/null 2>&1 && git diff --cached | delta || git diff --cach
 |---------|--------------|
 | `/explain` | Deep dive into flagged code |
 | `/test` | Generate tests for issues found |
-| `/saveplan` | Persist review findings to session state |
+| `/plan --save` | Persist review findings to session state |
 | `/plan` | Add review findings to project plan |
 
 ## Workflow Examples
@@ -441,7 +441,7 @@ git commit -m "feat: add user auth"
 /review --pr 123 --thorough
 # Creates TodoWrite tasks for critical issues
 # Fix issues...
-/saveplan "Addressed review findings"
+/plan --save "Addressed review findings"
 ```
 
 ### Security Audit
@@ -455,6 +455,6 @@ git commit -m "feat: add user auth"
 - Reviews are suggestions, not absolute rules
 - Context matters - some "issues" may be intentional
 - CRITICAL issues are auto-added to TodoWrite
-- Use `/saveplan` to persist review tasks across sessions
+- Use `/plan --save` to persist review tasks across sessions
 - Expert agents provide framework-specific insights
 - Respects project conventions from AGENTS.md

commands/setperms.md

@@ -3,7 +3,7 @@ name: setperms
 description: "Set tool permissions for Claude Code. Configures allowed commands, rules, and preferences in .claude/ directory."
 ---
 
-# /init-tools
+# /setperms
 
 Initialize Claude Code with modern dev-shell-tools for a comfortable development experience.
 

commands/sync.md

@@ -111,7 +111,7 @@ Based on the current state, suggest 2-3 logical actions:
 3. **[Tertiary action or "Ready for new task"]**
 
 Examples of recommendations:
-- If saved state exists: "Run `/loadplan` to restore your previous session tasks"
+- If saved state exists: "Run `/plan --load` to restore your previous session tasks"
 - If plan exists and in-progress: "Continue with Step N: [description]"
 - If uncommitted changes: "Review and commit staged changes"
 - If no plan/state: "Ready for new task - no pending work detected"
@@ -140,9 +140,9 @@ Examples of recommendations:
 | Command | Relationship |
 |---------|--------------|
 | `/sync` | **This command** - Read project context |
-| `/loadplan` | Restore TodoWrite + plan state from saved JSON |
-| `/saveplan` | Persist TodoWrite + plan state to JSON |
-| `/dash` | Quick status dashboard (read-only) |
+| `/plan --load` | Restore TodoWrite + plan state from saved JSON |
+| `/plan --save` | Persist TodoWrite + plan state to JSON |
+| `/plan --status` | Quick status dashboard (read-only) |
 | `/plan` | Create or manage project plans |
 
 ### Typical Session Flow
@@ -151,10 +151,10 @@ Examples of recommendations:
 New Session
 ────────────────────────────────────────────────────────────────────────
   1. /sync              ← Read project context (always)
-  2. /loadplan          ← Restore saved tasks (if continuing work)
+  2. /plan --load       ← Restore saved tasks (if continuing work)
   3. ... work ...
-  4. /dash              ← Check status anytime
-  5. /saveplan          ← Save before ending session
+  4. /plan --status     ← Check status anytime
+  5. /plan --save       ← Save before ending session
 ```
 
 ## Notes

commands/testgen.md

@@ -61,7 +61,7 @@ $ARGUMENTS
     └─→ Step 6: Integration
           ├─ Auto-create TodoWrite for generated tests
           ├─ Suggest: run tests to verify
-          └─ Link to /saveplan for tracking
+          └─ Link to /plan --save for tracking
 ```
 
 ## Execution Steps
@@ -212,7 +212,7 @@ Tests generated: src/auth.test.ts
 Next steps:
 1. Run tests: npm test src/auth.test.ts
 2. Review and refine edge cases
-3. Use /saveplan to track test coverage goals
+3. Use /plan --save to track test coverage goals
 ```
 
 ---
@@ -764,7 +764,7 @@ command -v jq >/dev/null 2>&1 && cat package.json | jq '.devDependencies' || cat
 |---------|--------------|
 | `/review` | Review generated tests before committing |
 | `/explain` | Understand complex code before testing |
-| `/saveplan` | Track test coverage goals |
+| `/plan --save` | Track test coverage goals |
 | `/testgen` | This command |
 
 ---

docs/PLAN.md

@@ -27,7 +27,7 @@ Build modular, composable tools that:
 ## Implementation Steps
 
 ### Completed
-- [x] Session continuity commands (`/save`, `/load`)
+- [x] Session continuity commands (`/plan --save`, `/plan --load`)
   - Completed: 2025-11-27
   - Persists TodoWrite state to `.claude/session-cache.json`
   - Human-readable progress in `.claude/claude-progress.md`

news/2025-12-12_pulse.md

@@ -16,7 +16,7 @@ Here's the thing about agents: they're brilliant within a conversation, but ask
 
 Their answer draws on an unexpected source: how human engineers manage context when they step away from a problem. The patterns here (checkpointing, resumable state, explicit handoff protocols) feel like the missing manual for anyone building tools that need to survive a context window reset. It's the kind of deep thinking that usually stays inside research labs, now published for the rest of us to steal.
 
-**Pulse insights:** This speaks directly to our `/saveplan` and `/loadplan` commands. The checkpoint pattern they describe is almost exactly what we're doing with `session-cache.json`, but they've thought through edge cases we haven't—particularly around what to do when the world changes between sessions. Worth a close read.
+**Pulse insights:** This speaks directly to our `/plan --save` and `/plan --load` commands. The checkpoint pattern they describe is almost exactly what we're doing with `session-cache.json`, but they've thought through edge cases we haven't—particularly around what to do when the world changes between sessions. Worth a close read.
 
 ---
 
@@ -141,7 +141,7 @@ Real workflows from someone actually shipping with Claude Code daily. Less theor
 
 ## The Hit List
 
-1. **Read the harnesses article** — Anthropic's checkpoint patterns are worth stealing for `/saveplan`
+1. **Read the harnesses article** — Anthropic's checkpoint patterns are worth stealing for `/plan --save`
 2. **Clone compound engineering** — Every's plugin is free, battle-tested, and solves problems you haven't hit yet
 3. **Set up worktrunk** — Your parallel agent workflow is a mess without proper worktree isolation
 4. **Kill your footers** — Anthropic removed "Generated with Claude Code" from their plugins. Take the hint.

pulse/BRAND_VOICE.md

@@ -74,7 +74,7 @@ Replace "Why it matters" with "Pulse insights:" — a brief, opinionated take on
 - Can be snarky when warranted (e.g., "Another 'awesome' list, but this one's actually useful")
 
 **Examples:**
-- "Pulse insights: This slots directly into our session state problem. Worth stealing the checkpoint pattern for `/saveplan`."
+- "Pulse insights: This slots directly into our session state problem. Worth stealing the checkpoint pattern for `/plan --save`."
 - "Pulse insights: The parallel worktree approach could let us run multiple agents without the git conflicts. Time for an experiment."
 - "Pulse insights: Mostly relevant if you're building MCP servers. If you're just using Claude Code, bookmark it for later."
 
@@ -168,6 +168,6 @@ Always link the source name to its parent site:
 >
 > Here's the thing about agents: they're brilliant within a conversation, but ask them to remember what happened yesterday and you're back to square one. The Anthropic team has been wrestling with this exact problem—how do you build harnesses that let agents work across sessions without losing their minds? Their answer draws on an unexpected source: how human engineers manage context when they step away from a problem. The patterns here (checkpointing, resumable state, explicit handoff protocols) feel like the missing manual for anyone building tools that need to survive a context window reset.
 >
-> **Pulse insights:** This speaks directly to our `/saveplan` and `/loadplan` commands. The checkpoint pattern they describe is almost exactly what we're doing with `session-cache.json`, but they've thought through edge cases we haven't. Worth a close read to see if we should adopt their handoff protocol.
+> **Pulse insights:** This speaks directly to our `/plan --save` and `/plan --load` commands. The checkpoint pattern they describe is almost exactly what we're doing with `session-cache.json`, but they've thought through edge cases we haven't. Worth a close read to see if we should adopt their handoff protocol.
 
 *Now it sounds like someone actually read it and has opinions.*