Add /delegate skill for multi-agent task delegation

.agents/skills/delegate/SKILL.md

@@ -0,0 +1,102 @@
+---
+name: delegate
+description: Code Cannon: Generate a scoped prompt for delegating work to another agent
+---
+
+> **Codex CLI:** This skill is triggered by description matching. State any arguments in your message. Sub-agent spawning is not supported — perform any review steps inline.
+
+---
+
+## What `/delegate` does
+
+`/delegate` generates a ready-to-paste prompt that gives another AI agent everything it needs to contribute code on the current branch. Run it during the planning gate of `/start` (Step 2), before saying `go`, to carve off part of the work for another agent.
+
+Each `/delegate` invocation also tells the lead agent to skip that work when it proceeds.
+
+---
+
+## Prerequisites
+
+`/delegate` relies on context already loaded by `/start`. If you are not in the middle of a `/start` planning gate (Case A Step 2 or Case B Step 2), say:
+
+> "`/delegate` is meant to be run during the planning step of `/start`, before you type `go`. Run `/start` first to load the issue context, then use `/delegate` to carve off tasks."
+
+Stop.
+
+If `$ARGUMENTS` is empty, ask: **"What task should the prompt describe?"** and wait for a response.
+
+---
+
+## Step 1 — Gather branch and diff context
+
+```bash
+git branch --show-current
+```
+
+```bash
+git diff --name-only dev...HEAD 2>/dev/null || git diff --name-only main...HEAD
+```
+
+---
+
+## Step 2 — Build the prompt
+
+Compose the following as a fenced markdown block (` ```markdown `) so the operator can copy it.
+
+Use the issue title, body, and agent implementation notes from the current `/start` session — do not re-fetch them.
+
+```markdown
+## Your task
+
+<$ARGUMENTS — the operator's description of the delegated work>
+
+## Branch
+
+You are on branch `<branch name>`. Stay on this branch.
+
+## Context
+
+**Issue #<number>: <title>**
+
+<issue body — include the full body as-is>
+
+<if there are agent implementation notes from the issue comments, include them under a "### Agent notes" subheading>
+
+## What's already been done on this branch
+
+<list of changed files from git diff, or "No changes yet — clean branch." if empty>
+
+## Rules
+
+- **Do not commit.** Leave all changes unstaged. The lead developer will handle commits.
+- **Be surgical.** Only modify what is necessary for your task. Do not refactor adjacent code, reorganize imports, or "improve" files outside the scope of your task.
+- **Do not start until the branch exists on the remote.** The lead developer will create and push the branch. Wait until `git checkout <branch name> && git pull origin <branch name>` succeeds before beginning work.
+```
+
+---
+
+## Step 3 — Present to operator and update lead scope
+
+Print the generated prompt preceded by:
+
+> Here's a delegation prompt for: **$ARGUMENTS**
+>
+> Review and edit as needed, then paste into your agent of choice after the lead agent has created and pushed the branch.
+
+Then print the fenced prompt block.
+
+After presenting, record internally that `$ARGUMENTS` has been delegated. When the operator says `go` and the lead agent proceeds to write code, it must skip the delegated work. If multiple `/delegate` invocations occur before `go`, accumulate all of them.
+
+After presenting, say:
+
+> Noted — the lead agent will skip this part when you say `go`. Run `/delegate <another task>` to delegate more, or type `go` to proceed.
+
+---
+
+## Hard rules
+
+- Never commit, push, or modify any files.
+- Never post to GitHub (no comments, labels, or issue updates).
+- Output only — the skill produces text for the operator to copy.
+- Do not suggest or name a specific agent to paste into — that is the operator's choice.
+<!-- generated by CodeCannon/sync.py | skill: delegate | adapter: codex | hash: 09337683 | DO NOT EDIT — run CodeCannon/sync.py to regenerate -->

.agents/skills/start/SKILL.md

@@ -109,7 +109,7 @@ Read the relevant code. Propose a concrete implementation approach. Be specific
 
 Say exactly:
 
-> **"Does this approach sound right? Type `go` to create a GitHub issue and branch, or share any questions/adjustments first."**
+> **"Does this approach sound right? Type `go` to create a GitHub issue and branch, or share any questions/adjustments first. To delegate part of the work to another agent, run `/delegate <task description>` before typing `go`."**
 
 Stop. Wait for the user to respond.
 
@@ -248,7 +248,7 @@ Tell the user:
 - What was previously done (from agent notes if present)
 - What appears to remain
 
-Ask: **"Does this match your understanding? Type `go` to start coding, or share any questions/adjustments first."**
+Ask: **"Does this match your understanding? Type `go` to start coding, or share any questions/adjustments first. To delegate part of the work to another agent, run `/delegate <task description>` before typing `go`."**
 
 Proceed only on unconditional approval. If the user's response includes conditions, questions, or adjustments, treat it as discussion — address their input and re-ask. If the user wants a fresh start, restart as Case A. If the user abandons, stop — nothing to clean up.
 
@@ -324,4 +324,4 @@ When done, say: **"The code is ready for review. Please run `make dev` and test
 - The issue is assigned to `@me` at creation. If you are creating a ticket on someone else's behalf, remove the assignee after creation with `gh issue edit <number> --remove-assignee @me`.
 - Apply resolved labels and milestone to every new issue. Label resolution order: per-invocation flag → pool selection from `bug, documentation, enhancement, chore` → omit `--label` entirely. Never apply a label outside `bug, documentation, enhancement, chore`.
 - Milestone resolution order: per-invocation flag → auto-detected from GitHub open milestones. Never prompt for a milestone more than once per invocation.
-<!-- generated by CodeCannon/sync.py | skill: start | adapter: codex | hash: 13614291 | DO NOT EDIT — run CodeCannon/sync.py to regenerate -->
+<!-- generated by CodeCannon/sync.py | skill: start | adapter: codex | hash: 834fb83e | DO NOT EDIT — run CodeCannon/sync.py to regenerate -->

.claude/commands/delegate.md

@@ -0,0 +1,97 @@
+Code Cannon: Generate a scoped prompt for delegating work to another agent
+
+---
+
+## What `/delegate` does
+
+`/delegate` generates a ready-to-paste prompt that gives another AI agent everything it needs to contribute code on the current branch. Run it during the planning gate of `/start` (Step 2), before saying `go`, to carve off part of the work for another agent.
+
+Each `/delegate` invocation also tells the lead agent to skip that work when it proceeds.
+
+---
+
+## Prerequisites
+
+`/delegate` relies on context already loaded by `/start`. If you are not in the middle of a `/start` planning gate (Case A Step 2 or Case B Step 2), say:
+
+> "`/delegate` is meant to be run during the planning step of `/start`, before you type `go`. Run `/start` first to load the issue context, then use `/delegate` to carve off tasks."
+
+Stop.
+
+If `$ARGUMENTS` is empty, ask: **"What task should the prompt describe?"** and wait for a response.
+
+---
+
+## Step 1 — Gather branch and diff context
+
+```bash
+git branch --show-current
+```
+
+```bash
+git diff --name-only dev...HEAD 2>/dev/null || git diff --name-only main...HEAD
+```
+
+---
+
+## Step 2 — Build the prompt
+
+Compose the following as a fenced markdown block (` ```markdown `) so the operator can copy it.
+
+Use the issue title, body, and agent implementation notes from the current `/start` session — do not re-fetch them.
+
+```markdown
+## Your task
+
+<$ARGUMENTS — the operator's description of the delegated work>
+
+## Branch
+
+You are on branch `<branch name>`. Stay on this branch.
+
+## Context
+
+**Issue #<number>: <title>**
+
+<issue body — include the full body as-is>
+
+<if there are agent implementation notes from the issue comments, include them under a "### Agent notes" subheading>
+
+## What's already been done on this branch
+
+<list of changed files from git diff, or "No changes yet — clean branch." if empty>
+
+## Rules
+
+- **Do not commit.** Leave all changes unstaged. The lead developer will handle commits.
+- **Be surgical.** Only modify what is necessary for your task. Do not refactor adjacent code, reorganize imports, or "improve" files outside the scope of your task.
+- **Do not start until the branch exists on the remote.** The lead developer will create and push the branch. Wait until `git checkout <branch name> && git pull origin <branch name>` succeeds before beginning work.
+```
+
+---
+
+## Step 3 — Present to operator and update lead scope
+
+Print the generated prompt preceded by:
+
+> Here's a delegation prompt for: **$ARGUMENTS**
+>
+> Review and edit as needed, then paste into your agent of choice after the lead agent has created and pushed the branch.
+
+Then print the fenced prompt block.
+
+After presenting, record internally that `$ARGUMENTS` has been delegated. When the operator says `go` and the lead agent proceeds to write code, it must skip the delegated work. If multiple `/delegate` invocations occur before `go`, accumulate all of them.
+
+After presenting, say:
+
+> Noted — the lead agent will skip this part when you say `go`. Run `/delegate <another task>` to delegate more, or type `go` to proceed.
+
+---
+
+## Hard rules
+
+- Never commit, push, or modify any files.
+- Never post to GitHub (no comments, labels, or issue updates).
+- Output only — the skill produces text for the operator to copy.
+- Do not suggest or name a specific agent to paste into — that is the operator's choice.
+<!-- generated by CodeCannon/sync.py | skill: delegate | adapter: claude | hash: 5f7a03dc | DO NOT EDIT — run CodeCannon/sync.py to regenerate -->

.claude/commands/start.md

@@ -104,7 +104,7 @@ Read the relevant code. Propose a concrete implementation approach. Be specific
 
 Say exactly:
 
-> **"Does this approach sound right? Type `go` to create a GitHub issue and branch, or share any questions/adjustments first."**
+> **"Does this approach sound right? Type `go` to create a GitHub issue and branch, or share any questions/adjustments first. To delegate part of the work to another agent, run `/delegate <task description>` before typing `go`."**
 
 Stop. Wait for the user to respond.
 
@@ -243,7 +243,7 @@ Tell the user:
 - What was previously done (from agent notes if present)
 - What appears to remain
 
-Ask: **"Does this match your understanding? Type `go` to start coding, or share any questions/adjustments first."**
+Ask: **"Does this match your understanding? Type `go` to start coding, or share any questions/adjustments first. To delegate part of the work to another agent, run `/delegate <task description>` before typing `go`."**
 
 Proceed only on unconditional approval. If the user's response includes conditions, questions, or adjustments, treat it as discussion — address their input and re-ask. If the user wants a fresh start, restart as Case A. If the user abandons, stop — nothing to clean up.
 
@@ -319,4 +319,4 @@ When done, say: **"The code is ready for review. Please run `make dev` and test
 - The issue is assigned to `@me` at creation. If you are creating a ticket on someone else's behalf, remove the assignee after creation with `gh issue edit <number> --remove-assignee @me`.
 - Apply resolved labels and milestone to every new issue. Label resolution order: per-invocation flag → pool selection from `bug, documentation, enhancement, chore` → omit `--label` entirely. Never apply a label outside `bug, documentation, enhancement, chore`.
 - Milestone resolution order: per-invocation flag → auto-detected from GitHub open milestones. Never prompt for a milestone more than once per invocation.
-<!-- generated by CodeCannon/sync.py | skill: start | adapter: claude | hash: 1829879a | DO NOT EDIT — run CodeCannon/sync.py to regenerate -->
+<!-- generated by CodeCannon/sync.py | skill: start | adapter: claude | hash: d7feebf1 | DO NOT EDIT — run CodeCannon/sync.py to regenerate -->

.cursor/rules/delegate.mdc

@@ -0,0 +1,103 @@
+---
+description: Code Cannon: Generate a scoped prompt for delegating work to another agent
+globs:
+alwaysApply: false
+---
+
+> **Cursor:** Trigger this skill via `@delegate` in Agent mode. State any arguments in your message. Sub-agent spawning is not supported — the automated review step in `/submit-for-review` must be done manually using the review-agent prompt.
+
+---
+
+## What `/delegate` does
+
+`/delegate` generates a ready-to-paste prompt that gives another AI agent everything it needs to contribute code on the current branch. Run it during the planning gate of `/start` (Step 2), before saying `go`, to carve off part of the work for another agent.
+
+Each `/delegate` invocation also tells the lead agent to skip that work when it proceeds.
+
+---
+
+## Prerequisites
+
+`/delegate` relies on context already loaded by `/start`. If you are not in the middle of a `/start` planning gate (Case A Step 2 or Case B Step 2), say:
+
+> "`/delegate` is meant to be run during the planning step of `/start`, before you type `go`. Run `/start` first to load the issue context, then use `/delegate` to carve off tasks."
+
+Stop.
+
+If `$ARGUMENTS` is empty, ask: **"What task should the prompt describe?"** and wait for a response.
+
+---
+
+## Step 1 — Gather branch and diff context
+
+```bash
+git branch --show-current
+```
+
+```bash
+git diff --name-only dev...HEAD 2>/dev/null || git diff --name-only main...HEAD
+```
+
+---
+
+## Step 2 — Build the prompt
+
+Compose the following as a fenced markdown block (` ```markdown `) so the operator can copy it.
+
+Use the issue title, body, and agent implementation notes from the current `/start` session — do not re-fetch them.
+
+```markdown
+## Your task
+
+<$ARGUMENTS — the operator's description of the delegated work>
+
+## Branch
+
+You are on branch `<branch name>`. Stay on this branch.
+
+## Context
+
+**Issue #<number>: <title>**
+
+<issue body — include the full body as-is>
+
+<if there are agent implementation notes from the issue comments, include them under a "### Agent notes" subheading>
+
+## What's already been done on this branch
+
+<list of changed files from git diff, or "No changes yet — clean branch." if empty>
+
+## Rules
+
+- **Do not commit.** Leave all changes unstaged. The lead developer will handle commits.
+- **Be surgical.** Only modify what is necessary for your task. Do not refactor adjacent code, reorganize imports, or "improve" files outside the scope of your task.
+- **Do not start until the branch exists on the remote.** The lead developer will create and push the branch. Wait until `git checkout <branch name> && git pull origin <branch name>` succeeds before beginning work.
+```
+
+---
+
+## Step 3 — Present to operator and update lead scope
+
+Print the generated prompt preceded by:
+
+> Here's a delegation prompt for: **$ARGUMENTS**
+>
+> Review and edit as needed, then paste into your agent of choice after the lead agent has created and pushed the branch.
+
+Then print the fenced prompt block.
+
+After presenting, record internally that `$ARGUMENTS` has been delegated. When the operator says `go` and the lead agent proceeds to write code, it must skip the delegated work. If multiple `/delegate` invocations occur before `go`, accumulate all of them.
+
+After presenting, say:
+
+> Noted — the lead agent will skip this part when you say `go`. Run `/delegate <another task>` to delegate more, or type `go` to proceed.
+
+---
+
+## Hard rules
+
+- Never commit, push, or modify any files.
+- Never post to GitHub (no comments, labels, or issue updates).
+- Output only — the skill produces text for the operator to copy.
+- Do not suggest or name a specific agent to paste into — that is the operator's choice.
+<!-- generated by CodeCannon/sync.py | skill: delegate | adapter: cursor | hash: 30cddce6 | DO NOT EDIT — run CodeCannon/sync.py to regenerate -->

.cursor/rules/start.mdc

@@ -110,7 +110,7 @@ Read the relevant code. Propose a concrete implementation approach. Be specific
 
 Say exactly:
 
-> **"Does this approach sound right? Type `go` to create a GitHub issue and branch, or share any questions/adjustments first."**
+> **"Does this approach sound right? Type `go` to create a GitHub issue and branch, or share any questions/adjustments first. To delegate part of the work to another agent, run `/delegate <task description>` before typing `go`."**
 
 Stop. Wait for the user to respond.
 
@@ -249,7 +249,7 @@ Tell the user:
 - What was previously done (from agent notes if present)
 - What appears to remain
 
-Ask: **"Does this match your understanding? Type `go` to start coding, or share any questions/adjustments first."**
+Ask: **"Does this match your understanding? Type `go` to start coding, or share any questions/adjustments first. To delegate part of the work to another agent, run `/delegate <task description>` before typing `go`."**
 
 Proceed only on unconditional approval. If the user's response includes conditions, questions, or adjustments, treat it as discussion — address their input and re-ask. If the user wants a fresh start, restart as Case A. If the user abandons, stop — nothing to clean up.
 
@@ -325,4 +325,4 @@ When done, say: **"The code is ready for review. Please run `make dev` and test
 - The issue is assigned to `@me` at creation. If you are creating a ticket on someone else's behalf, remove the assignee after creation with `gh issue edit <number> --remove-assignee @me`.
 - Apply resolved labels and milestone to every new issue. Label resolution order: per-invocation flag → pool selection from `bug, documentation, enhancement, chore` → omit `--label` entirely. Never apply a label outside `bug, documentation, enhancement, chore`.
 - Milestone resolution order: per-invocation flag → auto-detected from GitHub open milestones. Never prompt for a milestone more than once per invocation.
-<!-- generated by CodeCannon/sync.py | skill: start | adapter: cursor | hash: 2ff02ba9 | DO NOT EDIT — run CodeCannon/sync.py to regenerate -->
+<!-- generated by CodeCannon/sync.py | skill: start | adapter: cursor | hash: c2521db6 | DO NOT EDIT — run CodeCannon/sync.py to regenerate -->