Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tainn03-start-work
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
start-work- Description
- Start a Sisyphus work session from a Prometheus-generated plan. Manages boulder state, worktree setup, and delegates plan execution.
- License
- MIT
- Instructions
- 102 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Start Work Session
## Arguments
- `/start-work [plan-name] [--worktree <path>]`
- `plan-name` (optional): name or partial match of the plan to start
- `--worktree <path>` (optional): absolute path to an existing git worktree to work in
- If specified and valid: sets worktree_path in boulder.json
- If specified but invalid: run `git worktree add <path> <branch>` first
- If omitted: work directly in the current project directory (no worktree)
## Workflow
1. **Find available plans**: Search for Prometheus-generated plan files at `.sisyphus/plans/`
2. **Check for active boulder state**: Read `.sisyphus/boulder.json` if it exists
3. **Decision logic**:
- If `.sisyphus/boulder.json` exists AND plan is NOT complete (has unchecked boxes):
- Continue work on existing plan
- If no active plan OR plan is complete:
- List available plan files
- If ONE plan: auto-select it
- If MULTIPLE plans: show list with timestamps, ask user to select
4. **Worktree Setup** (ONLY when `--worktree` was explicitly specified):
1. `git worktree list --porcelain` - see available worktrees
2. Create: `git worktree add <absolute-path> <branch-or-HEAD>`
3. Update boulder.json to add `"worktree_path": "<absolute-path>"`
4. All work happens inside that worktree directory
5. **Create/Update boulder.json**:
```json
{
"active_plan": "/absolute/path/to/plan.md",
"started_at": "ISO_TIMESTAMP",
"plan_name": "plan-name",
"worktree_path": "/absolute/path/to/git/worktree"
}
```
6. **Read the plan file** and start executing tasks
## Output Format
When listing plans for selection:
```
Available Work Plans
1. [plan-name-1.md] - Modified: {date} - Progress: 3/10 tasks
2. [plan-name-2.md] - Modified: {date} - Progress: 0/5 tasks
Which plan would you like to work on? (Enter number or plan name)
```
When resuming existing work:
```
Resuming Work Session
Active Plan: {plan-name}
Progress: {completed}/{total} tasks
Worktree: {worktree_path}
Reading plan and continuing from last incomplete task...
```
## Task Breakdown (MANDATORY)
After reading the plan file, you MUST decompose every plan task into granular, implementation-level sub-steps and register ALL of them as todos BEFORE starting any work.
**How to break down**:
- Each plan checkbox item must be split into concrete, actionable sub-tasks
- Sub-tasks should be specific enough that each one touches a clear set of files/functions
- Include: file to modify, what to change, expected behavior, and how to verify
- Do NOT leave any task vague
**Example breakdown**:
Plan task: `- [ ] Add rate limiting to API`
Sub-tasks:
1. Create `src/middleware/rate-limiter.ts` with sliding window algorithm (max 100 req/min per IP)
2. Add RateLimiter middleware to `src/app.ts` router chain, before auth middleware
3. Add rate limit headers to response in `rate-limiter.ts`
4. Add test: verify 429 response after exceeding limit
5. Add test: verify headers are present on normal responses
## Worktree Completion
When working in a worktree and ALL plan tasks are complete:
1. Commit all remaining changes in the worktree
2. Sync `.sisyphus/` state back to main repo before removal
3. Switch to the main working directory
4. Merge the worktree branch into the current branch
5. If merge succeeds, clean up: `git worktree remove <worktree-path>`
6. Remove the boulder.json state
## Critical
- Always update boulder.json BEFORE starting work
- If worktree_path is set in boulder.json, all work happens inside that worktree directory
- Read the FULL plan file before delegating any tasksFrom tainn03/oh-my-copilot, MIT.
More from tainn03/oh-my-copilot
- 0.471score
codegraph
tainn03
Supercharges code exploration with a pre-indexed semantic knowledge graph.
SkillCFreshness: CClaude Code +9 - 0.471score
copilot-memories
tainn03
Guides the AI to persist context across sessions using 3-layer memory architecture (User/Repo/Session) with decision tree.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 17, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/tainn03/oh-my-copilot
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from tainn03
- 0.471score
codegraph
tainn03
Supercharges code exploration with a pre-indexed semantic knowledge graph.
SkillCFreshness: CClaude Code +9 - 0.471score
copilot-memories
tainn03
Guides the AI to persist context across sessions using 3-layer memory architecture (User/Repo/Session) with decision tree.
SkillCFreshness: CClaude Code +9
Cite this page
start-work skill. Agent Mart. https://agentmart.dev/skills/tainn03-start-work (last updated 2026-10-24)