sprint-status · rohitg00 — Claude Code skill: what it does, how to install
sprint-status tracks parallel Claude Code sessions and prevents confusion by enforcing session headers and standardized status lines.
MIT ★ 2,966 updated 2026-09-29
/plugin marketplace add rohitg00/pro-workflow
/plugin install pro-workflow@pro-workflowWhat sprint-status does
The skill enforces orientation headers and clear terminal outputs when multiple Claude Code instances run together. Every plan or major decision begins with SESSION: project | branch | task. Sibling sessions are detected using pgrep, git worktree list, or markers in the temporary directory. Context stays clear across separate terminals.
Each milestone ends with one explicit status line: COMPLETE, COMPLETE_WITH_NOTES, BLOCKED, or NEEDS_INFO. The NEEDS_INFO tag requires a sensible fallback value so work continues without delay. The skill can also compile a consolidated SPRINT STATUS dashboard across all active branches.
What it helps with
- distinguish context and branches across parallel Claude Code sessions
- flag external blockers and dependencies with structured status lines
- prevent idle waiting by providing default options in questions
- assemble a unified sprint summary across active worktrees
Example prompts for the agent
- Show sprint status across all running sessions
- Run the auth test suite and report final status
- Check for active sibling sessions and format output
How to install sprint-status
1Plugin marketplace
/plugin marketplace add rohitg00/pro-workflow/plugin install pro-workflow@pro-workflowThis installs the whole pro-workflow plugin with all its skills
2Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill sprint-status -a claude-code3Manually: put the files in place
~/.claude/skills/sprint-status/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/sprint-status/
1Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill sprint-status -a codex2Manually: put the files in place
.agents/skills/sprint-status/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill sprint-status -a cursor2Manually: put the files in place
.cursor/skills/sprint-status/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install rohitg00/pro-workflow skills/sprint-status2Manually: put the files in place
.github/skills/sprint-status/SKILL.md1Skills CLI (Vercel)
npx skills add rohitg00/pro-workflow --skill sprint-status -a gemini-cli2Platform CLI
gemini skills install https://github.com/rohitg00/pro-workflow --path skills/sprint-statusManually: put the files in place
.devin/skills/sprint-status/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about sprint-status
How to install sprint-status in Claude Code?
Run /plugin marketplace add rohitg00/pro-workflow inside Claude Code, then run /plugin install pro-workflow@pro-workflow.
What does sprint-status do?
It forces the agent to prefix decisions with session identifiers and conclude every key step with a standardized status line.
How does it detect parallel sessions?
It looks for active processes via pgrep, inspects git worktree list, or checks session files inside $TMPDIR/pro-workflow/sessions/.
Source text
SKILL.md · MIT
---
name: sprint-status
description: Track parallel work sessions and prevent confusion across multiple Claude Code instances. Every major step ends with a status line. Every question re-states project, branch, and task.
user-invocable: true
---
# Sprint Status
When running multiple Claude Code sessions in parallel, confusion is the enemy. This skill ensures every session identifies itself and every step reports its state.
## Session Identification
Every response that involves a decision, plan, or significant action starts with orientation:
```text
SESSION: my-app | branch: feat/auth | task: Add JWT refresh tokens
```
This takes one line. It costs almost nothing. It prevents the user from applying feedback to the wrong session.
### Detecting Parallel Sessions
Check for sibling Claude Code processes:
```bash
pgrep -af "claude" | grep -v "$$" | head -5
```
Or check for active worktrees:
```bash
git worktree list 2>/dev/null
```
Or look for session markers (written by session-start.js / session-end.js):
```bash
ls $TMPDIR/pro-workflow/sessions/ 2>/dev/null | tail -5
```
If multiple sessions are detected, always include the session identification header. If only one session is running, include it at task boundaries and before presenting options.
## Status Lines
End every major step with exactly one status line. No ambiguity.
### STATUS: COMPLETE
All work for the current step is done. Ready to commit, merge, or move to the next task.
```text
STATUS: COMPLETE
Changed: src/auth/refresh.ts, src/auth/refresh.test.ts
Tests: 14 pass, 0 fail
Ready to commit.
```
### STATUS: COMPLETE_WITH_NOTES
Done, but flagging something the user should know about.
```text
STATUS: COMPLETE_WITH_NOTES
Changed: src/api/upload.ts
Tests: 8 pass, 0 fail
Notes:
- Upload size limit is hardcoded to 10MB, should be configurable
- No rate limiting on this endpoint yet (separate task)
```
Notes are for things that work but could be better. Not blockers — observations.
### STATUS: BLOCKED
Cannot proceed without user input or an external dependency.
```text
STATUS: BLOCKED
Blocker: Need database migration approved before writing the ORM layer
Waiting on: DBA approval for schema change in migrations/0042_add_tokens.sql
Can continue: Nothing else in this task until unblocked
```
### STATUS: NEEDS_INFO
Missing context to make a good decision. Asking before guessing.
```text
STATUS: NEEDS_INFO
Question: Should refresh tokens expire after 7 days or 30 days?
Impact: Changes token cleanup job schedule and storage requirements
Default if no preference: 7 days (more secure, standard practice)
```
Always provide a sensible default so the user can say "go with the default" without context-switching into the decision.
## Parallel Session Patterns
### Pattern 1: Feature + Tests
```text
Session 1: feat/auth → implementing JWT refresh
Session 2: feat/auth-tests → writing test suite for auth module
```
Both sessions work on the same feature but don't touch the same files. Session 2 can start writing tests against the interface before Session 1 finishes the implementation.
### Pattern 2: Independent Features
```text
Session 1: feat/upload → file upload endpoint
Session 2: feat/billing → billing webhook handler
Session 3: fix/login-bug → login redirect fix
```
Completely independent. Merge order doesn't matter.
### Pattern 3: Stacked Changes
```text
Session 1: feat/base-types → shared type definitions (must merge first)
Session 2: feat/api → API layer (depends on Session 1)
Session 3: feat/ui → UI layer (depends on Session 1)
```
Session 1 merges first. Sessions 2 and 3 rebase after. Flag the dependency in every status update.
## When to Report Status
| Event | Include Status? |
|-------|----------------|
| File edit completed | No (too granular) |
| Test suite run | Yes, if pass/fail changed |
| Phase completed (research, plan, implement) | Yes |
| Presenting options to user | Yes (with session header) |
| Hitting a blocker | Yes, immediately |
| Before asking a question | Yes (NEEDS_INFO) |
| After committing | Yes (COMPLETE) |
| End of session | Yes (final status) |
## Sprint Dashboard
When the user asks for status across sessions, compile a sprint view:
```text
SPRINT STATUS
Session 1: feat/auth STATUS: COMPLETE (ready to merge)
Session 2: feat/upload STATUS: BLOCKED (waiting on S3 creds)
Session 3: fix/login-bug STATUS: COMPLETE_WITH_NOTES (works, needs perf review)
```
## Anti-Patterns
- Skipping the session header when multiple sessions are active
- Using STATUS: COMPLETE when there are known issues (use COMPLETE_WITH_NOTES)
- Burying the status line in a paragraph (put it on its own line, at the end)
- Reporting status after every single edit (only at meaningful boundaries)
- Not providing a default with NEEDS_INFO (forces the user to context-switch fully)
- Saying "almost done" or "mostly working" instead of a concrete status
## Add to CLAUDE.md
```markdown
## Sprint Status
Every decision and plan starts with: SESSION: project | branch | task
End major steps with STATUS: COMPLETE | COMPLETE_WITH_NOTES | BLOCKED | NEEDS_INFO
NEEDS_INFO always includes a sensible default.
When parallel sessions are detected, always include session headers.
```
© Rohit Ghumare · MIT · rohitg00/pro-workflow
Similar skills
All skills for Agent setup: memory, context, orchestration →sprint-status by other authors comes first.