sprint-status skill
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.
Is the sprint-status skill safe?
Clean: nothing in its files matched our rules. We read 1 file in the folder on 2026-09-28.
No findings.
Install the sprint-status skill
A skill is a folder. Copy it into your agent's skills folder and the agent loads it when the task matches its description.
git clone --depth 1 https://github.com/rohitg00/pro-workflow.git /tmp/pro-workflow mkdir -p ~/.claude/skills cp -r /tmp/pro-workflow/skills/sprint-status ~/.claude/skills/sprint-status
In the Claude apps, zip the folder and upload it from the Skills settings. The folder on GitHub
The instructions your agent would load
SKILL.md as published, without the frontmatter. Read it on GitHub
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:
SESSION: my-app | branch: feat/auth | task: Add JWT refresh tokensThis 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:
pgrep -af "claude" | grep -v "$$" | head -5Or check for active worktrees:
git worktree list 2>/dev/nullOr look for session markers (written by session-start.js / session-end.js):
ls $TMPDIR/pro-workflow/sessions/ 2>/dev/null | tail -5If 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.
STATUS: COMPLETE
Changed: src/auth/refresh.ts, src/auth/refresh.test.ts
Tests: 14 pass, 0 fail
Ready to commit.STATUS: COMPLETEWITHNOTES
Done, but flagging something the user should know about.
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.
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 unblockedSTATUS: NEEDS_INFO
Missing context to make a good decision. Asking before guessing.
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
Session 1: feat/auth → implementing JWT refresh
Session 2: feat/auth-tests → writing test suite for auth moduleBoth 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
Session 1: feat/upload → file upload endpoint
Session 2: feat/billing → billing webhook handler
Session 3: fix/login-bug → login redirect fixCompletely independent. Merge order doesn't matter.
Pattern 3: Stacked Changes
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
Sprint Dashboard
When the user asks for status across sessions, compile a sprint view:
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 COMPLETEWITHNOTES)
- 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
## 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.More skills from rohitg00/pro-workflow
- Aagent-teamsCoordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.
- Aauto-setupAuto-configure quality gates, hooks, and settings for a new project. Detects project type and sets up appropriate tooling. Use when onboarding a new codebase.
- Abatch-orchestrationDecompose large-scale changes into independent units and spawn parallel agents in isolated worktrees. Use for migrations, refactors, codemods, and any change touching 10+ files with the same pattern.
- Cbug-captureCapture a user-reported defect as a durable GitHub issue written in the project's own domain language. Explores the codebase in parallel for context but never leaks file paths or line numbers into the issue. Use when the user reports a bug conversationally, runs a QA pass, or says "file an issue", "log this as a bug", "capture this".
- Acompact-guardSmart context compaction with state preservation. Saves critical files, task progress, and working state before compaction, restores after. Use before manual compact or when auto-compact triggers.
- Acontext-engineeringMaster the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction strategies, and context partitioning to keep AI sessions sharp and efficient.
- Acontext-optimizerOptimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.
- Acost-trackerTrack session costs, set budget alerts, and optimize token spend. Use to check costs mid-session or set spending limits.
- Adesign-engineeringApply interface craft when building or reviewing UI - motion, easing, timing, springs, component feel, and visual foundations. Use when building a component, animation, transition, hover or press state, modal, drawer, toast, or when polishing an interface so it feels right. Says "make this feel better", "add an animation", "polish the UI", "review this component".
- AdeslopRemove AI-generated code slop, unnecessary comments, and over-engineering from the current branch diff. Cleans up boilerplate, simplifies abstractions, strips defensive code, and in skill-file mode lints SKILL.md files for quality. Use when cleaning up code, simplifying, removing boilerplate, before committing, or when reviewing a skill before promoting it.
- Adomain-modelingBuild the project's shared language and bounded contexts before writing code, so names stay consistent and the agent stops paraphrasing domain concepts. Produces a CONTEXT.md glossary and decision records. Use at the start of a project or feature, or when the codebase and the people describing it speak different languages.
- Afile-watcherConfigure file watching hooks to auto-react to config changes, env file updates, and dependency modifications. Use to set up reactive workflows.