sprint-status
Skill4 starsChanged 46 days agoMITView on GitHub
Read-only sprint status from artifacts — story states, tests/CI evidence, blockers, the dependency-update queue, burn, risk to the sprint goal. Use for 'where are we' during a sprint.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- striderZA/OpenCodeGameStudiostheir own version, first seen Nov 4, 2026
- Donchitos/Claude-Code-Game-Studiostheir own version, first seen Oct 19, 2026
- venus2099/codex-game-studiostheir own version, first seen Oct 17, 2026
- HunLuanZhiZhu/Game-Studios-Plugintheir own version, first seen Oct 5, 2026
- rohitg00/pro-workflowtheir own version, first seen Sep 29, 2026
- dawn840705/claude-code-studiostheir own version, first seen Aug 28, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- rohitg00/pro-workflow★ 2.9ksame name
- striderZA/OpenCodeGameStudios★ 118same name
- cenconq25/claude-code-app-studio★ 40same name
- dawn840705/codex-code-studios★ 17same name
- lilangMax/ClaudeCodeGameStudios★ 8same name
- hongyuanc/codex-game-studios★ 5same name
- dawn840705/claude-code-studios★ 1same name
- HunLuanZhiZhu/Game-Studios-Plugin★ 1same name
- philpalmieri/engineering-manager-skills★ 1same name
1 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository52 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- testing/CLAUDE.mdCLAUDE.md
- a11y-auditSkill
- adoptSkill
- api-contractSkill
- architecture-decisionSkill
- architecture-reviewSkill
- backlogSkill
- brainstormSkill
- changelogSkill
- code-reviewSkill
- collaboration-protocolSkill
- create-storiesSkill
- data-modelSkill
- dependency-auditSkill
- deploySkill
- design-systemSkill
- dev-storySkill
- docsSkill
- feature-specSkill
- game-conceptSkill
- hardenSkill
- helpSkill
- hotfixSkill
- impactSkill
- incidentSkill
- initSkill
- migrateSkill
- pentestSkill
- perf-auditSkill
- product-specSkill
- qa-planSkill
- refactorSkill
- release-checklistSkill
- retrospectiveSkill
- security-auditSkill
- setup-stackSkill
- skill-improveSkill
- skill-testSkill
- sprint-planSkill
- stack-updateSkill
- startSkill
- story-doneSkill
- team-featureSkill
- team-gameSkill
- team-releaseSkill
- team-securitySkill
- tech-debtSkill
- test-setupSkill
- threat-modelSkill
- updateSkill
- ux-specSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Read-only: no file is written and no status changes.
- Very specific: line 51
Never report starts minus stops.
“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Sprint Status
Reply in the project conversation language (CLAUDE.md → Language); code, identifiers, paths and commit messages stay in English.
Read-only: no file is written and no status changes. Source: artefacts (story files, git log, CI), not claims.
In the commands below, <hooks> is .claude/hooks/ in copy mode and ${CLAUDE_PLUGIN_ROOT}/hooks/ in plugin mode.
Phase 1: Data
- The sprint.
production/sprints/sprint-NN.mdfor the sprint number in the argument, else the latest file inproduction/sprints/. Its header givesStatus:, the start and end dates, the goal and the capacity. No sprint file → reportNo sprint in production/sprints/ — run /sprint-plan, give no verdict, and go straight to the next step with/sprint-planas the Recommended option. - Stories: the sprint's stories and their states from the roadmap's sprint block (the single source
/story-donewrites); the sprint file's## Storiestable compared with it row by row — a differing row is drift, counted, never the source. - Commits:
git log --since <sprint start>on thefeat/S-*branches. - CI and the dependency queue (only when
ghexists):gh run list, andgh pr list --state open --author app/dependabot --json number,title,createdAt,statusCheckRollup(Renovate:--author app/renovate). - Session state:
production/session-state/active.md. - Findings: open BLOCKING findings in
production/findings.md. - Who did the work:
<hooks>agent-stats.sh --since <sprint start>, which readsproduction/session-logs/agent-audit.logand includes theparent-writecount, code the session wrote instead of an engineer (coordination-rules § Subagents). The numbers come from the log thelog-agenthook keeps, never from memory of what ran. - Burn inputs: for every story in the sprint's roadmap block (step 2), the estimate (
~Nhon itsproduction/roadmap.mdline) and, when it is Done, its close date — the author date of thedocs: close S-NNNcommit, searched across every ref (git log --all --since <sprint start> --format='%as %s' --grep='^docs: close S-'): a close commit left on afeat/S-*branch after a declined merge is not in HEAD's history, and step 3 already walks those branches. No close commit for a Done story → the date the story's roadmap line was ticked: the roadmap'sUpdated:line when it names/story-done S-NNN, else the author date of the commit that ticked the line (git log --all --format=%as -S'[x] [S-NNN]' -- production/roadmap.md | tail -1). Never the story card'sActual:line — it is a duration, not a date. Estimates missing on any planned story → burn is counted in stories, not hours, and the report says so.
Phase 2: Report
- Print the report:
Sprint NN — goal: … status: active | closed YYYY-MM-DD | overdue (end date passed, not closed) days left: N Done N / In Progress N / Ready N / Blocked N sprint file ≠ roadmap: N rows Burn: X h of Y h closed (N of M stories) · day D of T · on a straight line Z h would be closed by now day 1: 0 · day 2: 8 h · day 3: 8 h · day 4: 18 h · … (cumulative, one entry per day since the sprint start) Blockers: … Risk to the goal: low | medium | high (why) In progress now: S-NNN (branch, last commit, tests: ✅/❌) Dependency PRs: N open (green N · red N · majors N · oldest YYYY-MM-DD) Agents: N runs all-time · M this sprint go-engineer N · vue-engineer N · appsec-engineer N · … (top five, plugin and copy-mode names merged) U agent(s) started and never closed — cut off at the turn limit, or still running R run(s) predate the agent ids — they cannot be paired, so "never closed" covers only the A agents that can ! F run(s) of non-studio agents — routing went around the roster ! P code file(s) written by the session itself (parent-write) - Burn (Phase 1 step 8): closed against planned, per day since the sprint start. Planned = the sum of
~Nhover the sprint's stories (or their count); closed = the same sum over the stories Done, each counted on its close date; the per-day line is cumulative from day 1 (the sprint start) to today,Tis the number of calendar days in the sprint. The straight-line expectation isplanned × D / T. Closed behind that line by more than one day's share (planned / T) → a line under Risk to the goal (burn: X h closed, Z h expected by day D). No story Done yet on day 1 or 2 is not a risk. Stories without an estimate make it a count (N of M stories), never an invented number. - Dependency PRs. A dependency PR older than the sprint start, or any red one, is a line under Risk to the goal with
/sprint-plan(its Phase 2) as the fix. Withoutghthe line readsDependency PRs: n/a (no gh). - Agent lines — the three counts are read differently:
- The non-studio count is a fact: the name is in the line, so routing went around the roster and the specialist's rules, stack reference and memory were not in the room.
- The unclosed agents are a lead, not a verdict: an agent started and never closed was cut off at its turn limit or is still running. The story it was given either came back half-done or was finished by the parent, so check the story results.
- The parent-write count (
P code file(s) written by the session itself) is a fact from theparent-writehook: product code or tests the parent wrote instead of a Tier-3 engineer, each file logged asParentWritein the audit log — a rule with no observer was broken on a real project, so the count is printed even when the stories are green. - Never report starts minus stops.
SubagentStartfires on every resume of the same agent, so that difference counts resumes, not lost work. - Each of these three lines goes under Risk to the goal when it is not zero; for parent-write the line reads
parent-write: P file(s) — engineer rule bypassed (coordination-rules § Subagents).
- Discrepancies on a separate line: "Done without a test/PR" for every story marked Done with no test or PR behind it.
sprint file ≠ roadmap: N rowsnames the rows; the fix is/retrospectiveat close (it reconciles them), never an edit from here. 5a. Sprint over and not closed: a sprint that isoverdue, or whose every roadmap line is[x]while its file is notStatus: closed, is a line under Risk to the goal:sprint NN is over and not closed — /retrospective NN. A sprint file without aStatus:line predates 0.13 and counts as closed only when its roadmap block is folded. - Findings:
Open BLOCKING findings: N (production/findings.md), naming the story per finding, or "no story".
Verdict: ON TRACK | AT RISK | OFF TRACK | OVER (not closed).
Next step — one AskUserQuestion: /dev-story <next story> (Recommended) · /help · nothing now; when the sprint is over and not closed, /retrospective NN is the Recommended option instead.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

