sprint-scaffold
Skill0 starsChanged 2 months agoApache-2.0View on GitHub
Scaffold a new sprint folder with the Filing Cabinet spec_charter.md + Flowstate .claude/agents/pr-review.md + reference/sql/ subdirs. Use when starting a new sprint (e.g. "open sprint 021", "start a sprint for X", "new sprint folder"). Drops a working skeleton in ./sprints/NNN_slug/ with the load-bearing files pre-filled so every shipped item gets an audit-trail home. Validated over a two-terminal sprint that shipped 20+ items under this pattern.
In this repository17 other files it gives its agents.
- aria-skill-candidatesSkill
- aria-skill-templateSkill
- aria-skill-testSkill
- call-scrubSkill
- cloudflare-dns-deploySkill
- doc-to-pdfSkill
- ffmpeg-audioSkill
- github-repo-deploySkill
- goal-to-planSkill
- headless-claudeSkill
- live-code-watchSkill
- premortemSkill
- screen-describeSkill
- session-cabinetSkill
- skill-manifest-genSkill
- surgical-patchSkill
- video-ingestSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
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
- Very specific: line 22
Pick the sprint number: Look at ./sprints/ (or your --dest) — find the highest existing NNN and add 1.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Sprint Scaffold
Apply the Filing Cabinet product spec_charter.md template + the Flowstate product .claude/agents/pr-review.md template to internal Aria sprints (not just customer-facing project tarballs). Closes the audit-trail loop: every sprint has a mission, scope, risks, acceptance criteria, and a review rubric for everything shipped under it.
This skill emerged from Sprint 020 (two_terminal_push, 2026-05-23) where T1 and T2 shipped 11 items in parallel with zero conflicts because the sprint folder enforced clean ownership boundaries up front.
When to use
- User says "open sprint NNN" / "start sprint for X" / "new sprint" / "scaffold a sprint" / "let's sprint on Y"
- You're about to start work that spans 3+ items + multiple sessions and should have one canonical home
- Multiple terminals or contributors need a file-lock contract (this skill ships HANDOFF_*.md templates)
Steps
./sprint_scaffold.sh NNN slug [--dest DIR] runs steps 2-5 in one shot; the steps below are what it does.
Pick the sprint number. Look at
./sprints/(or your--dest) — find the highest existing NNN and add 1. Slug is lowercase-hyphenated.ls ./sprints/ | sort -n | tail -3Create the folder + subdirs:
SPRINT=021_<slug> mkdir -p ./sprints/$SPRINT/{reference,sql,.claude/agents}Write spec_charter.md (Filing Cabinet pattern). Use the template below — pre-fill what you know, leave the rest as
TODO:# Sprint NNN — <Title> · spec_charter v1 **Opened:** YYYY-MM-DD **Closes:** YYYY-MM-DD (target) **Method:** Filing Cabinet spec_charter pattern + Flowstate pr-review pattern ## 1. Mission <1-2 sentences. What changes if this sprint succeeds?> ## 2. Stakeholders | Role | Person | Responsibility | |---|---|---| | Owner | <owner> | Final call | | T1 | Claude | <lane> | | T2 | (if applicable) | <lane> | | Informed | <teammate> | <when needed> | ## 3. Constraints 1. <calendar / doctrine / file-lock / restart / etc.> ## 4. Scope ### P0 (must ship) | # | Item | Owner | Status | ### P1 (close if possible) ### P2 (stretch) ### Out of scope (defensibly deferable) ## 5. Risks | Risk | Likelihood | Mitigation | ## 6. Open questions ## 7. v1 acceptance criteria - [ ] <criterion> ## 8. Versioning Per Filing Cabinet versioning protocol: copy to spec_charter_v2.md when scope changes. Never edit v1 in place. ## 9. Tools/skills used (reuse log) | Tool/skill | Used for | New or existing | ## 10. New skill emerging (if any)Write .claude/agents/pr-review.md (Flowstate pattern). Use this 5-dim rubric template:
# Sprint NNN PR-Review Rubric (Flowstate pattern, sprint-local) Apply to every item shipped before marking done. ## The 5 dimensions ### 1. Correctness — does it do what the charter §4 said? ### 2. Security — auth gates? secrets? injection? ### 3. Test coverage — smoke trace saved? ### 4. Doctrine alignment — which feedback_* rules apply? ### 5. Follow-ups — what was deferred? ## Output formatSprint NNN self-review —
<item slug>1. Correctness: ✅ / ⚠️ / ❌ —
<one-line evidence>2. Security: ✅ / ⚠️ / ❌ 3. Test coverage: ✅ / ⚠️ / ❌ 4. Doctrine: ✅ / ⚠️ / ❌ 5. Follow-ups: <ops_log ids, skill ideas> Verdict: APPROVE / REQUEST CHANGES / RETHINK Smoke command:<copy-paste-able>Drop a HANDOFF template (if multi-terminal):
touch ./sprints/$SPRINT/HANDOFF_T1_TO_T2.mdPre-fill with the file-lock contract + route-prefix partition pattern from the Sprint 020 handoff.
Insert a parent row in your ops log (example against our
v4_ops_logtable):INSERT INTO v4_ops_log (priority, status, category, area, title, detail, owner, purpose) VALUES ('P0','in_progress','product','<area>', 'Sprint NNN — <title>', 'Charter at ./sprints/NNN_slug/spec_charter.md', 'claude','sprint_NNN');Subsequent items in this sprint tag
purpose='sprint_NNN'for clean filtering.- Report. Print the absolute path to the new sprint folder + the next 1-3 items to populate.
Folder layout this skill creates
./sprints/NNN_slug/
├── spec_charter.md ← Filing Cabinet pattern
├── .claude/agents/pr-review.md ← Flowstate pattern
├── HANDOFF_T1_TO_T2.md ← Inter-terminal coordination (template)
├── reference/ ← Source docs that fed the sprint
└── sql/ ← Schema migrations this sprint introducesNotes
- This skill was promoted from Sprint 020 (
two_terminal_push, 2026-05-23) where the pattern proved itself shipping 11 items in parallel between T1 and T2 with zero file collisions. - The
spec_charter.mdtemplate here is the same one that ships at the root of every Filing Cabinet customer tarball, just retargeted at our internal sprint context. The Mission/Stakeholders/Constraints/Risks/Acceptance pattern works identically for both. - The
pr-review.mdtemplate here matches the Flowstate scaffold pack —.claude/agents/pr-review.mdat sprint root means Claude Code agents picked up later in the sprint will auto-honor the rubric. - Charter versioning rule (never edit v1 in place; copy to v2 if scope changes) is load-bearing. Audit trail needs the WHY of pivots.
- Pair with your session-close routine — at sprint close, the per-item memories that piled up should each have a
## Sprint NNN self-reviewblock already. - Cross-link sprint memories with
[[other-slug]]for navigability.
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.

