agency-sprint-runner
Skill2 starsChanged 33 days agoApache-2.0View on GitHub
Executes an autonomous 4-stage software agency sprint (Spec -> Build -> Verify -> Certify) powered by Google Antigravity. Coordinates CEO, CPO, CTO, Fullstack Developer, Automation Tester, and CISO avatars from initial backlog to production release. Use when building end-to-end features, running full development cycles, or executing multi-role sprints.
In this repository114 other files it gives its agents.
- AGENTS.mdAGENTS.md
- everything-gemini-maintainerSkill
- adversarial-fuzz-generatorSkill
- agency-boardroomSkill
- agency-design-systemSkill
- agency-growth-engineSkill
- agent-evalsSkill
- agent-ui-micro-componentsSkill
- ai-first-engineeringSkill
- alloydb-omni-vectorSkill
- apache-kafka-streamsSkill
- api-craftsmanSkill
- architecture-designerSkill
- argon-3d-game-engineSkill
- argon-3d-scene-architectSkill
- argon-procedural-asset-generatorSkill
- argon-visual-critique-loopSkill
- argo-workflowsSkill
- astryx-agent-design-systemSkill
- autonomous-incident-healerSkill
- axum-web-serviceSkill
- bigquery-vector-searchSkill
- browser-qa-testerSkill
- chromadb-vector-storeSkill
- cilium-ebpf-networkingSkill
- clickhouse-analyticsSkill
- cloud-deploy-canarySkill
- cloudflare-r2-object-storageSkill
- cloudflare-workersSkill
- cloud-run-agentsSkill
- context-cachingSkill
- context-distillation-compressorSkill
- context-warmerSkill
- continuous-learningSkill
- cost-oracle-finopsSkill
- cross-repo-swarm-syncSkill
- cve-remediation-orchestratorSkill
- database-architectSkill
- dataproc-spark-analyticsSkill
- dbt-transformationSkill
- debezium-cdcSkill
- devops-pipelineSkill
- distributed-rate-limitingSkill
- docker-compose-orchestratorSkill
- duckdb-local-olapSkill
- dynamic-thinking-allocationSkill
- ebpf-microvm-sandboxSkill
- ebpf-sandbox-enforcerSkill
- elephant-goldfish-modelSkill
- envoy-ai-gatewaySkill
- ephemeral-swarm-orchestratorSkill
- fastapi-productionSkill
- fullstack-nextjsSkill
- game-audio-synthesizerSkill
- game-studioSkill
- gemini-function-callingSkill
- gemini-groundingSkill
- gemini-live-audio-transcriberSkill
- gemini-live-multimodalSkill
- gemini-live-screen-visionSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 49
Exit Gate: All 4 executives sign the Sprint Directive.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Agency Sprint Runner (agency-sprint-runner)
The Agency Sprint Runner coordinates multi-role autonomous sprints across the virtual software agency. By moving work through four sequential, gated stages—Spec, Build, Verify, and Certify—it guarantees that features are built to specification, tested against regressions, vetted for security, and signed off before release.
🏃 The 4-Stage Sprint Execution Pipeline
flowchart LR
subgraph S1["Stage 1: Specification"]
CEO["CEO: Scope"] --> CPO["CPO: PRD & BDD"]
CPO --> CTO["CTO: Architecture ADR"]
end
subgraph S2["Stage 2: Implementation"]
CTO --> Dev["Fullstack Developer\nFrontend + Backend + DB Migration"]
end
subgraph S3["Stage 3: Verification"]
Dev --> QA["Automation Tester\nPlaywright E2E + Unit Tests"]
end
subgraph S4["Stage 4: Certification"]
QA --> CISO["CISO: Security Audit\nZero-Trust & Secret Check"]
CISO --> Release["CEO: Gold Master Ship\nMerge & Release"]
end
S1 --> S2 --> S3 --> S4📋 The 4 Gated Stages
Stage 1: Specification & Architecture Gate
- Participants:
ceo,cpo,cto,ciso. - Protocol:
ceosets the MVP scope boundaries.cpodrafts user stories with BDD acceptance criteria (docs/product/PRD.md).ctoauthors the Architecture Decision Record (docs/architecture/ADR.md) and selects the data model.cisoadds mandatory security invariants (authentication, RLS, input sanitization).
- Exit Gate: All 4 executives sign the Sprint Directive.
Stage 2: Fullstack Engineering Gate
- Participants:
fullstack-developer. - Protocol:
- Implements database models and migrations with foreign key constraints.
- Implements backend API endpoints with input validation (Zod/Pydantic) and error envelopes.
- Implements responsive frontend UI components using modern component libraries (shadcn/ui, Tailwind).
- Runs type-checking (
tsc --noEmit) and local unit tests with zero errors.
- Exit Gate: PR diff passes linter and type-checker with clean, minimal changes.
Stage 3: Automated Quality & Regression Gate
- Participants:
automation-tester. - Protocol:
- Ingests BDD scenarios from the PRD and writes end-to-end Playwright tests.
- Executes tests covering Happy Path, error states, and responsive viewports (Mobile & Desktop).
- Asserts 100% passing tests with zero console exceptions or unhandled promise rejections.
- Exit Gate: Formal QA Certification report (
docs/qa/TEST_REPORT.md) passes.
Stage 4: Security Certification & Executive Sign-Off
- Participants:
ciso,ceo. - Protocol:
cisoscans repository for hardcoded secrets, runs dependency audits, and verifies access control.cisoissues formal Security Clearance.ceoverifies business objectives and approves the final production release.
- Exit Gate: Unanimous executive clearance; release tagged and ready to ship.
🚀 Running an Autonomous Sprint
Trigger an autonomous sprint in chat:
"Act as the
agency-sprint-runner. Convene the agency avatars (ceo,cpo,cto,fullstack-developer,automation-tester,ciso) to execute an end-to-end sprint for: User Onboarding with Magic Link Authentication.1. Stage 1 (Spec): CPO & CTO create PRD and ADR. 2. Stage 2 (Build): Fullstack Developer creates the database schema, auth API, and login page. 3. Stage 3 (Verify): Automation Tester runs E2E tests for successful login and expired token handling. 4. Stage 4 (Certify): CISO audits for credential hygiene, and CEO approves the release."
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.

