borghei/Claude-Skills / project-management/execution/agents-in-the-team
agents-in-the-team
UnverifiedRun delivery when AI coding and ops agents take tickets. Use when setting agent delegation policy, writing agent-ready tickets, planning review capacity, measuring agent vs human delivery, or rolling agents out safely.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 17.6 KB |
| assets/agent_ticket_template.md | markdown | 1.8 KB |
| assets/backlog_sample.json | config | 3.8 KB |
| assets/backlog_within_capacity.json | config | 3.6 KB |
| assets/delegation_policy_template.md | markdown | 2.5 KB |
| assets/delivery_records_sample.json | config | 9.7 KB |
| assets/rollout_plan_template.md | markdown | 1.7 KB |
| examples/payments-platform-sprint.md | markdown | 4.4 KB |
| references/delegation-and-accountability.md | markdown | 8.4 KB |
| references/metrics-and-capacity.md | markdown | 8.1 KB |
| references/security-and-rollout.md | markdown | 5.4 KB |
| scripts/agent_delegation_scorer.py | script | 9.7 KB |
| scripts/agent_delivery_metrics.py | script | 10.5 KB |
assets/backlog_sample.json
View on GitHub{
"sprint": "Sprint 42",
"as_of": "2026-09-21",
"team": {
"name": "Payments Platform",
"reviewers": [
{"name": "Senior engineer A", "review_hours_per_sprint": 6},
{"name": "Senior engineer B", "review_hours_per_sprint": 6},
{"name": "Tech lead", "review_hours_per_sprint": 4}
],
"max_review_utilization": 0.8,
"review_model": {"base_hours": 0.5, "hours_per_point": 0.5, "rework_allowance": 0.3}
},
"tickets": [
{
"id": "PAY-101", "title": "Add unit tests for currency rounding helpers", "type": "test",
"risk": "low", "blast_radius": "isolated", "test_coverage": "good", "points": 2,
"acceptance_criteria": ["Tests cover half-even rounding for 5 currencies", "Coverage of rounding.py at least 90%"],
"context_links": ["src/money/rounding.py"], "constraints": ["Do not change production code"],
"planned_assignee": "agent"
},
{
"id": "PAY-102", "title": "Bump HTTP client library to latest patch", "type": "dependency-update",
"risk": "low", "blast_radius": "module", "test_coverage": "good", "points": 1,
"acceptance_criteria": ["Lockfile updated to latest patch release", "CI green, no new deprecation warnings"],
"context_links": ["requirements.lock"], "constraints": ["Patch versions only"],
"planned_assignee": "agent"
},
{
"id": "PAY-103", "title": "Fix pagination off-by-one on invoice list API", "type": "bug",
"risk": "medium", "blast_radius": "service", "test_coverage": "partial", "points": 3,
"acceptance_criteria": ["Page 2 starts at item limit+1", "Regression test added for boundary"],
"context_links": ["api/invoices.py", "Issue thread with repro"], "constraints": ["No API contract change"],
"planned_assignee": "agent"
},
{
"id": "PAY-104", "title": "Refactor refund service into smaller modules", "type": "refactor",
"risk": "medium", "blast_radius": "service", "test_coverage": "partial", "points": 8,
"acceptance_criteria": ["No behavior change; all existing tests pass", "Each module under 300 lines"],
"context_links": ["services/refunds/"], "constraints": ["Keep public interfaces"],
"planned_assignee": "agent"
},
{
"id": "PAY-105", "title": "Rotate webhook signing secret handling", "type": "security",
"risk": "high", "blast_radius": "cross-system", "test_coverage": "partial", "points": 5,
"touches": ["secrets", "payments"],
"acceptance_criteria": ["Old and new secrets accepted during rotation window"],
"context_links": ["runbooks/webhook-secrets.md"], "constraints": ["Zero-downtime rotation"],
"planned_assignee": "agent"
},
{
"id": "PAY-106", "title": "Improve checkout", "type": "feature",
"risk": "medium", "blast_radius": "service", "test_coverage": "none", "points": 5,
"acceptance_criteria": [],
"planned_assignee": "human"
},
{
"id": "PAY-107", "title": "Update API docs for new invoice filters", "type": "docs",
"risk": "low", "blast_radius": "isolated", "test_coverage": "partial", "points": 1,
"acceptance_criteria": ["All 4 new filters documented with examples", "Docs build passes link check"],
"context_links": ["docs/api/invoices.md"], "constraints": ["Follow docs style guide"],
"planned_assignee": "agent"
},
{
"id": "PAY-108", "title": "Add CSV export to payouts report", "type": "feature",
"risk": "medium", "blast_radius": "module", "test_coverage": "good", "points": 5,
"acceptance_criteria": ["Export matches on-screen columns", "Exports up to 50k rows under 10 s", "Amounts use locale-independent format"],
"context_links": ["reports/payouts.py", "Design note in ticket"], "constraints": ["Reuse existing export helper"],
"planned_assignee": "agent"
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |