Decisions
- How autonomous should the Tech Lead be? (pick from planned vs. wait for assignment) · Phase 1 · ready
- Git branching strategy (per feature vs. per task) · Phase 1 · ready
- Escalation threshold (when agents ask you vs. decide themselves) · Phase 1 · ready
- Report verbosity (always full vs. only non-trivial) · Phase 2 · ready
User Tasks
- Review and approve design: agency-company-structure · Phase 1 · ready
- Decide on model routing per role (Opus/Sonnet/Haiku) · Phase 1 · ready
Summary
Model Opus as a company: agents have roles, a reporting hierarchy, and produce structured reports. You are management.
Problem / Motivation
The autonomous coding agency (Group 9) defines what agents do technically, but not how they communicate. Without structured reporting:
- You have no visibility into what agents did or why
- Agents can’t coordinate or hand off work
- There’s no audit trail beyond git history
- You’d have to read diffs to understand what happened
The company metaphor solves this: defined roles, chain of command, structured reports.
Proposed Solution
Three agent roles (Tech Lead, Developer, QA) with a reporting chain. Every agent writes a structured report when done. Tech Lead aggregates into feature reports. Reports stored in date-organized folders. A /build skill kicks off the pipeline.
Full design: agency-company-structure
Open Questions
1. Autonomy Level
Question: Should the Tech Lead auto-pick features from planned/, or always wait for assignment?
| Option | Description |
|---|---|
| A) Assignment only | You explicitly say “build FR-072”. Safest, full control |
| B) Auto-pick with confirmation | Tech Lead proposes next feature, you approve before work starts |
| C) Fully autonomous | Tech Lead picks and builds. You review after |
Recommendation: Option A initially, evolve to B once trust is established.
Decision:
2. Git Branching
Question: One branch per feature or per task?
| Option | Description |
|---|---|
| A) Per feature | feature/FR-072 — simpler, one PR per feature |
| B) Per task | feature/FR-072/01-extract-middleware — more granular, more PRs |
Recommendation: Option A — per-feature branches. Simpler. Tasks are commits within the branch.
Decision:
3. Escalation Policy
Question: When should agents escalate to you vs. decide themselves?
| Option | Description |
|---|---|
| A) Escalate architectural decisions | Agents decide implementation details, escalate design choices |
| B) Escalate everything unclear | Conservative — more interruptions, more control |
| C) Never escalate | Fully autonomous — report after the fact |
Recommendation: Option A — architectural decisions and ambiguous requirements escalate. Implementation details are the agent’s call.
Decision:
Phase Overview
| Phase | Description | Status |
|---|---|---|
| Phase 1 | Agent definitions + report templates | — |
| Phase 2 | Reporting infrastructure + storage | — |
| Phase 3 | Orchestration pipeline + /build skill | — |
| Phase 4 | Daily digest (PM agent) | — |
Phase 1: Agent Definitions & Templates —
Goal: Define the three core agent roles and report templates.
| File / Feature | Details | Owner | Status |
|---|---|---|---|
.claude/agents/tech-lead.md | Orchestrator agent definition | opus | — |
.claude/agents/developer.md | Implementation agent definition | opus | — |
.claude/agents/qa-reviewer.md | Code review agent definition | opus | — |
vault/_templates/task-report.md | Dev task report template | opus | — |
vault/_templates/review-report.md | QA review report template | opus | — |
vault/_templates/feature-report.md | Tech Lead summary template | opus | — |
Phase 2: Reporting Infrastructure —
Goal: Set up report storage and establish the reporting chain.
| File / Feature | Details | Owner | Status |
|---|---|---|---|
vault/00_system/logs/agent-reports/ | Date-organized report storage | opus | — |
| Agent prompts | Agents write reports as part of their workflow | opus | — |
| Tech Lead aggregation | Tech Lead reads sub-agent reports, writes feature report | opus | — |
Phase 3: Orchestration Pipeline —
Goal: End-to-end pipeline: assign feature → agents work → reports produced.
| File / Feature | Details | Owner | Status |
|---|---|---|---|
.claude/skills/build/SKILL.md | /build FR-XXX kicks off pipeline | opus | — |
| Tech Lead pipeline logic | Break down → assign → review → aggregate | opus | — |
| Escalation handling | Tech Lead knows when to ask management | opus | — |
Phase 4: Daily Digest —
Goal: Automated daily summary of all agent work. Feeds into FR-037 (Daily Briefings) as dedicated sections.
| File / Feature | Details | Owner | Status |
|---|---|---|---|
.claude/agents/pm.md | PM agent scans reports, writes digest | opus | — |
FR-037 agent-reports-agent | Section agent that reads agent reports and summarizes per-role activity | opus | — |
FR-037 cron-tasks-agent | Section agent that reads cron/scheduler logs and summarizes system-triggered tasks | opus | — |
vault/30_daily/briefings/ | Daily digest output location (via FR-037 compiler) | opus | — |
Prerequisites / Gap Analysis
Requirements
| Requirement | Description |
|---|---|
| REQ-1 | Custom agents infrastructure (FR-043) |
| REQ-2 | Python project scaffold for any tooling (FR-009) |
| REQ-3 | Agent git workflow for branching/PRs (FR-058) |
Current State
| Component | Status | Details |
|---|---|---|
| Agent definitions | — | No agents built yet |
| Report templates | — | Don’t exist yet |
/build skill | — | Doesn’t exist |
src/ codebase | — | Not started |
Gap (What’s missing?)
| Gap | Effort | Blocker? |
|---|---|---|
| Agent definitions can be built now (plain markdown) | Low | No |
| Report templates can be built now | Low | No |
| Orchestration needs FR-043 agent infrastructure | Med | Soft — can prototype with Task tool |
| Git workflow needs FR-058 | Med | Yes for Phase 3 |
Test
Manual tests
| Test | Expected | Actual | Last |
|---|---|---|---|
| … | … | pending | - |
AI-verified tests
| Scenario | Expected behavior | Verification method |
|---|---|---|
| … | … | … |
E2E tests
| Scenario | Assertion |
|---|---|
| … | … |
Integration tests
| Component | Coverage |
|---|---|
| … | … |
Unit tests
| Component | Tests | Coverage |
|---|---|---|
| … | … | … |
History
| Date | Event | Details |
|---|---|---|
| 2026-03-13 | Created | Initial FR based on user idea. Design draft: agency-company-structure |
References
- Design: agency-company-structure
- Related: FR-043 (Custom Agents), FR-056 (Autonomous Coding Orchestrator), FR-057 (Code Review Pipeline), FR-058 (Agent Git Workflow), FR-059 (Escalation Policy), FR-037 (Daily Briefings — agent reports + cron tasks feed into daily)