git:20260920.2f3ac58 to git:20260923.f190e57

1 added, 1 removed. Audit A to A.

# tonone — Engineering + Product + Operations + Legal + Design + Data Science + Security Operations + Developer Experience + Infrastructure Specialist + AI Operations Team

Ten AI teams. 100 agents total. Engineering executes. Product decides what to build and why. Operations keeps the company running. Legal de-risks every move. Design makes it beautiful and accessible. Data Science turns data into decisions. Security Operations keeps everything safe. Developer Experience ensures developers succeed. Infrastructure Specialist runs the cloud. AI Operations ships models to production.

- **Read `docs/repomap.md` first** — this repo is too big to crawl by hand (100 agents, 422 skills). It points to `docs/agent-index.json` and `docs/skill-index.json` for lookups, and lists known content drift to watch for.

+ **Read `docs/repomap.md` first** — this repo is too big to crawl by hand (100 agents, 427 skills). It points to `docs/agent-index.json` and `docs/skill-index.json` for lookups, and lists known content drift to watch for.

## Engineering Team — 15 agents

| Agent | Hat | Owns |

|-------|-----|------|

| **Apex** | Engineering Lead | Orchestrates the team, scopes work, controls depth and budget |

| **Forge** | Infrastructure | Cloud services, networking, IaC, cost optimization |

| **Relay** | DevOps | CI/CD, deployments, GitOps, developer experience |

| **Spine** | Backend | APIs, system design, performance, distributed systems |

| **Flux** | Data | Databases, migrations, pipelines, data modeling |

| **Warden** | Security | IAM, secrets, compliance, threat modeling |

| **Vigil** | Observability + Reliability | Monitoring, alerting, SRE, incident response, SLOs |

| **Prism** | Frontend/DX | UI, internal tools, developer portals |

| **Cortex** | ML/AI | Model training, MLOps, feature engineering, LLM integration |

| **Touch** | Mobile | Native iOS/Android, cross-platform, app stores |

| **Volt** | Embedded/IoT | Firmware, microcontrollers, edge computing, protocols |

| **Atlas** | Knowledge Engineering | Architecture docs, ADRs, API specs, system diagrams |

| **Lens** | Data Analytics & BI | Dashboards, metrics design, reporting, data storytelling |

| **Proof** | QA & Testing | Test strategy, E2E suites, integration testing, flaky triage |

| **Pave** | Platform Engineering | Developer experience, golden paths, service catalogs |

## Product Team — 12 agents

| Agent | Hat | Owns |

|-------|-----|------|

| **Helm** | Head of Product | Orchestrates the product team, writes briefs, hands off to Apex |

| **Echo** | User Research | User interviews, personas, Jobs-to-Be-Done, feedback synthesis |

| **Lumen** | Product Analytics | Metrics frameworks, funnel analysis, OKRs, A/B test design |

| **Draft** | UX Design | User flows, information architecture, wireframes |

| **Form** | Visual Design | Brand identity, color systems, typography, design system |

| **Crest** | Product Strategy | Roadmap planning, prioritization, competitive analysis |

| **Pitch** | Product Marketing | Positioning, messaging, value prop, GTM, launch copy |

| **Surge** | Growth | Acquisition channels, activation funnels, retention playbooks |

| **Deal** | Revenue & Sales | B2B pipeline, deal strategy, pricing, sales playbooks, enterprise closing |

| **Keep** | Customer Success | Onboarding optimization, health scoring, expansion revenue, churn prevention |

| **Ink** | Content Marketing | Blog strategy, SEO, thought leadership, developer content, content calendar |

| **Buzz** | PR & Community | Press pitches, social media, open source community, DevRel, launch moments |

## Operations Team — 4 agents

| Agent | Hat | Owns |

|-------|-----|------|

| **Mint** | Finance | P&L, runway, unit economics, fundraising, board reporting, cap table |

| **Folk** | People | Org design, hiring pipelines, comp frameworks, onboarding, performance, human-to-agent migration |

| **Keel** | Operations | Process design, vendor management, legal ops, compliance (SOC2/GDPR), OKR execution |

| **Brace** | Support | Ticket workflow, SLA design, knowledge base, escalation paths, support operations |

## Legal Team — 10 agents

| Agent | Hat | Owns |

|-------|-----|------|

| **Brief** | Contract & Policy Drafter | NDAs, MSAs, employment agreements, SLAs, vendor contracts |

| **Clause** | Contract Clause Analyst | Redlining, risk scoring, negotiation playbooks |

| **Bind** | Compliance Framework Engineer | SOC2, GDPR, HIPAA, ISO 27001 gap analysis and remediation |

| **Frame** | Corporate Governance Advisor | Board resolutions, cap table hygiene, equity plan docs |

| **Shield** | Regulatory Risk Advisor | GDPR exposure, CCPA, FTC rules, financial regulation, export controls |

| **Scope** | IP & Trademark Advisor | Trademark clearance, patent landscape, open source license compliance |

| **Audit** | Legal Compliance Auditor | Internal controls review, legal risk register, audit trail docs |

| **Cite** | Legal Researcher | Case law synthesis, statute analysis, jurisdiction comparison |

| **Lodge** | Regulatory Filing Advisor | DMCA, FTC disclosures, GDPR DPAs, government filings, state registrations |

| **Terms** | Privacy & ToS Drafter | GDPR-compliant privacy policies, ToS, cookie policies, DPAs |

## Design Team — 10 agents

| Agent | Hat | Owns |

|-------|-----|------|

| **Hue** | Color Systems Designer | Color palettes, semantic tokens, dark/light mode, WCAG contrast |

| **Grid** | Layout Systems Designer | Spacing systems, responsive grids, breakpoints, layout primitives |

| **Glyph** | Typography Designer | Font selection, type scale, hierarchy, readability tokens |

| **Move** | Motion Designer | Animation systems, transitions, micro-interactions, motion tokens |

| **Wire** | Prototyping Engineer | Interactive prototypes, flow documentation, design handoff specs |

| **Mark** | Brand Designer | Logo usage, brand guidelines, visual identity, asset library |

| **Cut** | Illustration & Icon Designer | Custom illustrations, icon systems, SVG optimization |

| **Axe** | Accessibility Engineer | WCAG audits, keyboard navigation, screen reader testing, ARIA |

| **Tone** | Design Token Engineer | Token architecture, multi-brand theming, style-dictionary pipelines |

| **Copy** | Content Designer | UX writing, microcopy, error messages, onboarding copy, UI content strategy |

## Data Science Team — 10 agents

| Agent | Hat | Owns |

|-------|-----|------|

| **Cast** | Forecasting Engineer | Time series forecasting, demand prediction, seasonal decomposition |

| **Feat** | Feature Engineer | Feature engineering, encodings, feature stores, pipeline design |

| **Fit** | Model Training Engineer | Algorithm selection, hyperparameter tuning, training pipelines |

| **Score** | Model Evaluation Engineer | Metrics design, statistical significance, model comparison |

| **Drift** | ML Monitoring Engineer | Data drift, concept drift, model degradation, production ML health |

| **Vect** | Embeddings & Vector Search Engineer | Semantic search, RAG pipelines, vector database design |

| **Tune** | LLM Fine-tuning Engineer | PEFT/LoRA, RLHF, instruction tuning, prompt optimization |

| **Plot** | Data Visualization Engineer | Chart design, EDA, visualization libraries, dashboard specs |

| **Clean** | Data Quality Engineer | Deduplication, validation, outlier detection, ETL pipelines |

| **Eval** | Experiment Design Engineer | A/B testing, statistical power, experiment tracking, causal inference |

## Security Operations Team — 10 agents

| Agent | Hat | Owns |

|-------|-----|------|

| **Red** | Offensive Security Engineer | Pen testing plans, red team exercises, attack path documentation |

| **Blue** | Defensive Security Engineer | SOC design, detection engineering, hardening playbooks |

| **Hunt** | Threat Hunter | Hypothesis-driven hunting, compromise assessment, IOC analysis |

| **Patch** | Vulnerability Management Engineer | CVE triage, CVSS + EPSS prioritization, patch SLA design |

| **Chain** | Supply Chain Security Engineer | SBOM generation, dependency scanning, third-party risk |

| **Sast** | Application Security Engineer | SAST/DAST pipelines, code security review, secure SDLC |

| **Siem** | Detection & SIEM Engineer | Log pipeline design, SIGMA rules, alert tuning |

| **Resp** | Incident Response Engineer | IR playbooks, containment runbooks, DFIR, post-incident review |

| **Zero** | Zero Trust Architect | Zero trust roadmap, network microsegmentation, ZTNA design |

| **Phish** | Security Awareness Engineer | Phishing simulations, security training programs, culture metrics |

## Developer Experience Team — 10 agents

| Agent | Hat | Owns |

|-------|-----|------|

| **Guide** | API Documentation Engineer | API reference docs, integration guides, SDK documentation |

| **Sample** | Code Sample Engineer | Working examples, quickstarts, language-specific tutorials |

| **Mock** | API Mocking & Contract Engineer | Mock servers, consumer-driven contract testing, API simulation |

| **Schema** | API Schema Engineer | OpenAPI, GraphQL, gRPC schema quality and design standards |

| **Port** | SDK Design Engineer | Multi-language SDK architecture, idiomatic patterns, consistency |

| **Change** | Changelog & Release Communication Engineer | Breaking change docs, deprecation notices, migration guides |

| **Onboard** | Developer Onboarding Engineer | Quickstart design, time-to-first-call optimization |

| **Bench** | API Performance Engineer | Latency profiling, throughput testing, regression detection |

| **Compat** | Backwards Compatibility Engineer | Breaking change detection, deprecation management, semver |

| **Gate** | API Quality Gate Engineer | Linting, style enforcement, breaking change CI, API governance |

## Infrastructure Specialist Team — 10 agents

| Agent | Hat | Owns |

|-------|-----|------|

| **Kube** | Kubernetes Engineer | Cluster design, RBAC, networking policies, operators, Helm charts |

| **Terra** | Terraform Engineer | IaC modules, state management, provider config, drift detection |

| **Finop** | FinOps Engineer | Cloud cost optimization, budget alerts, rightsizing, waste elimination |

| **Serv** | Service Reliability Engineer | SLO design, error budgets, reliability reviews, capacity planning |

| **Edge** | Edge Computing Engineer | CDN config, edge functions, latency optimization, global routing |

| **Cache** | Caching Engineer | Redis/Memcached design, cache invalidation, TTL strategy, hit-rate tuning |

| **Queue** | Message Queue Engineer | Kafka/SQS/RabbitMQ design, consumer groups, DLQs, backpressure |

| **Mesh** | Service Mesh Engineer | Istio/Linkerd config, mTLS, traffic management, observability |

| **Multi** | Multi-Cloud Engineer | Cross-cloud architecture, vendor portability, cloud-agnostic patterns |

| **Chaos** | Chaos Engineering Lead | Failure injection, game days, resilience testing, blast radius control |

## AI Operations Team — 9 agents

| Agent | Hat | Owns |

|-------|-----|------|

| **Deploy** | AI Deployment Engineer | Model serving, inference APIs, blue/green deploys, rollback, canary releases |

| **Evals** | LLM Evaluation Engineer | Eval harness design, benchmark suites, automated regression, human eval pipelines |

| **Trace** | LLM Observability Engineer | LLM tracing, span capture, prompt/completion logging, cost attribution, debugging |

| **Guard** | AI Guardrails Engineer | Input/output safety filters, PII detection, content moderation, policy enforcement |

| **Budget** | AI Cost Engineer | LLM spend tracking, model cost optimization, budget alerts, token efficiency audits |

| **Token** | Token Management Engineer | Context window optimization, token counting, truncation strategies, chunking patterns |

| **Prompt** | Prompt Engineer | System prompt design, few-shot libraries, chain-of-thought patterns, prompt versioning |

| **Embed** | Embeddings Engineer | Embedding model selection, vector pipeline design, similarity search, index management |

| **Rank** | AI Ranking Engineer | Retrieval reranking, relevance scoring, learning-to-rank, result quality evaluation |

## Helm↔Apex Interface

Helm hands off to Apex using a 6-field product brief schema. See `agents/apex.md` → `## Helm Handoff` for the full contract.

## Structure

```

tonone/

├── .claude-plugin/ ← root plugin (installs full team)

├── agents/ ← all agent definitions (100 total: 15 engineering + 12 product + 4 operations + 10 legal + 10 design + 10 data-science + 10 secops + 10 devx + 10 infra-specialist + 9 ai-ops)

│ ├── apex.md

│ ├── forge.md

│ ├── relay.md

│ └── ...

├── skills/ ← root-level Apex skills

│ ├── apex-plan/

│ ├── apex-review/

│ ├── apex-status/

│ └── apex-takeover/

├── team/ ← specialist source (scripts, skills, hooks, tests)

│ ├── forge/

│ │ ├── .claude-plugin/ ← plugin manifest

│ │ ├── agents/ ← agent definition (canonical copy)

│ │ ├── skills/ ← slash commands

│ │ ├── hooks/ ← lifecycle hooks

│ │ ├── scripts/ ← Python source + venv

│ │ └── tests/

│ ├── relay/

│ ├── spine/

│ └── ...

├── docs/ ← naming guide, design docs

└── templates/new-agent/ ← scaffolding for new agents

```

## Adding a New Agent

1. Copy `templates/new-agent/` to `team/<agent-name>/`

2. Replace placeholders in plugin.json, agent def, skills

3. Implement analyzers in `scripts/<module>/`

4. Copy agent def to root `agents/` directory

5. See `docs/naming-guide.md` for naming conventions

6. Agent must expose skills via its plugin manifest

## Conventions

- Agent names: single word, 1-2 syllables, evocative of the domain (see `docs/naming-guide.md`)

- Skills: `/{agentname}-{action}` (e.g., `/forge-audit`)

- Each agent is self-contained with own pyproject.toml, tests, hooks

- All agent CLI output follows the output kit (`docs/output-kit.md`): 40-line max, box-drawing skeleton, unified severity indicators

## Development

```bash

# Individual agent (plugin layout)

cd team/forge/scripts && bash setup.sh

.venv/bin/python -m pytest ../tests/

```

## gstack

gstack is installed at `~/.claude/skills/gstack`. Use `/browse` for all web browsing — never use `mcp__claude-in-chrome__*` tools.

Available gstack skills: /office-hours, /plan-ceo-review, /plan-eng-review, /plan-design-review, /design-consultation, /design-shotgun, /design-html, /review, /ship, /land-and-deploy, /canary, /benchmark, /browse, /connect-chrome, /qa, /qa-only, /design-review, /setup-browser-cookies, /setup-deploy, /setup-gbrain, /retro, /investigate, /document-release, /codex, /cso, /autoplan, /plan-devex-review, /devex-review, /careful, /freeze, /guard, /unfreeze, /gstack-upgrade, /learn

## Skill routing

When the user's request matches an available skill, ALWAYS invoke it using the Skill

tool as your FIRST action. Do NOT answer directly, do NOT use other tools first.

The skill has specialized workflows that produce better results than ad-hoc answers.

Key routing rules:

- Product ideas, "is this worth building", brainstorming → invoke office-hours

- Bugs, errors, "why is this broken", 500 errors → invoke investigate

- Ship, deploy, push, create PR → invoke ship

- QA, test the site, find bugs → invoke qa

- Code review, check my diff → invoke review

- Update docs after shipping → invoke document-release

- Weekly retro → invoke retro

- Design system, brand → invoke design-consultation

- Visual audit, design polish → invoke design-review

- Architecture review → invoke plan-eng-review

- Save progress, checkpoint, resume → invoke checkpoint

- Code quality, health check → invoke health

## Health Stack

- structure: python -m pytest tests/test_structure.py tests/test_agent_compliance.py tests/test_skill_compliance.py -v

- skills mirror: python scripts/sync-skills.py --check

- hooks: python -m pytest tests/test_hooks.py -v

- shell: find . -name "setup.sh" -not -path "./.git/*" -not -path "./.claude/*" | xargs shellcheck -S warning

- versions: python scripts/bump-version.py --check

- upstream drift: python scripts/check-upstream.py (exit 1 = an upstream plugin we borrow from shipped a new release; see docs/upstream.md)