From engineering-workflow
Micro-agent system for engineering architecture decisions across DB, BE, IF, SE domains. Routes queries to specialized micro agents for deep technical analysis. Activated by keywords: "db architecture", "storage engine", "index design", "query optimization", "concurrency", "isolation level", "schema design", "replication", "sharding", "consistency model", "engineering workflow", "architecture decision".
How this skill is triggered — by the user, by Claude, or both
Slash command
/engineering-workflow:engineering-workflowThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
> A 3-tier micro-agent system that routes engineering architecture queries to specialized domain agents,
agents/audit-reviewer.mdagents/be-orchestrator.mdagents/be/b1-context-classifier.mdagents/be/b2-acl-designer.mdagents/be/b3-event-architect.mdagents/be/b4-saga-coordinator.mdagents/be/b5-implementation-guide.mdagents/be/r1-bulkhead-architect.mdagents/be/r2-cb-configurator.mdagents/be/r3-retry-strategist.mdagents/be/r4-observability-designer.mdagents/be/s1-dependency-auditor.mdagents/be/s2-di-pattern-selector.mdagents/be/s3-architecture-advisor.mdagents/be/s4-fitness-engineer.mdagents/be/s5-convention-verifier.mdagents/be/t1-test-guard.mdagents/be/t2-test-strategist.mdagents/be/t3-test-generator.mdagents/be/t4-quality-assessor.mdA 3-tier micro-agent system that routes engineering architecture queries to specialized domain agents, resolves cross-domain constraints, and synthesizes unified recommendations.
A 3-tier micro-agent orchestration system for engineering architecture decisions spanning four major systems: DB (Database), BE (Backend), IF (Infrastructure), and SE (Security).
Tier 1: Gateway Router (this SKILL.md)
|
┌───────────────┼───────────────┐
| | |
Tier 2: System Orchestrators
┌────┐ ┌────┐ ┌────┐ ┌────┐
│ DB │ │ BE │ │ IF │ │ SE │
└──┬─┘ └──┬─┘ └──┬─┘ └──┬─┘
| | | |
Tier 3: Micro Agents (domain-specific)
┌─────────────────────────────┐
│ A: Storage D: API Design │
│ B: Query E: Concurrency │
│ C: Schema F: Networking │
│ ... ... │
└─────────────────────────────┘
classify-query.sh for unambiguous queries; reserve LLM classification for edge cases| System | Keywords | Orchestrator |
|---|---|---|
| DB | database, storage engine, index, query optimization, schema, replication, sharding, partition, consistency model, isolation level, MVCC, WAL, B-tree, LSM, vacuum, ACID, DynamoDB, RCU, WCU, hot partition, adaptive capacity, throttling | agents/db-orchestrator.md |
| BE | backend, API design, service layer, concurrency, thread pool, connection pool, caching strategy, microservice, event-driven, CQRS, saga, domain model | agents/be-orchestrator.md |
| IF | infrastructure, deployment, container, kubernetes, CI/CD, load balancer, CDN, monitoring, observability, scaling, network topology, DNS, TLS | agents/if-orchestrator.md |
| SE | security, authentication, authorization, encryption, key management, RBAC, ABAC, OAuth, JWT, zero-trust, penetration, vulnerability, compliance | agents/se-orchestrator.md |
| Cluster | Sub-Domain | Code | Keywords | Agent |
|---|---|---|---|---|
| A Authentication | AuthN Flow Design | A1 | authentication, OAuth2, OIDC, SAML, SSO, login flow, protocol selection | agents/se/a1-authn-flow-designer.md |
| A Authentication | Token Strategy | A2 | JWT, refresh token, access token, token rotation, token storage, claims | agents/se/a2-token-strategist.md |
| A Authentication | Session Architecture | A3 | session management, MFA, SSO federation, stateless, session fixation | agents/se/a3-session-architect.md |
| A Authentication | Credential Management | A4 | bcrypt, argon2, passkey, WebAuthn, passwordless, credential rotation | agents/se/a4-credential-manager.md |
| Z Authorization | Access Model Selection | Z1 | RBAC, ABAC, ReBAC, access control model, multi-tenant, permission model | agents/se/z1-access-model-selector.md |
| Z Authorization | Policy Design | Z2 | OPA, Cedar, Casbin, policy engine, policy rule, policy test | agents/se/z2-policy-designer.md |
| Z Authorization | Permission Audit | Z3 | least privilege, over-privilege, permission matrix, role explosion | agents/se/z3-permission-auditor.md |
| Z Authorization | Scope Architecture | Z4 | OAuth scope, API permission, dynamic scope, consent, token-permission | agents/se/z4-scope-architect.md |
| E Encryption | Encryption Strategy | E1 | encryption at-rest, in-transit, field-level, AES-256, ChaCha20 | agents/se/e1-encryption-advisor.md |
| E Encryption | Key Lifecycle | E2 | key rotation, HSM, Vault, KMS, key escrow, key distribution | agents/se/e2-key-lifecycle-planner.md |
| E Encryption | TLS Configuration | E3 | TLS, mTLS, cipher suite, certificate chain, OCSP, certificate pinning | agents/se/e3-tls-configurator.md |
| E Encryption | Secret Management | E4 | HashiCorp Vault, AWS Secrets Manager, secret rotation, dynamic secret | agents/se/e4-secret-manager.md |
| N Network Security | Header Hardening | N1 | CORS, CSP, HSTS, X-Frame-Options, Referrer-Policy, security headers | agents/se/n1-header-hardener.md |
| N Network Security | WAF/Rate-Limiting | N2 | WAF, rate limiting, IP filtering, DDoS, geo-blocking, ModSecurity | agents/se/n2-waf-rule-designer.md |
| N Network Security | API Gateway Security | N3 | API gateway, auth delegation, request validation, throttling, API key | agents/se/n3-api-gateway-security.md |
| N Network Security | Input Sanitization | N4 | SQL injection, XSS, path traversal, content-type validation, sanitization | agents/se/n4-input-sanitizer.md |
| C Compliance | Compliance Mapping | C1 | SOC2, ISO27001, GDPR, PCI-DSS, compliance framework, cross-mapping | agents/se/c1-compliance-mapper.md |
| C Compliance | Audit Trail Design | C2 | audit logging, event schema, append-only, WORM, tamper detection | agents/se/c2-audit-trail-designer.md |
| C Compliance | Zero-Trust Planning | C3 | zero-trust, microsegmentation, device trust, BeyondCorp, continuous verification | agents/se/c3-zero-trust-planner.md |
| C Compliance | Privacy Engineering | C4 | GDPR data subject, consent management, PII, data masking, DPIA | agents/se/c4-privacy-engineer.md |
| V Vulnerability | Threat Modeling | V1 | STRIDE, PASTA, attack tree, threat scenario, attack surface | agents/se/v1-threat-modeler.md |
| V Vulnerability | OWASP Audit | V2 | OWASP Top 10, injection, XSS, auth flaw, SSRF, deserialization | agents/se/v2-owasp-auditor.md |
| V Vulnerability | Pentest Strategy | V3 | penetration test, black-box, white-box, Burp, ZAP, Nuclei | agents/se/v3-pentest-strategist.md |
| V Vulnerability | Supply Chain Audit | V4 | SCA, SBOM, license compliance, CVE, dependency vulnerability, Sigstore | agents/se/v4-supply-chain-auditor.md |
| Sub-Domain | Code | Keywords | Agents |
|---|---|---|---|
| Storage Engine | A | storage engine, B-tree, LSM-tree, page layout, WAL, buffer pool, compaction, write amplification | agents/db/a1-engine-selector.md, agents/db/a2-compaction-strategist.md |
| Index & Query Plan | B | query plan, explain analyze, index scan, seq scan, join strategy, cost estimation, query rewrite, statistics | agents/db/b1-index-architect.md, agents/db/b2-join-optimizer.md, agents/db/b3-query-plan-analyst.md |
| Concurrency & Locking | C | concurrency, isolation level, MVCC, locking, deadlock, optimistic, pessimistic, serializable, phantom read | agents/db/c1-isolation-advisor.md, agents/db/c2-mvcc-specialist.md, agents/db/c3-lock-designer.md |
| Schema & Normalization | D | schema design, normalization, denormalization, document model, embedding, referencing, access pattern | agents/db/d1-schema-expert.md, agents/db/d2-document-modeler.md, agents/db/d3-access-pattern-modeler.md |
| I/O & Buffer Management | E | page, buffer pool, WAL, write-ahead log, checkpoint, dirty page, flush, I/O optimization | agents/db/e1-page-optimizer.md, agents/db/e2-wal-engineer.md, agents/db/e3-buffer-tuner.md |
| Distributed & Replication | F | replication, failover, consensus, raft, paxos, sharding, partition, consistency, CAP theorem, dynamodb, rcu, wcu, hot partition, adaptive capacity, throttling, provisioned throughput, on-demand, TPS | agents/db/f1-replication-designer.md, agents/db/f2-consistency-selector.md, agents/db/f3-sharding-architect.md, agents/db/f4-dynamodb-throughput-optimizer.md |
| Cluster | Sub-Domain | Code | Keywords | Agent |
|---|---|---|---|---|
| S Structure | Dependency Audit | S1 | dependency violation, import direction, runtimeOnly, layer rule, module boundary | agents/be/s1-dependency-auditor.md |
| S Structure | DI Pattern | S2 | Port design, Adapter injection, Constructor Injection, Stub pattern, DI | agents/be/s2-di-pattern-selector.md |
| S Structure | Architecture | S3 | new module, naming convention, publisher vs producer, module layout, hexagonal | agents/be/s3-architecture-advisor.md |
| S Structure | Fitness Function | S4 | ArchUnit, Konsist, checkTestNames, fitness function, CI automation | agents/be/s4-fitness-engineer.md |
| B Boundary | Context Classification | B1 | external system, ACL vs Conformist, Semantic Gap, context mapping | agents/be/b1-context-classifier.md |
| B Boundary | ACL Design | B2 | ACL design, Translator, Feign, testFixtures, anti-corruption | agents/be/b2-acl-designer.md |
| B Boundary | Event Architecture | B3 | internal event, external event, SQS, event versioning, domain event | agents/be/b3-event-architect.md |
| B Boundary | Saga Coordination | B4 | payment flow, compensation, Saga, Pivot step, compensable, retryable | agents/be/b4-saga-coordinator.md |
| R Resilience | Bulkhead | R1 | bulkhead, Thread Pool, Semaphore, pool size, isolation | agents/be/r1-bulkhead-architect.md |
| R Resilience | Circuit Breaker | R2 | Circuit Breaker, failureRate, slowCall, Resilience4j, half-open | agents/be/r2-cb-configurator.md |
| R Resilience | Retry/Timeout | R3 | timeout budget, retry, fallback, idempotencyKey, backoff | agents/be/r3-retry-strategist.md |
| R Resilience | Observability | R4 | monitoring, dashboard, tracing, Grafana, Prometheus, alert rule, micrometer | agents/be/r4-observability-designer.md |
| S Structure | Convention Verifier | S5 | convention, code style, naming rule, JPA pattern, entity model, dynamic update | agents/be/s5-convention-verifier.md |
| B Boundary | Implementation Guide | B5 | implementation guide, code pattern, feign client, translator code, saga implementation | agents/be/b5-implementation-guide.md |
| T Test | Test Guard | T1 | Fixture Monkey, FakeRepository, test name byte, spyk, MockK, testcontainers | agents/be/t1-test-guard.md |
| T Test | Test Strategist | T2 | test strategy, test technique, coverage target, property-based, contract test | agents/be/t2-test-strategist.md |
| T Test | Test Generator | T3 | generate test, test generation, write test, focal context, type-driven | agents/be/t3-test-generator.md |
| T Test | Quality Assessor | T4 | test quality, coverage, mutation, validation pipeline, gap analysis | agents/be/t4-quality-assessor.md |
Four execution patterns exist: None (0 systems matched — falls through to LLM classification), Single-Domain (1 agent), Multi-Domain (2-3 agents, parallel dispatch), and Cross-System (multiple orchestrators + synthesizer).
For detailed flow diagrams and examples, see resources/orchestration-protocol.md § Pattern Examples.
Run before any phase execution to ensure clean session state and detect reusable context.
jq is available (command -v jq)~/.claude/cache/engineering-workflow/progress.json
status == "in_progress": previous session was interrupted~/.claude/cache/engineering-workflow/session-summary.json
progress.json with {phase: "pre-flight", status: "in_progress"}[engineering-workflow] Pre-Flight: deps=OK | prev_session={none|interrupted} | summary={available|none}
Resource: Read resources/routing-protocol.md when entering this phase.
--domain, --depth)scripts/classify-query.sh "$QUERY" for keyword-based fast-path classification (2-phase: binary keywords → cross-keyword weighted scoring)prior_boost and suggest domain expansions based on transition patterns (see routing-protocol.md § Step 5.5)resources/constraints-archetypes.jsonneeds_llm_verification == true, i.e., confidence > 0.0 AND < 0.85):
Execute the lightweight LLM verification protocol defined in routing-protocol.md § Step 4.5:
verification_prompt as-is (it is context-specific to system count)classifier: "llm-verified", recalculate domains{ systems: [...], domains: [...], pattern: "...", confidence: float, classifier: "...", prior_boost: float, suggested_expansions: [...], archetype_matched: [...], needs_llm_verification: bool, verification_prompt: string|null }Progressive Classification rollback: Set EW_PROGRESSIVE_CLASSIFICATION=0 to disable.
Status Display:
[engineering-workflow] Phase: Classification | Pattern: {single|multi|cross} | Systems: {DB,BE,...}
Resource: Read resources/orchestration-protocol.md when entering this phase.
.md file(s) from agents/scripts/enforce-budget.sh <pattern> orchestrator-dispatch <output> to verify token budget before proceedingOrchestrator Task prompt template:
You are the {system} System Orchestrator.
## Classification
{classification result from Phase 0}
## User Query
{original user query}
## Instructions
Read the relevant agent definition(s) from agents/{system}/ and dispatch sub-tasks.
Collect agent outputs and resolve intra-system constraints.
Return your analysis in the structured format defined in your orchestrator definition.
BE Test Pipeline Status Display (when T2-T3-T4 loop is active):
[engineering-workflow] Phase: Test Pipeline | Loop: {n}/{max} | Coverage: {pct}% (target: {target}%)
Orchestrators handle this phase internally. Each orchestrator:
.md file(s) from agents/{system}/Each agent determines its confidence score using the calibration rubric in
resources/confidence-calibration.md (5-factor model: input completeness,
specificity, evidence grounding, trade-off coverage, assumption count).
Agent Task prompt template:
You are the {domain} Micro Agent.
## Query Context
{focused sub-question extracted by orchestrator}
## Reference Material
{relevant excerpts loaded by orchestrator via Read with offset/limit}
## Output Requirements
1. Analysis: detailed technical analysis
2. Recommendation: concrete actionable recommendation
3. Constraints: declare any constraints your recommendation imposes on other domains
4. Trade-offs: explicit trade-off documentation
5. Confidence: score between 0.0–1.0 per `resources/confidence-calibration.md` rubric
Resource: Read resources/analysis-audit-protocol.md when entering this phase.
This phase validates agent output quality before constraint resolution.
| Tier | Steps | Additional Tokens |
|---|---|---|
| LIGHT | Confidence gating only | +0.3K |
| STANDARD | Confidence + Completeness + Feasibility | +1.5K |
| THOROUGH | All above + Dynamic Expansion via audit-reviewer agent | +3.5K |
Steps:
0. Tier Determination: Run scripts/audit-analysis.sh tier <classification> <agent-count> — auto-selects LIGHT / STANDARD / THOROUGH based on system count, agent count, depth, and security keywords. Escalation is upward only (see auto-escalation rules below).
scripts/enforce-budget.sh <pattern> quality-gate <output> to verify token budget before auditscripts/audit-analysis.sh confidence per agent result
= 0.70: PASS
validate-agent-output.sh): automatically checked, no LLM cost
validate-agent-output.sh detects number+unit patterns (ms, GB, %, TPS, etc.)trade_offs array length check (>= 2 options)constraints field presence checkconstraints_used environmentaudit-reviewer agent for gap detection and expansionAuto-escalation (upward only):
Resource: Read resources/constraint-propagation.md when entering this phase.
scripts/resolve-constraints.sh to detect conflicts:
KNOWN_CONFLICT_PAIRS in _common.shall_declared_constraints (pre-resolution snapshot) for synthesizer transparency~/.claude/cache/engineering-workflow/constraints.jsonResource: Reuse resources/analysis-audit-protocol.md (already loaded at Phase 2.5).
STANDARD+ tier only. Validates orchestrator output contracts before synthesis.
Steps:
scripts/audit-analysis.sh orchestrator per orchestrator output
system, status, guidance, recommendations, etc.)priority-matrix.mdimpacts are forwarded to unresolved_constraintsOnly activated for Pattern "cross" (cross-system) queries.
scripts/enforce-budget.sh <pattern> synthesis <output> to verify token budget before synthesisagents/synthesizer.mdResource: Reuse resources/analysis-audit-protocol.md (already loaded at Phase 2.5).
THOROUGH tier, cross-system pattern only. Validates synthesis output integrity.
Steps:
scripts/audit-analysis.sh synthesis — verify all systems_analyzed are reflected in unified_recommendationimplementation_order.depends_on references valid phases (topological sort consistency)risk: "high" phases have rollback strategies definedconfidence_assessment.overall is "low", add explicit caveat to outputscripts/format-output.sh to structure the final output## Engineering Analysis: {query summary}
### Classification
- Pattern: {single|multi|cross}
- Systems: {DB, BE, ...}
- Domains: {A, C, ...}
- Depth: {shallow|deep}
### Analysis
{per-domain analysis sections}
### Recommendation
{unified recommendation}
### Constraints
{resolved constraint set}
### Trade-offs
| Option | Pros | Cons | Recommended When |
|--------|------|------|-----------------|
### Implementation Priority
1. {highest priority action}
2. {next action}
...
### Risk Assessment
| Risk | Impact | Likelihood | Mitigation |
|------|--------|------------|------------|
| Mode | Input Example | Behavior |
|---|---|---|
| Query (default) | "Should I use B-tree or LSM for writes?" | Full pipeline: Classify → Dispatch → Execute → Resolve → Format |
| Analyze | analyze: "our current sharding strategy" | Deep analysis without recommendation |
| Compare | compare: "PostgreSQL vs CockroachDB for multi-tenant" | Structured comparison with decision matrix |
| Recommend | recommend: "caching strategy for read-heavy API" | Recommendation-focused with implementation steps |
Depth flag: --depth shallow (1 agent, ~3K) or --depth deep (all relevant agents, ~6-14K, default).
Resources are loaded on-demand per phase. MUST NOT pre-load all resources.
| Phase | Resource to Load | Trigger |
|---|---|---|
| Phase 0 | resources/routing-protocol.md | Always at Phase 0 entry |
| Phase 1 | resources/orchestration-protocol.md | Always at Phase 1 entry |
| Phase 1 (DB) | resources/db-orchestration-protocol.md | When DB system detected |
| Phase 1 (BE) | resources/be-orchestration-protocol.md | When BE system detected |
| Phase 1 (IF) | (stub — no dedicated protocol; uses general orchestration-protocol.md) | When IF system detected |
| Phase 1 (SE) | resources/se-orchestration-protocol.md | When SE system detected |
| Phase 2 | resources/confidence-calibration.md | Loaded by orchestrators for agent confidence scoring |
| Phase 2.5 | resources/analysis-audit-protocol.md | Always at Phase 2.5 entry (reused in 3.5, 4.5) |
| Phase 3 | resources/constraint-propagation.md | Always at Phase 3 entry |
| Phase 3 | resources/priority-matrix.md | When conflicts detected (reused in Phase 4) |
| Phase 4 | resources/synthesis-protocol.md | Cross-system pattern only |
| Any | resources/error-playbook.md | On error occurrence |
Agent definitions (loaded by orchestrators during Phase 2):
.md files: loaded by Gateway Router in Phase 1.md files: loaded by orchestrators in Phase 2agents/synthesizer.md: loaded by Gateway Router in Phase 4 (cross-system only)Reference excerpts (loaded by agents during Phase 2):
Read with offset/limit to load relevant sections from large reference filesAgents declare constraints (requires | recommends | prohibits | conflicts_with) in their output. Constraints flow upward through orchestrators → synthesizer for resolution. Hard constraints MUST be respected; soft constraints may be overridden with justification.
Schema, flow diagrams, and storage: resources/constraint-propagation.md
Token budgets are guidelines, not hard limits. Exceeding the budget triggers reference excerpt truncation, not query failure.
| Pattern | Agents | Budget | Audit | Total |
|---|---|---|---|---|
| Shallow | 1 | ~3.5K | +0.3K (LIGHT) | ~3.8K |
| Analysis only | 1-4 | ~6K | +1.5K (STANDARD) | ~7.5K |
| Implementation guide | 3-6 | ~8K | +1.5K (STANDARD) | ~9.5K |
| Test generation | 3-5 | ~10K | +1.5K (STANDARD) | ~11.5K |
| Full pipeline | 6-10 | ~12K | +1.5K (STANDARD) | ~13.5K |
| Cross-system | 3-6 | ~15K | +3.5K (THOROUGH) | ~18.5K |
| Cross-system (pruning) | 3-6 | ~10K | +3.5K (THOROUGH) | ~13.5K |
Note: Budgets include ~20% contingency for complex queries requiring additional reference loading. Actual token usage is typically 10-20% below budget for standard queries.
Budget enforcement: Run scripts/enforce-budget.sh <pattern> <phase> <output> at phase transitions.
Exits non-zero if estimated tokens exceed 120% of budget. Patterns: shallow, analysis, implementation, test, full, cross-system, cross-pruning.
Budget guidelines:
Resource: Read resources/error-playbook.md on error occurrence.
| Category | Example | Response |
|---|---|---|
| Agent timeout/failure | Agent Task does not return within 60s | Fallback to general guidance from orchestrator |
| Constraint conflict | Two agents impose contradictory requirements | Escalate to synthesizer with both positions |
| Missing reference data | Referenced document or section not found | Degrade gracefully; note data gap in output |
| Unknown domain | Query does not match any routing keywords | Return routing suggestions with related domains |
| Token budget exceeded | Cumulative tokens exceed budget guideline | Truncate reference excerpts; preserve agent analysis |
| Cross-system failure | One orchestrator fails in cross-system query | Return partial results from successful orchestrators with warning |
| Classification ambiguity | confidence < 0.50 after LLM classification | Ask user for domain clarification |
1. Agent fails → Orchestrator provides fallback analysis
2. Orchestrator fails → Gateway Router provides high-level guidance
3. Multiple failures → Report partial results + clear error summary to user
4. Total failure → Return classification result + suggest manual domain selection
Long sessions with multiple queries accumulate context. Monitor and manage proactively.
| Usage | Level | Response |
|---|---|---|
| 70% | WARNING | Minimize reference loading; rely on agent expertise |
| 80% | RECOMMEND | Complete current query, then suggest /compact |
| 85% | CRITICAL | Truncate all non-essential context; complete with minimal references |
1. /compact executed → context summarized
2. Check for classification result in context
3. IF not found AND mid-query:
- Re-run classify-query.sh (fast, deterministic)
- Re-read only the orchestrator .md needed for current phase
4. Resume from current phase
Display current state at each phase entry.
[engineering-workflow] Phase: {phase} | Pattern: {pattern} | Systems: {systems} | Budget: {used}/{total}K
[engineering-workflow] Phase: Classification | Pattern: pending | Systems: pending
[engineering-workflow] Phase: Agent Execution | Pattern: cross-system | Systems: DB,BE,SE | Budget: 5.8/14K
Session pattern caching: ~/.claude/cache/engineering-workflow/ (details in constraint-propagation.md)
| Agent | Purpose | Model |
|---|---|---|
| db-orchestrator | Database system orchestration | sonnet |
| be-orchestrator | Backend system orchestration | sonnet |
| if-orchestrator | Infrastructure system orchestration (stub) | haiku |
| se-orchestrator | Security system orchestration | sonnet |
| synthesizer | Cross-system synthesis and constraint resolution | sonnet |
| audit-reviewer | Analysis quality audit (THOROUGH tier only) | sonnet |
| Document | Purpose |
|---|---|
| routing-protocol.md | Query classification algorithm and domain detection matrix |
| orchestration-protocol.md | Agent invocation procedure and Task prompt construction |
| constraint-propagation.md | Constraint flow, merge logic, and conflict resolution |
| be-orchestration-protocol.md | BE 4-cluster agent selection, chain rules, and dispatch protocol |
| error-playbook.md | Error handling procedures and fallback strategies |
| analysis-audit-protocol.md | Analysis Quality Gate, Contract Enforcement, Synthesis Validation |
| db-orchestration-protocol.md | DB agent selection matrix, dispatch protocol, and result merge algorithm |
| se-orchestration-protocol.md | SE 6-cluster agent selection, 8 chain rules, and security dispatch protocol |
| priority-matrix.md | Universal priority hierarchy for conflict resolution across all systems |
| synthesis-protocol.md | Cross-system synthesis procedure and dependency graph construction |
| confidence-calibration.md | 5-factor confidence scoring rubric for micro agents |
| constraints-archetypes.json | Archetype library — preset constraint sets for common architecture patterns |
| Script | Purpose |
|---|---|
| classify-query.sh | Deterministic keyword-based query classification (fast-path) |
| resolve-constraints.sh | Constraint conflict detection and auto-resolution |
| validate-agent-output.sh | Agent output JSON schema + quality indicator validation |
| audit-analysis.sh | Deterministic audit checks (confidence, schema, synthesis, tier) |
| format-output.sh | Output formatting for display (supports --summary for compact output, --graph for Mermaid constraint graph) |
| enforce-budget.sh | Token budget enforcement — exits non-zero if output exceeds 120% of budget |
| _common.sh | Shared utilities — imported by all other scripts (not called directly) |
references/db/ — 18 files covering domains A-F (mapped in db-orchestrator.md § Load Reference Excerpts)references/be/ — 11 files covering clusters S/B/R/T (mapped in be-orchestrator.md § Load Reference Excerpts)references/se/ — 7 files covering clusters A/Z/E/N/C/V + best practices (mapped in se-orchestrator.md § Load Reference Excerpts)npx claudepluginhub hungrytech/hungrytech-claude-skills --plugin engineering-workflowDesigns system architecture for tech stack, API contracts, data models, and infrastructure shape. Supports brownfield extensions and engagement modes from Express to Meticulous.
Designs scalable backend APIs and microservices architectures focusing on service boundaries, data contracts, resilience, observability, and distributed systems. Use for new services or integration planning.
Designs system architecture and high-level technical strategy. Use for new systems or subsystems, major refactors, technology selections, system boundaries, and long-term decisions with broad impact.