AI Agent Workflow Collection

AI SDLC approvals, sandbox, and command rule workflow. Use when an AI assistant needs to decide whether to request escalated permissions, explain sandbox failures, propose prefixrule approvals, avoid unsafe command patterns, or document why a command was or was not rerun outside the sandbox. Supports --quick-flow for fast assumption-driven execution and --full-flow for question-driven verified execution.

Optional AI SDLC architecture workflow. Use when an AI assistant needs to define system boundaries, components, interfaces, architectural constraints, alternatives, decisions, tradeoffs, risks, or validation for a feature and produce routed human and machine artifacts linked to requirements and durable decisions. Supports --quick-flow for focused design and --full-flow for strict decision, risk, and validation coverage.

AI SDLC business analysis workflow. Use when an AI assistant needs to frame a feature or change before implementation, derive actors, workflows, business rules, assumptions, acceptance criteria, and richer spec context for requirements and design. Supports --quick-flow for fast assumption-driven execution and --full-flow for question-driven verified execution. Explicit full or end-to-end spec refinement requests continue through the existing 18-stage refinement cascade.

Use when goals, capabilities, and epics are defined and you need to decompose them into features, user stories, acceptance summaries, and cross-functional delivery tasks. Supports --quick-flow for fast assumption-driven execution and --full-flow for question-driven verified execution. Explicit full or end-to-end spec refinement requests continue through the existing 18-stage refinement cascade.

Use when PRFAQ, BRD, PRD, product brief, workflow, or equivalent initiative artifacts exist and you need to review them for planning gaps, unclear scope, weak priorities, missing actors, and backlog-blocking ambiguity before decomposing work. Supports --quick-flow for fast assumption-driven execution and --full-flow for question-driven verified execution. Explicit full or end-to-end spec refinement requests continue through the existing 18-stage refinement cascade.

AI SDLC Git-flow branching workflow. Use when an AI assistant starts implementation work, needs to create or verify a task branch, checks branch/spec alignment, or prepares to hand off a completed user-visible task to validation and commit prep. Supports --quick-flow for fast assumption-driven execution and --full-flow for question-driven verified execution.

AI SDLC change-impact and lifecycle recovery workflow. Use when a requirement, acceptance criterion, decision, API contract, risk assumption, or other traced source changed after downstream artifacts were created and an AI assistant must identify stale artifacts, affected lifecycle stages, and evidence-backed reopen or revalidation actions without silently rewriting authoritative state. Supports --quick-flow for focused trace scanning and --full-flow for strict state and source-evidence gates.

AI SDLC controlled change-workspace and specification-delta workflow. Use when an AI assistant needs to create or validate an isolated proposal workspace, author and validate requirement deltas, preview canonical changes, or apply and archive an explicitly approved change with rollback evidence. Supports --quick-flow for assumption-driven drafts and --full-flow for strict owner, target, evidence, and authority checks.

AI SDLC code review workflow. Use when an AI assistant is asked to review a diff, PR, branch, commit, staged changes, or completed implementation against SDD requirements, tests, API contracts, security, and scope discipline. Supports --quick-flow for fast assumption-driven execution and --full-flow for question-driven verified execution.

AI SDLC commit preparation workflow. Use when an AI assistant is asked to commit repository changes, prepare an auditable commit message, stage files safely, include SDD traceability, verify branch/spec alignment, or verify the working tree before committing. Supports --quick-flow for fast assumption-driven execution and --full-flow for question-driven verified execution.

AI SDLC Conventional Commit workflow. Use when an AI assistant drafts, validates, reviews, or fixes commit messages in this repository, especially when commits must include SDD spec references, validation summaries, or safe conventional commit subjects. Supports --quick-flow for fast assumption-driven execution and --full-flow for question-driven verified execution.

AI SDLC repository delivery-graph and evidence-freshness workflow. Use when an AI assistant needs to index lifecycle traceability, resolve end-to-end paths, report gaps or orphans, register evidence identity, propagate stale dependencies, or calculate fresh evidence coverage. Supports --quick-flow for deterministic local analysis and --full-flow for strict trace and evidence review.

Use after story and spec synthesis to perform a strict delivery handoff review, identify remaining gaps or contradictions, and score readiness for engineering and cross-functional execution. Supports --quick-flow for fast assumption-driven execution and --full-flow for question-driven verified execution. Explicit full or end-to-end spec refinement requests continue through the existing 18-stage refinement cascade.

Use when a PRFAQ, BRD, or equivalent discovery package exists and you need to review it for delivery gaps, contradictions, missing business rules, and insufficient implementation handoff detail before writing user stories or specs. Supports --quick-flow for fast assumption-driven execution and --full-flow for question-driven verified execution. Explicit full or end-to-end spec refinement requests continue through the existing 18-stage refinement cascade.

Use when stories and clarified delivery context are ready and you need to produce a structured delivery specification that engineering and cross-functional teams can use for implementation planning and handoff. Supports --quick-flow for fast assumption-driven execution and --full-flow for question-driven verified execution. Explicit full or end-to-end spec refinement requests continue through the existing 18-stage refinement cascade.

AI SDLC installation diagnostics and safe upgrade planning. Use when an AI assistant needs to inspect harness prerequisites, repository layout, module and skill registration, detect actionable installation problems, compare versioned file inventories, preview additions/modifications/removals/schema migrations, or produce backup and rollback plans without applying an upgrade. Supports --quick-flow and --full-flow.

Optional AI SDLC evidence-council workflow. Use when an AI assistant needs to review a high-impact topic through several explicit perspectives, orchestrate simulated lenses or truly independent reviewer executions, and synthesize evidence-backed agreements, conflicts, proposals, owners, and unresolved questions without allowing panel members to rewrite authoritative artifacts. Supports --quick-flow for labeled simulated review and --full-flow for stricter panel and evidence coverage.

Guided AI SDLC Explore then Apply workflow. Use when a contributor needs one readable entrypoint that classifies intent before feature selection, explains context, rigor, roles, workspaces, blockers, and planned writes, then revalidates and starts exactly one lifecycle checkpoint.

Use when planning inputs are clear enough and you need to map business goals, roles, capabilities, and outcome-oriented epics before detailed backlog decomposition. Supports --quick-flow for fast assumption-driven execution and --full-flow for question-driven verified execution. Explicit full or end-to-end spec refinement requests continue through the existing 18-stage refinement cascade.

AI SDLC host adapter and capability negotiation workflow. Use when an AI assistant needs to validate a host adapter manifest, map portable workflow operations to host-native operations, negotiate capabilities and limits, select deterministic semantic-preserving fallbacks, or explain why a host cannot run a plan. Supports --quick-flow and --full-flow.

AI SDLC context-aware navigation workflow. Use when an AI assistant needs to determine what to do next, select the right installed skill, start or resume a feature, explain blockers, inspect available capabilities, or provide evidence-backed required and optional next actions from repository state. Supports --quick-flow for compact guidance and --full-flow for stricter context verification.

AI SDLC package trust and privacy-preserving local metrics workflow. Use when an AI assistant needs to verify package origin, file integrity, harness compatibility, declared capabilities, provenance evidence, or generate reproducible aggregate run, retry, budget, coverage, and freshness metrics without collecting source, prompts, commands, or diffs. Supports --quick-flow and --full-flow.

AI SDLC versioned policy-as-code workflow. Use when an AI assistant needs to resolve layered delivery policy, evaluate an action with explainable rules and gates, protect organization minimums from weaker overrides, apply or reject an expiring waiver, or select a reusable assurance profile. Supports --quick-flow for deterministic evaluation and --full-flow for strict owner and exception review.

Use when working-backwards discovery is complete and you need to synthesize a PRFAQ, FAQ package, and business requirements document tied to business value, scenarios, and testable acceptance logic. Supports --quick-flow for fast assumption-driven execution and --full-flow for question-driven verified execution. Explicit full or end-to-end spec refinement requests continue through the existing 18-stage refinement cascade.