loa-constructs

Security and quality audit of application codebase

Autonomous agent execution mode

Bridgebuilder — Autonomous PR Review

Triage a bug report through structured phases and create micro-sprint

L2 cost-budget enforcer — daily token cap with fail-closed semantics under uncertainty (billing-API primary, internal counter fallback, periodic reconciliation cron)

L5 cross-repo status reader — reads structured cross-repo state via gh API with TTL cache + stale fallback, BLOCKER extraction from NOTES.md, per-source error capture, p95 <30s for 10 repos

Design and deploy production infrastructure

Launch PRD discovery with codebase grounding and context ingestion

Query Flatline protocol knowledge base via NotebookLM integration

L4 graduated-trust ledger — per-(scope, capability, actor) trust tier with hash-chained immutable history, configurable transitions, auto-drop on operator override + cooldown enforcement, and force-grant audit-logged exceptions

L1 jury-panel adjudication primitive — convenes ≥3 panelists, logs reasoning, selects binding view via deterministic seed

Execute sprint tasks with production-quality code and tests

Install Loa framework onto an existing repository

Red Team — Generative Adversarial Security Design

Validate sprint implementation against acceptance criteria

Analyze codebase to extract reality into Loa artifacts

Run documentation-driven testing against Ground Truth and protocols

Run Bridge — Autonomous Excellence Loop

Autonomous sprint execution mode

L3 generic 5-phase autonomous-cycle template — schedules a DispatchContract (reader → decider → dispatcher → awaiter → logger) via /schedule, with flock-guarded concurrency, content-addressed idempotency, and optional L2 budget pre-check

Simstim - HITL Accelerated Development Workflow

L7 soul-identity-doc — schema + SessionStart hook for descriptive `SOUL.md` (descriptive identity complement to prescriptive `AGENTS.md`). Composes with audit-envelope (soul.surface event), context-isolation-lib (sanitize body at SessionStart surfacing), and the prescriptive-rejection pattern file (NFR-Sec3 enforcement).

Create comprehensive Software Design Document based on PRD. System architecture, tech stack, data models, APIs, security design.

Archive the current development cycle and prepare for a new one. Creates a dated archive with all cycle artifacts.

Security audit of deployment infrastructure. Reviews server setup, configs, hardening, secrets management.

Comprehensive security and quality audit of the application codebase. OWASP Top 10, secrets, architecture, code quality review.

Security and quality audit of sprint implementation. Final gate before sprint completion. Creates COMPLETED marker on approval. Resolves local sprint IDs to global IDs via Sprint Ledger.

Triage a bug report through structured phases: eligibility check, hybrid interview, codebase analysis, and micro-sprint creation. Produces a handoff contract for /implement. Test-first is non-negotiable. Bugs always get their own micro-sprint.

Build the current sprint

Browse, select, and install packs from the Loa Constructs Registry. Multi-select UI for composable pack installation.

Create a standards-compliant PR to contribute improvements to Loa upstream. Includes pre-flight checks, secrets scanning, DCO verification, and PR creation.

Design and deploy production infrastructure. IaC, CI/CD, monitoring, security hardening, operational docs.

Enhance a prompt for better outputs

Submit developer feedback about Loa experience with optional execution traces. Creates GitHub Issues with structured format for debugging. Smart routing to appropriate ecosystem repo (loa, loa-constructs, forge, project). Construct-aware routing files issues on construct vendor repos with content redaction. Open to all users (OSS-friendly).

Manual invocation of Flatline Protocol for adversarial multi-model review. Use when auto-trigger is disabled or to re-run after document changes. Also provides rollback capability for autonomous integrations.

Execute sprint tasks with production-quality code and tests. Automatically checks for and addresses audit/review feedback before new work. Resolves local sprint IDs to global IDs via Sprint Ledger. If beads_rust is installed, handles task lifecycle automatically (no manual br commands).

View and manage Sprint Ledger status. Provides global sprint numbering and cycle management.

Install Loa framework onto an existing repository. Prepares the System Zone, initializes State Zone structure, and sets up integrity verification. "The Loa mounts the repository, preparing to ride."

View and analyze HITL permission requests to optimize settings.json

Launch PRD discovery with automatic codebase grounding and context ingestion. For brownfield projects, automatically runs /ride analysis before PRD creation. Reads existing documentation from grimoires/loa/context/ before interviewing. Initializes Sprint Ledger and creates development cycle automatically. Use --fresh flag to force re-running /ride even if recent reality exists.