GAAI-framework

Validate that all Discovery artefacts (Epics, Stories) are clear, governed, complete, and safe to pass into Delivery. Activate after generating Epics or Stories and before any Delivery planning. This is the mandatory Discovery → Delivery gate.

Scan all agent and sub-agent definition files in .gaai/core/agents/, extract YAML frontmatter, merge with specialists.registry.yaml, and generate a derived agents-index.yaml at .gaai/core/agents/agents-index.yaml. Activate after adding, modifying, or removing any agent, sub-agent, or specialist entry.

Implement validated GAAI OSS backlog Stories by activating the Delivery Agent and applying backlog-first delivery rules.

Guide creation of a new GAAI skill following the agentskills.io spec and GAAI best practices. Activate when adding a new skill to the .gaai/core/skills/ catalog.

Identify and formalize durable product and technical decisions from agent outputs into long-term memory. Activate after Discovery produces artefacts, Delivery resolves trade-offs, or product direction materially changes.

Adversarial review of any input (human idea, agent analysis, research report, feedback, observation) BEFORE it mutates persistent project state. Universal interceptor with domain auto-detection, 2-phase classification + evaluation, and triple-verdict output (veracity / fit / actionability). Anti-girouette guardrail that distinguishes drift from pivot — preserves human decisional authority. Manual invocation only (no hooks, no enforcement). Activate when an input may affect strategic-frame.md, a DEC, an OT, an architecture/pattern doc, an agent definition, a backlog story scope/AC/wedge field, or user-facing copy.

Translate product intent or a PRD into a small set of outcome-driven Epics (3–7 max). Activate when starting a new product, adding a significant feature domain, or breaking down a PRD into actionable user outcomes.

Translate a single Epic into clear, actionable User Stories with explicit acceptance criteria. Activate when an Epic is defined and work needs to be prepared for Delivery execution.

Search local GAAI OSS project memory without using GAAI Cloud MCP tools.

Initialize or refresh a project's GAAI OSS memory by activating the Bootstrap Agent and context-bootstrap workflow.

Start, stop, or inspect the GAAI OSS autonomous delivery daemon from Codex.

Activate the GAAI OSS Discovery Agent to clarify intent and produce governed artefacts such as PRDs, Epics, Stories, and decisions.

Summarize current GAAI OSS project state, including backlog, memory, rules, skills, and framework health.

Update or redeploy the local GAAI OSS framework and Codex adapter without invoking GAAI Cloud behavior.

Validate that implemented code fully satisfies Story acceptance criteria, respects rules, and introduces no regressions. This is the hard quality gate — no pass means no delivery. Activate after implementation is complete.

After QA PASS, compare the Story's implementation footprint against relevant memory entries. Reports confirmed entries, contradictions, and new knowledge candidates. Never writes to memory — produces a delta report for Discovery to action.

Generate correct, minimal, maintainable code that satisfies a validated Story's acceptance criteria against an execution plan. Activate when a Story is validated, a plan exists, and all prerequisites are unambiguous.

Decompose a high-level delivery plan into a precise, file-level execution sequence with explicit ordering, edge cases, and test checkpoints. Activate after delivery-high-level-plan for complex or multi-phase Stories before implementation begins.

Adversarial review of generated stories against the Discovery Session Brief, referenced DECs, and Epic DoR. Detects contradictions, omissions, and intent drift BEFORE stories reach Delivery. Produces a structured verdict (PASS/FAIL) with specific findings per story. Triggers after generate-stories, before backlog registration as refined.

Compact verbose memory index / registry files to pointer-only form. Activate when an index file (index.md, index-decisions.md, or any sibling registry table) breaches the file-size budget OR shows substance-duplication drift. Distinct from memory-compact (which targets content categories) and memory-archive-superseded (which migrates superseded rows to archive).

Detect and heal index.md drift — finds memory files on disk not registered in index.md and registers them. Run when /gaai-status reports unregistered files, after batch memory operations, or as a post-delivery gate.

Takes surface scan results, optional LLM synthesis open-question entries, and optional tree-sitter AST signals to score project ambiguities (1-10). Outputs structured ambiguity_feed for smart-question-generator. Pure heuristic — no LLM calls. Designed for Stage 3.5 of the /gaai:bootstrap pipeline (between LLM synthesis and Q&A).

Construct the LLM synthesis prompt from project surface scan + optional tree-sitter context + optional Q&A answers. Call the LLM. Parse and validate the response into 6-8 structured memory entries with clarity tags and source traceability. Used as Stage 3 of the /gaai:bootstrap pipeline.

Write structured memory entries to the Cloud workspace via gaai_memory.store MCP tool with source='bootstrap'. Loops over entries from bootstrap-llm-synthesis, calls the tool per entry, collects success/fail counts. Used as Stage 5 of the /gaai:bootstrap pipeline (Cloud path only).

Maintain a canonical i18n glossary file — sync new terms across all language pairs, detect drift, flag missing translations, and enforce consistent terminology across the codebase.

Migrate a superseded DEC's index rows from active `index.md` to `archive/superseded-decisions.archive.md`. Idempotent. Discovery-only — never invoked by daemon delivery. Updates DEC frontmatter as canonical source of truth.

Validate discoverability invariants of memory `index.md` and `archive/superseded-decisions.archive.md`. Tool-agnostic L3 prompt + capability-dependent L4 script. Detects table corruption, dangling/orphan supersession pointers, frontmatter inconsistencies, missing affordance signals.

Transform validated knowledge into structured long-term memory. Activate after Bootstrap scan, after Discovery produces validated artefacts, or after architecture insights are available.

Scan all memory files, documentation (**/docs/**/*.md), and README files (**/README.md) for drift, contradictions, and stale references. Produce a reconciliation report for Discovery to action. Activate on demand or via cron.

Search memory by frontmatter fields, full-text keywords, or cross-reference graph. Returns ranked file list — never loads full content. Use when the agent needs to find relevant memory without knowing exact paths.

Takes aggregated ambiguity insights from the LLM synthesis stage and produces ≤5 ranked questions to surface to the user. Applies a two-layer anti-fabrication filter (pre-LLM exclusion of score<3 insights + post-LLM structural strip) so that Q&A surfaces only genuine ambiguities. Used as Stage 4 of the /gaai:bootstrap pipeline.

Counts Q&A skip events from the abort-safe-handler and qa-loop-ui outputs. Shows an optional skip-reason dropdown when a user-initiated skip occurred. Produces a structured skip_metrics_record suitable for PostHog ingestion. Used in Stage 4 of the /gaai:bootstrap pipeline after abort-safe-handler returns.

Presents up to 5 questions from smart-question-generator one at a time, records answers, handles per-question skip and skip-all, captures per-question response time and total session duration. Renders a streaming progress header with question count and time estimate. Used as the interaction layer of Stage 4 of the /gaai:bootstrap pipeline.

Orchestrator-level Stage 4 entry gate for /gaai:bootstrap. Presents a pre-loop "Skip Q&A entirely" option, delegates to qa-loop-ui when the user proceeds, and returns a unified abort_safe_result with telemetry on every path. Guarantees no partial state on skip or abort.

Scan project root for file tree, dominant languages, and LOC estimate. Produces structured baseline context for Stage 2 LLM synthesis during bootstrap. Respects .gitignore and standard exclusions. Outputs per-directory file counts, ranked language list, size class, and observability summary.

Validate sub-agent handoff artefacts, sequence phase transitions, and manage retry and escalation logic. Activate after each sub-agent terminates to determine next action.

Apply three deterministic heuristics to a single memory-delta file to produce a structured verdict block; invoke memory-ingest on ACCEPTED candidates only in validate mode. Activate when Discovery processes a raw memory-delta from contexts/artefacts/memory-deltas/.

Load only the minimum relevant memory for a task using 3-level progressive disclosure. Activate before context-building — never load full memory dumps. Never substitute summaries for durable memory.

Discover structurally similar patterns across domains, assess transfer viability via structural invariant checking, and propose domain adaptations with risk gates. Activate when Discovery identifies a problem that may have been solved in another domain.

Scan SKILL.md files in .gaai/core/skills/ and .gaai/project/skills/, extract YAML frontmatter, and regenerate separate skills indices for each layer. Core index ships with the OSS framework; project index is project-specific.