gzkit

Validate and stage a candidate rendition from the corpus via gz content compose. Use when the agent has made compression decisions (drop/combine/rewrite of compressible corpus entries toward the declared setpoint) and wants the tool to validate invariant-floor compliance, compute byte evidence, write the candidate artifact, and emit a ledger event.

Enter and exit the MX Maintenance Hangar — operator's interface to gz mx. Use when entering the hangar to perform governance repair, checking hangar status mid-session, or cleanly exiting when repair is complete. Operator operates the skill; the skill invokes gz mx; nobody shells out.

Create and resume session handoff documents for agent context preservation across engineering sessions.

Create and resume session handoff documents for agent context preservation across engineering sessions.

Collaborative design dialogue that produces GovZero ADR artifacts. Use when exploring a new feature, capability, or architectural change before implementation — replaces superpowers brainstorming for this project. Triggers on "design X", "let's design", "brainstorm X", "I want to build X", "gz-design".

Cross the airlock membrane — the entry/exit gate every unit of work passes through (ADR-0.33.0). Use to inspect a target's seam-map before touching it (`gz airlock in`), account for what a transit disturbed (`gz airlock out`), or make a governed ad-hoc reconnaissance entry with light repair at most (`gz permitted-entry`). Diagnostic-only for now — a staged posture, not the declared end state; never writes L1 canon.

Run full quality checks in one pass. Use for pre-merge or pre-attestation quality verification.

Run full quality checks in one pass. Use for pre-merge or pre-attestation quality verification.

Create and book a GovZero ADR with its OBPI briefs. Enforces next-free-integer nominal allocation for foundation IDs and five-gate compliance. Portable skill for GovZero-compliant repositories.

Create and book a GovZero ADR with its OBPI briefs. Enforces next-free-integer nominal allocation for foundation IDs and five-gate compliance. Portable skill for GovZero-compliant repositories.

Do the work described in a GHI, then close it with verifiable evidence. Use to execute and resolve an open defect, enhancement, or investigation — the skill performs the fix, verifies artifacts, and closes the issue in one sweep.

Gate-5 audit templates and procedure for ADR verification. GovZero v6 skill.

Namespace router → ADR/OBPI/ledger governance skills. Use to pick the governance intent before invoking the matched skill directly.

Reconcile an OBPI brief against current project state and optionally write operator-attested amendments. Use when a brief's allowlist, discovery checklist, verification verbs, REQ count, or citation tuples may have drifted from reality.

Claim or release OBPI-level work locks for multi-agent coordination. Use when claiming an OBPI before starting work, releasing a lock after completing or abandoning work, or checking which OBPIs are currently claimed by agents.

OBPI-scoped code review for reuse, quality, and efficiency. Resolves scope from the brief's Allowed Paths, reviews across three dimensions, and applies fixes. Use after implementation, before reconcile.

OBPI brief reconciliation — Audit briefs against evidence, fix stale metadata, sync ADR table, write ledger proof.

Pre-flight alignment audit — verify ADR intent, OBPI brief scope, and plan are aligned before implementation begins. Use when exiting plan mode, before starting implementation, or to catch scope drift between ADR intent and the active OBPI brief.

Route agents to the correct skill for a given task type. Use when starting a session, when unsure which skill applies, or when an agent needs to discover the right workflow for a task.

Gate-5 audit templates and procedure for ADR verification. GovZero v6 skill.

OBPI brief reconciliation — Audit briefs against evidence, fix stale metadata, sync ADR table, write ledger proof.

Pre-flight alignment audit — verify ADR intent, OBPI brief scope, and plan are aligned before implementation begins. Use when exiting plan mode, before starting implementation, or to catch scope drift between ADR intent and the active OBPI brief.

Execute the ADR closeout ceremony protocol for human attestation. GovZero v6 skill.

Post-plan OBPI execution pipeline — implement, verify, present evidence, and sync after a plan is approved. Use after exiting plan mode for an OBPI, when the user says "execute OBPI-X.Y.Z-NN", or to enforce governance on already-implemented work via --from=verify or --from=ceremony.

Execute the ADR closeout ceremony protocol for human attestation. GovZero v6 skill.

Post-plan OBPI execution pipeline — implement, verify, present evidence, and sync after a plan is approved. Use after exiting plan mode for an OBPI, when the user says "execute OBPI-X.Y.Z-NN", or to enforce governance on already-implemented work via --from=verify or --from=ceremony.

Create and semantically author OBPI briefs linked to parent ADR items. Use when decomposing implementation into OBPI increments.

Create and semantically author OBPI briefs linked to parent ADR items. Use when decomposing implementation into OBPI increments.

Author a GitHub Issue (GHI) for a defect, enhancement, or investigation surfaced in flight. Use when a defect cannot be fixed in the current patch, when scope expansion would violate the active brief's boundaries, or when a finding deserves a trackable home before routing.

Build ADR-to-artifact traceability using gz state and repository search.

Validate configured and manifest path coherence. Use when diagnosing control-surface or path drift.

Namespace router → maintenance and code-quality chore skills. Use to pick the chore intent before invoking the matched concrete skill directly.

Audit CLI documentation coverage and headings. Use when verifying command manpage and index parity.

Run a monthly B+ competitor-discovery radar for spec-driven and agent-workflow tools, render JSON-governed reports, grill suggested gzkit moves, and route approved opportunities without unattended governance mutation.

Preview complexity advisor diagnosis, understand auto-chain context, or check intrinsic complexity attestation guidance. Use when the operator says "preview complexity advisor", "complexity diagnosis", "advisor recommendation", "what does the advisor say", or "intrinsic complexity attestation".

Run a complexity distillation pass against the exemplar corpus to refresh distilled-characteristics doctrine. Use when the operator says "run distillation", "refresh complexity corpus", or "distill complexity" — and at the cadence triggers below (annual calendar, advisor verdict-frequency drift > 25% from baseline, or operator judgment for a ground-breaking project).

Preview authoring-time complexity hints before committing. Use when the operator says "authoring-time complexity hint", "complexity guide preview", "preview before commit", or "advise-band hints".

Create constitution artifacts. Use when governance constitutions must be created or refreshed.

Trim per-turn agent context weight by lifting pedagogical narrative from AGENTS.md, CLAUDE.md, and .claude/rules/** to docs/governance/, leaving binding bullets and one-line pointers behind. Use when the per-turn contract surface has accreted multi-paragraph rationale and "Why this is canon" codas, when an operator asks for a "diet" or "progressive disclosure" pass on the agent contract, or when the advisory scorecard surfaces Judgment-class duplicates that can be folded into Mechanical neighbors. Thin trigger-discovery wrapper for the `instructions-files-diet` chore — the chore's `CHORE.md` carries the procedure.

Run Gate 2 verification and record result events. Use when validating implementation progress for an ADR.