runx

Governed runtime for agent skills: discover and install portable skills, run bounded skill graphs with explicit authority, and inspect signed receipts for what happened.

Audit a sealed runx receipt for governance, comparing the authority a run exercised against what it was granted, and flag over-reach, ungated mutation, unrecorded refusals, or exposed secret material.

Verify the receipt ids behind a normalized authority-usage summary, compare that evidence with granted scopes, and propose the narrowest grant the evidence supports.

Answer a cross-run audit question against the receipt ledger, returning matched receipts and a chain-verification result.

Read durable reflect projections, group repeated signals by skill, and emit validated handoffs to skill-lab improve when the evidence clears configured floors.

Review receipts and harness failures to propose bounded skill improvements.

Read Runx's native receipt history and skill catalog, then return deterministic run outcomes, catalog test coverage, and governance follow-ups without model-authored metrics.

Canonical Runx skill-authoring implementation. Use for designing, creating, updating, improving, or adding harness coverage to a Runx skill package; it combines bounded agent judgment with native file writes, inspection, and safe harness validation. When a host skill-creator also triggers, use its general guidance but execute Runx work through this skill.

Audit exact npm dependency versions against OSV and emit a reproducible evidence packet with zero unverified findings.

Wrap a borrowed Anthropic SKILL.md under a governed runx overlay, with scope bounds, an allowed-tool set, and a pinned digest, so the open skill ecosystem can run under runx authority without editing the upstream skill.

docs-demo runx skill. Replace this with what the skill does and returns.

Run a standing team with a mandate, advanced one governed case-turn at a time: a fixed roster, a persistent objective, a multi-turn case, member dispatch under a scoped grant, escalation gates, a measurable done-check, and a sealed receipt trail.

Build a scoped brand voice packet from source material so downstream agents can write, review, and adapt content without inventing brand claims.

Route one business signal through a replayable governed ops graph: classify, docs, release, work, outreach, spend, and proof, with consequential actions stopping at the right gate.

Govern one inbound provider-side paid tool call through price, challenge, credential verification, receipt sealing, and receipt-gated forwarding.

Convert mailbox and calendar context into a reviewable executive action packet.

Research a topic, draft the content, and package the approved publication bundle.

Govern provider-agnostic data reads and state transitions through declared data-source operations, not model-authored raw queries.

Produce an approved deep-research brief from bounded research, synthesis, and governed packaging.

Prepare a governed dispute response artifact from a linked charge receipt.

Produce an approved ecosystem briefing from bounded research and a governed content pass.

Governed repo evolution with fixed phase semantics and bounded outcomes.

Extract schema-validated JSON from messy HTML or text fixtures with digest-bound provenance.

Turn evidence and operator intent into publication-ready drafts and handoff packets.

Plan a scoped pull or push of GitHub issues, threads, or PRs, gating any write behind human approval.

Gather an external source, scrub personal data before it crosses the boundary, plan a human-approved notification, and seal the run to the ledger.

Classify a bounded support request, choose the safe next path, and draft a customer-ready reply only when a human-gated send is appropriate.

Turn a noisy inbound request into a bounded intake artifact and an explicit next runx lane.

Govern a scafld-backed issue-to-PR lane with native scafld review and handoff surfaces.

Discover, analyze, and draft high-signal issue-thread responses and follow-up actions.

Route one question or source event through a supplied knowledge catalog to validated source, owner, escalation, and follow-up skill references. Use for evidence discovery and ownership routing, not broad business-action fanout or answering the question itself.

Enrich a lead from supplied account signals and produce a reviewable outreach recommendation.

Qualify a lead and route it to the right governed action, direct outreach, a nurture campaign, or a recorded hold, sealing which path was taken and why.

Govern a bounty-style messageboard from post through moderation, claim, delivery, acceptance, payout authorization, and trial take evidence.

Scan for posting opportunities and prepare governed Moltbook publication packets.

Validate a runx execution context and hand off a governed payload to an n8n workflow webhook with scoped auth, idempotency, and receipt expectations.

Fetch National Weather Service forecast evidence through the governed HTTP front, producing a sealed provider packet for downstream weather planning.

Resolve a place and fetch global forecast and air-quality evidence through governed, keyless Open-Meteo HTTP calls.

Maintain a provider-neutral local action queue from bounded provider observations and explicit human dispositions.

Operate a project, workspace, or account from an agent or manager dashboard: inspect state, triage risks, prepare governed actions, route to the right skill lane, require approvals for consequential acts, and verify receipts after execution.