transitrix
v0.1.0by transitrix · author: Transitrix
Scaffold a Transitrix enterprise-architecture-as-text repository and author your first notation file with inline canonical validation. Drops the canonical zoned canon/ + field/ + codex/ layout with an assistant-neutral AGENTS.md guide and a pinned transitrix.yaml manifest, then walks the user through one of the 12 diagram views (BPMN, DGCA / DGA, Goals, Capability map, Process landscape map, Process Blueprint, Action schedule, Nested blocks, Applications, Integration map, Products, Action Card) + PlantUML rendering, one of the 6 report views (Scenarios, Actions tree, Compliance Impact, Coverage Metric, Rules in Force, Glossary), or a document view (MRD, SRS, SDD) or a codex artefact.
What transitrix does, in the publisher's words
Transitrix is a text-native methodology for enterprise architecture: every artefact lives in a versioned YAML file, reviewed as a diff, and governed by a published spec. This plugin brings the methodology's operational surface into Claude Code, scaffolding adopter repositories, turning organisational documents into structured canon candidates, running a read-only repo health check, and producing reproducible compliance reports.
Install command (once the plugin is published):
Self-hosted install (available now: the transitrix/methodology repository acts as a marketplace):
- Claude Code: the plugin runs inside a Claude Code session.
- An adopter repository: a repository following the Transitrix zoned layout (canon/ + field/ + codex/). Create one with /transitrix:onboard, or clone the worked example at github.com/transitrix/acme-corp.
- Methodology version pin: the repository must declare its methodology version in transitrix.yaml. Skills check the declared version against their min_version field and warn if the repo is on an older release.
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 10
- MCP servers
- 0
- Stars
- 17
- License
- MIT
- Repo created
- 2026-05-03
- Last pushed
- 2026-10-21
- Publisher type
- User
- Version
- 0.1.0
Links
Skills · 10
- adr
- Help a user formulate an architecture decision and land it as a valid, gated Architecture Decision Record in the repo's per-repo decision log, the input door to the agent-authored decision flow method/07-decisions.md specifies but ships no workflow for. Runs a Context → Decision → Consequences int…
- feedback
- Author an upstream methodology-directed finding as a gated, anonymised entry in the repo's own operations/feedback.md register: the input door to the upstream feedback channel method/06-team-operations.md §3.2 specifies but ships no workflow for. Routes non-methodology observations away first, run…
- health-profile
- Measure how effectively a Transitrix adoption is working in practice. Computes five instrumental indicators (validity, coverage, freshness, assertion-queue age/drain, connectedness) over a repository's model files. Each indicator is sourced from two independent records; the measure cannot be faked…
- ingest
- Turn raw organisational material (interviews, policies, org charts, spreadsheets, notes) into Transitrix field artefacts and typed canon candidates at scale, with source-quality scoring and a human review queue. Operates the field→canon derivation pipeline: convert a document, emit a field artefac…
- knowledge-store
- Ingest raw source material into the OKF single-repo MVP knowledge store, assess, archive, route to the OKF track (extract drafts → verify → human review → promote to knowledge/) and/or the Canon track (extract Transitrix primitives → PR to canon/), and log every decision.
- onboard
- Scaffold a new Transitrix architecture-as-text repository (zoned canon/ + field/ + codex/ layout with assistant-neutral AGENTS.md + transitrix.yaml manifest) and drive a first modelling session, enterprise architecture (BPMN, DGCA / Goals, capability map, process blueprint, action schedule, action…
- reg-intel
- Collect regulatory-source changes in practice: the operational counterpart to the methodology's codex / SEGMENT / AMENDMENT notation work. Reads the centralised watch-list at `operations/config/scan-sources.yaml`, runs a cheap change-signal gate before any expensive extraction, then on signal-move…
- repo-check
- Read-only health check (\"doctor\") for a Transitrix adopter repository. Emits a short, DATA-FREE report: methodology version, resolved coverage profile, per-zone and per-TYPE counts, an adoption-level indicator, integrity red flags (invalid IDs, misplaced canon elements, unresolved profile), and…
- report
- Produce a compliance report (obligation × subject impact matrix, or per-regime coverage metric) from a Transitrix repository, by conversation. Resolves the report's parameters, from the request, from the view spec's defaults, or from a named saved view-config, materialises a versioned view-config…
- status
- On-demand view of what is waiting behind every human gate in a Transitrix adopter repository, ADR proposed/accepted/superseded (author:agent broken out), Work Item phase, canon element status, REQUIREMENT/CONSTRAINT review-overdue, and ingest batches awaiting review. One table, phases and counts o…
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
Category
Documentation & Writing. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
enterprise-architecture · architecture-as-text · methodology · scaffolding · onboarding · transitrix · bpmn · dgca · capability-map · process-blueprint
Related by publisher and keywords
Google Cloud guidance for coding agents: first-project onboarding, authentication and credential selection, and safety-critical validation for gcloud CLI commands. Includes the Google Developer Knowledge MCP server for grounded, up-to-date Google Cloud documentation.
Interactive architecture diagrams and explanations of public GitHub repositories.
Scaffold, develop, evaluate, and deploy AI agents with Google ADK. Bundles skills for the agent development lifecycle.
Scaffold and safely evolve verified fullstack projects with Better Fullstack skills and its official MCP server.
Shared delivery practices for human: AI teams: planning, tickets, model selection, testing, independent review and release readiness. Install for a project or user; adopt project-owned authority and checks.
Guided setup for Claude Cowork: confirms your workspace folder, connects your tools, builds your context files (about you, your voice, how you work), and creates working folders that match your job.
[](https://agentpluginsdirectory.com/plugins/transitrix)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.