Esta página está disponible solo en inglés; el resumen en español, si existe, está al final.
v1.14.0 support matrix
Purpose
Declare what DIXI Spec Kit v1.14.0 supports, with what evidence, and which controls are automatic or only instructions. Nothing outside this table is announced as supported.
Systems and Python
| Platform | Status | Evidence |
|---|---|---|
| macOS + Python 3.15 | Supported | Local make verify, clean install from wheel and sdist (B3). |
| macOS / Linux + Python 3.11 and 3.13 | Supported when CI passes | verify job on ubuntu-latest and macos-latest (ADR-103). |
| Windows (WSL 2, Linux filesystem) | Supported when CI passes | Ubuntu 24.04 in WSL 2 on windows-latest, project under ~ on ext4: make verify, init --agent claude --controls, check, upgrade --dry-run and blocking hooks, run by the wsl.yml CI job (first run, contract). Projects under /mnt/c (or any Windows drive mounted in WSL) are not supported: Windows processes can create junctions there and its translation layer does not have ext4 link semantics. |
| Windows (native) | Not supported | Requires POSIX operations (O_NOFOLLOW, directory descriptors); dixi exits with code 4 and writes nothing, verified on windows-latest by the windows-refusal CI job. Use WSL 2 (ADR-107). |
Integrations
| Integration | Status | What it installs |
|---|---|---|
--agent none | Supported | Documentary base, AGENTS.md and guide. Use it with any editor or agent, without installed commands. |
--agent claude | Supported (Claude Code 2.1.319) | All of the above plus CLAUDE.md and thirty-three /dixi.* commands in .claude/commands/ (fewer in projects created with earlier versions; see dixi upgrade --dry-run). |
--agent codex | Supported (Codex CLI 0.167.0; manual run) | Baseline plus thirty-three skills in .agents/skills/dixi-<operation>/SKILL.md, each with agents/openai.yaml disabling implicit invocation. Invoke them as $dixi-<operation>. Codex reads AGENTS.md itself. |
--agent skills | Supported in OpenCode 1.19.5 (full run with dixi 1.12.0: discovery, explicit invocation as @dixi-<operation>, no implicit start observed); format compatible, not verified, in the other agents (contract) | Baseline plus thirty-three Agent Skills in .agents/skills/dixi-<operation>/SKILL.md with disable-model-invocation: true, read by Cursor, Gemini CLI and OpenCode according to their documentation (read on 2026-11-14), and by Goose and Amp according to search results; VS Code/Copilot reads .github/skills/ instead. No hooks: --controls is not available. An agent moves to Supported only with a recorded run. |
| Others | Not included | Having AGENTS.md does not amount to support. |
Claude Code adapter controls
| Control | Mechanism | Default | With --controls |
|---|---|---|---|
| Do not overwrite on install | dixi init | Automatic | Automatic |
| Structure, links and traceability | dixi check / make verify | Automatic | Automatic |
| Frozen tests (committed tests are not edited) | Instruction + PR review; hook protect_tests | Instruction | Enforced by hook |
| Do not sign, attest, approve or merge | Instruction + branch protection; hook guard_attestation | Instruction | Enforced by hook |
| Do not read secrets | Instruction; dixi rejects sensitive paths; hook guard_secrets | Partial | Enforced by hook |
No destructive commands in MODE=prod | Instruction; hook mode_gate | Instruction | Enforced by hook |
No "done" with make verify in red | Instruction; hook verify_on_stop | Instruction | Enforced by hook (once, then the person decides) |
| Validate structural decisions | Instruction (the command stops) | Instruction | Instruction |
| Tool permissions | Your Claude Code configuration; the kit does not change it | — | — |
Hooks are a second layer, not the last one: an agent can reach a file through a path a hook does not inspect. Human review and branch protection remain the effective protection.
Codex adapter controls
| Control | Mechanism | Automatic? |
|---|---|---|
| No overwrite on install | dixi init | Yes |
| Structure, links and traceability | dixi check / make verify | Yes |
| No implicit start of a DIXI skill | allow_implicit_invocation: false per skill | Yes (Codex setting) |
Frozen tests; no sign, attest, approve or merge; no secrets; MODE=prod safety; no "done" in red | Instruction in every skill; with --controls, the same hooks through .codex/hooks.json (Bash, apply_patch, Stop, SubagentStop) | Instruction; enforced by hook with --controls once you trust the project and approve the hooks with /hooks |
| Validate structural decisions | Instruction in every skill + human review | No |
| Sandbox and approvals | Your Codex configuration; the kit does not change it | — |
Capabilities
Included: init with the minimal, site, app and platform profiles and --regulated, doctor, check, workflow list/show/prepare, upgrade --dry-run, placeholders, pr-size, opt-in --controls, Claude Code subagents, the thirty-three operations constitution, checklist, converge, onboard, bugfix, issues, discover, specify, clarify, plan, tasks, build, verify, review, analyze, status, domain, architecture, contract, threat-model, handoff, change, data, quality, ai, release, promote, operate, finops, compliance, duediligence, interview, risk-review, and es/en documents.
Not included yet: extension and preset catalogs, and a second example language.
Related
Resumen en español
Soportado: macOS y Linux con Python ≥ 3.11 (evidencia local en macOS/3.15; CI en Ubuntu y macOS con 3.11 y 3.13). Windows: soportado a través de WSL 2 con el proyecto en el filesystem de Linux (bajo ~; /mnt/c no está soportado), verificado en CI; Windows nativo sale con código 4. Integraciones: --agent none, --agent claude (Claude Code 2.1.319), --agent codex (Codex CLI 0.167.0, treinta y tres skills con invocación implícita desactivada; ejecución manual registrada) y --agent skills (treinta y tres Agent Skills en .agents/skills/; soportado en OpenCode 1.19.5 con ejecución completa registrada (descubrimiento, invocación explícita como @dixi-<operación>, sin arranque implícito observado); formato compatible, no verificado, en los demás agentes; sin hooks). El adaptador de Claude Code instala treinta y tres comandos, cuatro subagentes y CLAUDE.md, sin permisos ni servidores MCP. Por defecto, las reglas de pruebas congeladas, no firmar/aprobar/integrar, no leer secretos y validar decisiones estructurales son instrucciones; con --controls se instalan hooks (Claude Code y Codex) que hacen cumplir todas salvo la validación de decisiones. Los hooks son una segunda capa, no la última. Aún no incluidos: catálogos de extensiones y presets, y Windows nativo.