Skip to main content

A governed development framework for AI-assisted engineering

Project description

vaultspec logo

vaultspec-core

Vaultspec is a spec-driven harness for coding agents (and us, the humans).

Continuous integration PyPI version Python 3.13+ Model Context Protocol uv License: MIT

Getting started · The pipeline · Framework manual · CLI reference · MCP

vaultspec pipeline demo - provisioning a project, scaffolding research, ADR, and plan, then checking and graphing the vault

Vaultspec guides agents through a Research → Decide (ADRs) → Plan → Code → Verify pipeline, not dissimilar to other spec-driven frameworks (Superpowers!) - with one difference: nothing is throwaway. All work leaves a papertrail in the project's .vault. Documents are bound together by feature tags and wiki-link references. Together, they represent the project's decision and execution history - a second brain your agents read before they write.

We hold ourselves to it, too: vaultspec-core is developed with vaultspec. Its own .vault currently holds 800+ CLI-scaffolded documents across 100+ features, and every terminal render on this page is real output against that live vault:

vaultspec-core status - live output from this repository's own vault

What is included?

vaultspec-core implements the natural language description of the workflow, and the machinery that enforces it:

  • Rules, skills, and agent personas for Claude, Codex, Gemini, and Antigravity, seeded from one .vaultspec source of truth and synced per provider.
  • A CLI that scaffolds, audits, and repairs every vault document - templates, tag taxonomy, wiki-link resolution, and plan structure are enforced, never hand-written.
  • Structured plans that scale with the work: four complexity tiers (L1-L4) with waves, phases, and steps under stable canonical identifiers.
  • An MCP server for Model Context Protocol clients.

See the framework manual for the full tour.

[!TIP] The framework favours semantic search via the core's optional sister project, vaultspec-rag.

Getting started

1. Install

For the quickest, dependency-free project bootstrap, run from a git project folder:

uvx vaultspec-core install

Use it as a tool or dependency:

# You can add it as a local tool
uv tool install vaultspec-core

# Or a project dependency
uv add vaultspec-core

2. Bootstrap

uv run --no-sync vaultspec-core install [--upgrade]

See the CLI reference for installation options.

[!NOTE] vaultspec-core install handles project integration separately: it manages a block in your .gitignore and .gitattributes, writes pre-commit hooks, and drops an .mcp.json for Model Context Protocol clients by default.

3. Sync

All development paper trails live in .vault as markdown files. Rules, agents, and skills are seeded from .vaultspec via:

uv run --no-sync vaultspec-core sync

[!TIP] Make sure to run

uv run --no-sync vaultspec-core install --upgrade

after a library update as the shipped agents, skills and rules might change between library versions.

The pipeline at a glance

The pipeline breaks down into these steps: [R] Research → [D] Decide (ADRs) → [P] Plan → [C] Code → [V] Verify. Each step ships with its skills, agents and CLI verbs.

To start using the framework describe the work you want done in natural language:

"Start a new vaultspec pipeline to research options for adding full-text search to the API."

The synced rules guide the agent through the pipeline stage by stage, writing documents into .vault/ as it goes: a research note, then a decision record, a plan, execution records, and a final review. You approve each checkpoint before the agent moves on.

Invoke a stage skill directly - for example /vaultspec-research - to enter the pipeline at a specific stage. See the framework manual for how each one works.

Skills

Skills are the slash-commands that drive each stage of the pipeline. Six map to the pipeline stages; two helpers - curate and documentation - cover everyday upkeep. The framework manual gives full guidance on each, plus two further skills for team coordination and project management.

Which skill, when

When you want to Skill
Explore a problem and weigh options /vaultspec-research
Ground the work in the existing codebase /vaultspec-code-research
Record the decision and its consequences /vaultspec-adr
Turn the decision into an implementation plan /vaultspec-write
Work through the plan, step by step /vaultspec-execute
Audit the finished work by severity /vaultspec-code-review
Repair vault links, frontmatter, and naming /vaultspec-curate
Draft user-facing documentation /vaultspec-documentation

Every feature leaves a paper trail

One feature tag binds a feature's whole lifecycle - research, decision, plan, execution records, and audit - into a linked graph the CLI can trace, validate, and visualize:

vaultspec-core vault graph - a feature's document graph

The vault, rendered in Obsidian

The vault is plain Markdown with wiki-links, so it opens directly in Obsidian: point a vault at .vault/ and the feature tags and document links render as a navigable graph network, while every document's frontmatter - tags, dates, and related: wiki-links - shows up as first-class properties.

A vaultspec vault opened in Obsidian - the document corpus as a graph network on the left, an accepted ADR with its tags, dates, and related wiki-links on the right

A vaultspec project's vault in Obsidian: the whole document corpus as a graph, and an accepted ADR open beside it with its tags and related records one click away.

A vault that audits itself

Structure only helps if it holds. vaultspec-core vault check runs a battery of validators over the corpus - frontmatter, tags, links, dangling references, leftover placeholders, plan schema, encoding - and every finding ships with its fix:

vaultspec-core vault check all - validators with fix hints

Documents are created and maintained through the vaultspec-core vault command group - never hand-written. The CLI enforces templates, tag taxonomy, and wiki-link resolution so your vault stays consistent.

# Scaffold a document from a template
vaultspec-core vault add research --feature search-api

# Find and inspect documents
vaultspec-core vault list --feature search-api

# Validate frontmatter, links, and cross-references (--fix to auto-repair)
vaultspec-core vault check all --fix

# Visualize a feature's dependency graph
vaultspec-core vault graph --feature search-api

Plans carry deeper structure - waves, phases, and steps. The framework manual covers that structure.

Ask your history questions

A vault is only as useful as its recall. The optional sister project vaultspec-rag indexes both the vault and the codebase for hybrid semantic search, so agents (and you) can ask why something was decided and get the decision record back:

vaultspec-rag search - semantic recall of a decision record

MCP server

We ship an MCP but the current implementation strongly favours direct CLI calls. See the MCP reference for setup and available tools.

Learn more

Guide What it covers
Framework manual The development workflow, skills, agents, and customization
CLI reference Every command, flag, and option for vaultspec-core
MCP reference The MCP server tools, setup, and configuration

The companion projects extend the framework: vaultspec-rag adds semantic search over your vault and codebase, vaultspec-dashboard provides a visual UI, and vaultspec-a2a handles agent orchestration.

Status, help, and license

vaultspec-core is actively developed. The version badge shows the current release. File bugs and questions on the issue tracker. Bug reports, feature ideas, and pull requests are welcome. vaultspec-core is released under the MIT License.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vaultspec_core-0.1.37.tar.gz (5.0 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

vaultspec_core-0.1.37-py3-none-any.whl (1.0 MB view details)

Uploaded Python 3

File details

Details for the file vaultspec_core-0.1.37.tar.gz.

File metadata

  • Download URL: vaultspec_core-0.1.37.tar.gz
  • Upload date:
  • Size: 5.0 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.11.28 {"installer":{"name":"uv","version":"0.11.28","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for vaultspec_core-0.1.37.tar.gz
Algorithm Hash digest
SHA256 6f6dbb8014e231ec3fcc4f36582a905f5245c1a48aa7c7b7f955cd3a059b8517
MD5 900d807ea29dab911e6543bb9f8a2122
BLAKE2b-256 d4b297fa823e1cae23561b816fa997a616a87fcd791d50879427c6d5e5bdc176

See more details on using hashes here.

File details

Details for the file vaultspec_core-0.1.37-py3-none-any.whl.

File metadata

  • Download URL: vaultspec_core-0.1.37-py3-none-any.whl
  • Upload date:
  • Size: 1.0 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.11.28 {"installer":{"name":"uv","version":"0.11.28","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for vaultspec_core-0.1.37-py3-none-any.whl
Algorithm Hash digest
SHA256 d435e1ad9748f5eaef50bee472235ed909658fb909f3cc7f94e16c2bd2ca9aa3
MD5 0603b5e2e86fec77f759b0322700bdd4
BLAKE2b-256 218bc1b700d41cde328537238278557c5dad7b04df1373204789d7c3ebb19e91

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page