Skip to main content
skill CX Codex

vstack-s0-decompose — Claude Code skill: system mapping

vstack-s0-decompose is a Claude Code skill that maps system control, data flow, and boundaries, then builds evidence-backed historical anchors. It runs during analysis of a pinned source revision before verification.

MIT ★ 89 updated 2026-11-16

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add hao-ai-lab/vstack
/plugin install vstack@hao-ai-lab-vstack
Open on GitHub

What vstack-s0-decompose does

The skill separates mutable state and its writers from data and computation consumers, then maps handoffs across system boundaries. Each recorded fact is tied to a file path, line, and commit; unsupported conclusions stay marked as unverified. It also searches related components for historical candidates and records rejected matches and search coverage.

For calibration, the skill freezes the historical-fix denominator I_U, exclusion reasons, and SHA-256 before the coordinator draws calibration and blind sets. Critical assumptions about physical behavior and synchronization are tested on the real system with authorized resources. Source review is manual. The source KB checker is repository-specific and is not bundled.

What it helps with

  • map system control, data flow, and boundaries
  • identify every writer of mutable state
  • record historical bugs and fixes against source revisions
  • test assumptions about handoffs and synchronization
  • prepare calibration and blind sets

Example prompts for the agent

  • Map this pinned source revision into control, data, and boundary views.
  • Find every writer of ownership and in-flight state, then trace the producer-to-consumer handoff.
  • Build evidence-backed historical anchors and prepare the calibration and blind sets.

How to install vstack-s0-decompose

1Plugin marketplace

/plugin marketplace add hao-ai-lab/vstack
/plugin install vstack@hao-ai-lab-vstack

This installs the whole vstack plugin with all its skills

2Skills CLI (Vercel)

npx skills add hao-ai-lab/vstack --skill vstack-s0-decompose -a claude-code

3Manually: put the files in place

~/.claude/skills/vstack-s0-decompose/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/vstack-s0-decompose/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about vstack-s0-decompose

How do I install vstack-s0-decompose in Claude Code?

Add the marketplace with /plugin marketplace add hao-ai-lab/vstack, then install the skill with /plugin install vstack@hao-ai-lab-vstack.

What does vstack-s0-decompose do?

It maps state, data flows, and system boundaries, links findings to source evidence, and prepares historical anchors for verification.

What does vstack-s0-decompose need to run?

It needs a pinned source revision and existing anchors for deduplication. Critical physical assumptions are tested on the real system using authorized resources.

Source text

SKILL.md · MIT
---
name: vstack-s0-decompose
description: "Map a pinned system into control, data and boundary views and build evidence-backed historical anchors before verification."
---

# S0 — Reconstruct and separate the system

Read [Layer 0: shared operating rules](../../docs/layer-0.md), this stage and the assigned input bundle.

## Role and write scope

Assigned investigators own separate maps and candidate files; a verifier and coordinator check evidence. Target source is read-only.

## 1. Input

A fixed source revision and existing anchors for deduplication.

## 2. Procedure

1. Build a control map of mutable state, owners and **all** writers. Search all assignments before saying a field has one writer.
2. Map data and computation consumers and their unchecked preconditions. At each boundary, map the producer, consumer, execution context, overwrite time and synchronization. Classify every in-scope file.
3. Record facts with `path:line@commit` and short source excerpts. Keep unsupported inferences explicitly unverified.
4. Search the target and related systems by component. Record every examined candidate, rejection reason and search coverage. Confirm buggy triggers and fixed behavior on the stated revisions; a closed issue is not evidence that a fix merged.
5. Test critical physical and synchronization assumptions on the real system before treating them as axioms, using authorized resources.
6. For the full [adequacy readout](../../docs/model-adequacy.md#denominator-i_u), freeze each slice's historical-fix denominator `I_U` with its exclusion reason codes and SHA-256. The coordinator then draws the calibration set by a published seed and seals the blind set `H`, removing every trace of `H` from the maps handed downstream.

## 3. Exit checks

- Require zero evidence schema errors and a positive checked-item count. The source KB checker is repository-specific and is not bundled.
- Have the verifier and coordinator review original source and bind review marks to its content. This review is manual.
- Classify every file, label unsupported claims and deduplicate upstream identifiers. These checks have no generic automation.
- Keep disproved anchors. Rename an unsupported historical `Bug*` switch to `Mut*`; do not count it as historical calibration.

## 4. Rollback

An invalid physical assumption reopens the boundary map. A downstream report of a missing state writer returns here with the pinned source location. Use [a rollback ticket](../../templates/rollback.md).

## Concrete Examples

For a PD KV slot, map every writer of ownership and in-flight state, then record the producer-to-consumer handoff. An unsupported historical-bug claim stays a mutation hypothesis until pinned code supports it.

© Hao AI Lab · MIT · hao-ai-lab/vstack

Similar skills

All skills for Code review and refactoring →

From the same set13

The whole set →
vstack-main vstack-main — a subagent for Claude Code coordinates Verification Stack stages and checks their evidence independently. It accepts a stage only after reviewing its artifacts and results. CX Codex ★ 89repo stars vstack The vstack Claude Code plugin gives coding agents a formal workflow for checking state-machine models without weakening their safety properties. Run it on a module and a stated safety requirement. ★ 89repo stars vstack-s1-select The vstack-s1-select Claude Code skill selects verification methods and assurance tiers for system properties. It splits obligations by property and weighs scale, code ownership, and failure impact. CX Codex +1 ★ 89repo stars vstack-s6-hunt-fix The vstack-s6-hunt-fix Claude Code skill searches for bugs within a trace-validated model and checks proposed fixes. It classifies counterexamples and tests changes against real code. CX Codex +1 ★ 89repo stars vstack-s4-calibrate-tv The vstack-s4-calibrate-tv Claude Code skill calibrates behavior models and checks them against real traces. It runs stage S4 checks for bugs, fixes, repair components, and reachability witnesses. CX Codex +1 ★ 89repo stars vstack-mode The vstack-mode Claude Code skill runs staged verification for concurrent, distributed, and systems software. It takes a property from source investigation through proof and regression. CX Codex +1 ★ 89repo stars vstack-s2-spec The vstack-s2-spec Claude Code skill turns a design into testable specifications and pinned checks. It runs during specification work based on an approved S1 design and obligation matrix. CX Codex +1 ★ 89repo stars vstack-s5-redteam The vstack-s5-redteam Claude Code skill probes a model and its gates with independent attacks. It runs at stage S5 to expose weak checks and verify findings against real code. CX Codex +1 ★ 89repo stars

Project sponsors

Companies that keep this analytics open