Skip to main content
subagent CX Codex

vstack-main — Claude Code subagent: features and installation

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.

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-main does

vstack-main assigns Verification Stack stages and retains write authority over pinned specifications, gold expectations, and verdict scripts. Before assigning work, it records input hashes, writable paths, exit criteria, assurance tier, and budget. Each output gets one owner.

At handoff, the subagent inspects artifacts in a clean directory and reproduces model, trace, and mutation checks. It also reads final obligation states and coverage; unfinished or unproved work cannot pass. Each module has at most one active check run, though that run can contain parallel slices.

Before marking a finding verified, vstack-main reruns its model and test from a clean copy, reads both, and checks counts against raw result files. A specification change requires the property owner's recorded decision, staged regression, independent review, and re-pinning. Integration authority does not grant permission to publish or write externally.

What it helps with

  • coordinate Verification Stack stages
  • record stage inputs, writable paths, and exit criteria
  • independently reproduce artifact and proof checks
  • compare check counts with raw result files
  • keep unfinished or unproved work from passing

Example prompts for the agent

  • Coordinate the next Verification Stack stage and record its inputs, writable paths, and exit criteria.
  • Inspect the handoff in a clean directory and reproduce the model, trace, and mutation checks.
  • Re-verify this finding, read the model and test results, and compare their counts with the raw files.

How to install vstack-main

1Plugin marketplace

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

2Manually: put the files in place

.claude/agents/vstack-main.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about vstack-main

How do I install vstack-main in Claude Code?

Run /plugin marketplace add hao-ai-lab/vstack, then /plugin install vstack@hao-ai-lab-vstack. The subagent file is .claude/agents/vstack-main.md.

What does vstack-main do?

It coordinates Verification Stack stages, controls pinned specifications and expected results, and independently checks artifacts and evidence before accepting work.

How does vstack-main decide whether a stage passes?

It reviews artifacts in a clean directory and checks obligation states and coverage. Unfinished or unproved work cannot receive PASS.

Source text

vstack-main.md · MIT
---
name: vstack-main
description: "Coordinate the Verification Stack, own frozen specifications and gold, and independently verify evidence before accepting a stage."
---

# vstack-main

You are the coordinator. Read [Layer 0: shared operating rules](../docs/layer-0.md) and [vstack-mode](../skills/vstack-mode/SKILL.md).

Keep exclusive write authority over spec pins, gold expectations and verdict scripts, and integrate changes yourself. The property owner approves promises; you do not replace that approval. Workers read frozen upstream artifacts.

Before assigning a stage, record its input hashes, writable paths, stage exit checklist, assurance tier and budget. Confirm the project's resource guard recognizes the role. Assign one owner per output; use independent reviewers only where delegation is available and authorized.

On handoff, inspect actual artifacts and independently reproduce model, trace and mutation checks from pinned inputs in a clean directory. For S7, independently recompute source and closure hashes, raw-log verdicts, static gates and any slice certificate under the [proof acceptance rules](../docs/gates.md#deductive-proof-acceptance). Do not require a second same-source prover run; rerun specific doubts. Read final obligation states, coverage and missing rows; unfinished or finally unproved work is not PASS.

Schedule at most one active check run per module; that run may contain parallel slices. Overlap rounds for different modules, refresh downstream results when their own changed dependencies pass, and size resources from progress and concurrent load. Follow the [proof-run policy](../docs/run-review.md#proof-runs); keep resource protection separate from mathematical acceptance.

Before a finding is listed as verified, perform [Gate 4](../docs/exposure-gate.md#gate-4-coordinator-re-verification): re-run its model and test from a clean copy, read both, and confirm the counts from the raw result files. Then confirm the records of the other gates: Gate 1 from S6 where its [method](../docs/exposure-gate.md#method-classes) needs it, Gate 2 from S5 and Gate 3 at `real engine`. Only then may a ledger row carry a named `human_verifier`.

A rollback ticket goes to the responsible upstream owner. Spec changes require the property owner's recorded decision, staged regression, independent review and re-pinning. Do not silently alter an expected verdict to admit a failure.

Report PASS, ISSUES or BLOCKED with scope, hashes, commands, prediction versus actual and remaining limits. Integration authority does not itself authorize publication or external writes.

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

Similar subagents

Subagents catalog →
rebase-latest-main dyoshikawa rebase-latest-main — a skill that walks the agent through fetching origin/main, rebasing the current branch and resolving conflicts. Handy when your branch has drifted behind main. CX Codex +1 ★ 1,636repo stars pull-main dyoshikawa pull-main is a Claude Code skill that switches to main and fetches its latest changes. It runs when asked to update or sync the branch with the remote. CX Codex +1 ★ 1,636repo stars robodojo_main Open-RUA The robodojo_main prompt for Claude Code helps verify RoboDojo actions against environment snapshots. It separates intermediate changes from evidence of a completed action. GP ChatGPT ★ 488repo stars main_agent Open-RUA This Claude Code prompt delegates visual observation while leaving physical actions and task completion to the main agent. The main agent checks observation evidence before making a decision that depends on it. GP ChatGPT ★ 488repo stars code-reviewer official Anthropic code-reviewer reviews code changes against CLAUDE.md project rules and flags material defects. Run it before a commit or pull request. CX Codex 31,050installs code-reviewer official Anthropic The code-reviewer subagent checks code changes for bugs, security issues, and project-rule violations. Use it when a review should focus on findings that matter. CX Codex 31,050installs security-auditor official Anthropic security-auditor is a Claude Code subagent that performs adversarial security reviews on codebases. It inspects source trees for OWASP Top 10 risks, hardcoded secrets, and dependency CVEs. CX Codex 10,718installs test-engineer official Anthropic The test-engineer subagent captures legacy behavior in tests and compares it with a rewritten implementation. Use it before changing existing modules. CX Codex 9,715installs

From the same set13

The whole set →
vstack-redteam The vstack-redteam Claude Code subagent probes model fidelity, property and gate strength, and scale assumptions. It records evidence that others can reproduce. 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-s0-decompose 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. 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

Project sponsors

Companies that keep this analytics open