Install
$ agentstack add skill-nevenincs-vaultspec-core-vaultspec-team ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Team coordination skill (vaultspec-team)
This skill defines how to supervise multiple specialized agent personas when work is too large for a single worker. Use it for massive refactors, multi-module auditing, or any scenario where parallel execution and multi-agent coordination provide an advantage. The work itself follows the plan conventions: a Wave / Phase / Step plan governs scope, and each Step is one prompt-run plus one commit.
Announce at start: "I'm using the vaultspec-team skill to coordinate a team of agent personas."
When to use
- The work spans multiple modules, repositories, or domains.
- Parallel execution would significantly reduce total effort.
- The work benefits from specialized roles (researcher, coder, reviewer) working in
coordination.
For focused, single-persona work, load the agent persona directly instead.
Mechanism
This skill is a coordination policy, not a shipped MCP API contract.
- The host environment selects the participating agent personas.
- The host environment assigns Step / Phase / Wave boundaries, context, and sequencing
per the plan document.
- The host environment monitors progress, handles permission prompts, and decides when
to re-route or stop work.
Mapping the team to the plan
The plan document is the team's work queue; the plan's structure decides the team's shape:
- Assign whole Phases (or Waves at L3/L4) to workers, never fragments of a Phase; the
plan's Parallelization section states which containers may run concurrently.
- Each worker executes its Steps under the
vaultspec-executediscipline: one Step is
one prompt-run plus one commit, closed via vaultspec-core vault plan step check, with one Step Record per Step.
- Workers must not mutate plan structure; structural changes route back to the
supervisor, who applies them via the vaultspec-core vault plan verbs.
- The supervisor enforces the mandatory review gate: a
vaultspec-code-reviewerpersona
audits completed work before the affected Steps are reported done.
Use this skill when you need a supervised team shape such as:
- researcher -> author -> editor
- researcher -> executor -> reviewer
- supervisor with multiple parallel specialists
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: nevenincs
- Source: nevenincs/vaultspec-core
- License: MIT
- Homepage: https://neve.md/vaultspec
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.