AgentStack
SKILL verified MIT Self-run

Allium

skill-vinnie357-claude-skills-allium · by vinnie357

Allium behavioral specs integrated with /core:agent-loop. Use when attaching a formal spec to an epic, propagating tests from a spec before TDD, or weed-checking spec/code divergence after CI passes.

No reviews yet
0 installs
3 views
0.0% view→install

Install

$ agentstack add skill-vinnie357-claude-skills-allium

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README — it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-vinnie357-claude-skills-allium)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.

Preview Execution monitoring

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 →
Are you the author of Allium? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Allium

Opinionated integration between juxt/allium and the /core:agent-loop workflow. Allium captures observable behavior in .allium files using entity, rule, and config blocks — implementation-agnostic, co-located with code.

When to Use

  • Epic author is attaching a formal behavioral spec to a new epic
  • Worker needs to seed failing TDD tests from a spec before implementing
  • Validator has passed CI and needs to confirm the code matches the spec semantically
  • Refactor epic requires a behavioral baseline before decomposition

Prerequisites

Upstream Allium Claude plugin must be installed separately:

/plugin install allium@juxt

The CLI (allium-tools binary) installs via mise — see references/installation.md.

Spec Location Convention

Recommended convention for projects adopting this skill: specs live at docs/specs/.allium with shared specs in docs/specs/shared/. A project-root allium.config.json declares specPaths: ["docs/specs"] so the CLI and LSP resolve them. Copy templates/allium.config.json into the project root to bootstrap this layout.

Integration Points by Tier

See references/agent-loop-integration.md for the complete 6-tier breakdown. Summary:

| Tier | Allium action | |---|---| | Epic Author | Run /allium:elicit or copy a template from templates/; set spec: field in epic markdown | | Team Leader | If refactor label and no spec: run /allium:distill for baseline | | Worker | If spec attached: run /allium:propagate to seed failing tests BEFORE implementing | | Validator | After CI passes: run /allium:weed; divergences route to fix-agent same as CI failures |

Spec Syntax (v3)

entity Order {
    status: pending | confirmed | shipped | delivered | cancelled
    tracking_number: String when status = shipped | delivered

    transitions status {
        pending -> confirmed
        confirmed -> shipped
        terminal: delivered, cancelled
    }

    invariant NonNegativeTotal { this.total >= 0 }
}

rule ShipOrder {
    when: ShipOrder(order, tracking)
    requires: order.status = confirmed
    ensures:
        order.status = shipped
        order.tracking_number = tracking
}

Key constructs:

  • entity — domain object with typed fields, conditional attributes (when), state transitions, and invariants
  • rule — behavioral rule with when (trigger), requires (preconditions), ensures (postconditions)
  • config — project-level settings (thresholds, retry counts, timeout values)
  • use — import another spec: use "./shared/oauth.allium" as oauth

Templates

Copy-pasteable specs in templates/:

  • oauth-pkce-flow.allium — OAuth2 PKCE flow matching the agent-loop epic-authoring example
  • circuit-breaker.allium — infrastructure contract with entity + config + rule
  • runex-workflow.allium — spec for a Runex workflow step
  • epic-with-spec.md — VantageEx epic showing the spec: field in use

See references/epic-spec-template.md for a guided walkthrough.

Anti-Fabrication

All claims about spec content must derive from reading actual .allium files with Read tool. Never assert that a spec covers a behavior without verifying the ensures or invariant blocks. See /core:anti-fabrication.

References

  • references/installation.md — mise backend details and upstream plugin install
  • references/agent-loop-integration.md — 6-tier integration procedure
  • references/epic-spec-template.md — template walkthrough
  • references/distilling-legacy-code.md/allium:distill procedure for existing modules

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.