A workflow that connects Allium behavioral specifications with an agent development loop. Allium is a tool for describing observable rules in files without prescribing the implementation.

Use it to attach specs to epics, derive tests before TDD work, create baseline specs for refactors, and check for specification–code drift after CI passes.

It keeps a written description of expected behavior connected to an epic, its tests, and later checks for differences between the specification and the code. TDD means writing tests as part of the development process before or alongside implementation.

allium — Skill for Claude Code by vinnie357

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add vinnie357/claude-skills --skill allium

Clone the repo

git clone --depth 1 https://github.com/vinnie357/claude-skills

Made for: Claude Code.

Or install allium, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/vinnie357/claude-skills/allium/github.svg)](https://agentmods.dev/skills/vinnie357/claude-skills/allium)

Your own site

<a href="https://agentmods.dev/skills/vinnie357/claude-skills/allium"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/allium/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/vinnie357/claude-skills/allium"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/allium.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 855 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00046	$0.00855
Opus 5	$0.00023	$0.00428
Sonnet 5	$0.00009	$0.00171
Haiku 4.5	$0.00005	$0.00085

Measured 7d ago against content hash 1da4ae2291ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

allium scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/tools/allium/skills/allium/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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.

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/<epic-slug>.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

Read the full file on GitHub · 88 lines

Files

What ships with it

9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

7d ago First seen · 88 lines · 46 tokens per session scan A 1da4ae2291ec

Subscribe to this mod's changes

allium is a skill published in the GitHub repository vinnie357/claude-skills (25 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 855 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Planning TDD Testing

allium

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Allium

Prerequisites

Spec Location Convention

Integration Points by Tier

Spec Syntax (v3)

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

engram-testing-coverage

iterative-development

python

nw-fp-clojure

strict-tdd

mobiai-mobile-tdd