Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Full

skill · oliver-kriska/claude-elixir-phoenixMIT licenceAudited 18 Oct 2026 · source 492f17636999

★ 567pushed 2 days ago
!CAUTIONGrade C · 79/100 · 1 finding · 492f176
567repo stars · whole oliver-kriska/claude-elixir-phoenix

Is it safe? With care — CAUTION, grade C (79/100). We read this skill's source at commit 492f17636999 and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 1 finding, 1 critical or high. What it does: Deliver a large, cross-domain Phoenix feature or complete end-to-end system through planning, implementation, verification, and review. Use when several coordinated workflows or contexts must ship together. NOT for an…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Full (oliver-kriska/claude-elixir-phoenix)”. Retrieved 18 Oct 2026. https://modelsatlas.com/skills/oliver-kriska/full

Trust audit

Audit 0.4.1 · source read 18 Oct 2026

Trust score79/100!CAUTION C
0 critical1 high0 medium0 low0 info

CAUTION means the audit found things worth knowing before you trust this skill. Grade C is shared by 100 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesFAIL1
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: instruction override, no behavioural pass.

Findings (1)

HIGHPrompt injectionprompt.hide_from_user · SKILL.md:95
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
Never tell the user to set an environment variable just to make `/phx:full`
Why
asks the agent to act without the user's knowledge
Fix
—

Audit 0.4.1 · source sha 492f17636999 · 18 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisheroliver-kriska GitHub userOwner of the repository this skill is read from
  • Source folderoliver-kriska/claude-elixir-phoenix/plugins/elixir-phoenix/skills/fullThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict492f17636999A new audit runs when the source changes
  • Repository statusNot archivedLast push 2 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Deliver a large, cross-domain Phoenix feature or complete end-to-end system through planning, implementation, verification, and review. Use when several coordinated workflows or contexts must ship together. NOT for an…

---
name: full
description: "Deliver a large, cross-domain Phoenix feature or complete end-to-end system through planning, implementation, verification, and review. Use when several coordinated workflows or contexts must ship together. NOT for an existing plan; use /phx:work."
effort: high
argument-hint: <feature description> [--codex]
---

# Full Phoenix Feature Development

Execute complete Elixir/Phoenix feature development autonomously: research patterns,
plan with specialist agents, implement with verification, Elixir code review.
Cycles back automatically if review finds issues.

## Usage

```
/phx:full Add user authentication with magic links
/phx:full Real-time notification system with Phoenix PubSub
/phx:full Background job processing for email campaigns --max-cycles 5
/phx:full Add magic-link auth --codex
```

**Wrong input guard**: if the argument is a path to an existing plan file
(`.claude/plans/*/plan.md`), do NOT re-plan it. Say so and run `/phx:work {path}`
instead — the plan phase already happened.

## Flags

- **`--codex`** — Codex CLI joins the review panel on **every** review
  cycle, matching `/phx:review --codex`.
- **Requires** the `codex` CLI. A missing CLI degrades to a SKIPPED note —
  the cycle never fails.
- **Consensus** findings (flagged by a Claude agent **and** codex) are
  marked HIGH CONFIDENCE.

## Workflow Overview

```
┌──────────────────────────────────────────────────────────────────┐
│                       /phx:full {feature}                        │
├──────────────────────────────────────────────────────────────────┤
│                                                                  │
│  ┌────────┐  ┌────────┐  ┌────────┐  ┌────────┐  ┌────────┐  ┌────────┐  │
│  │Discover│→ │  Plan  │→ │  Work  │→ │ Verify │→ │ Review │→ │Compound│→Done│
│  │ Assess │  │[Pn-Tm] │  │Execute │  │  Full  │  │4 Agents│  │Capture │     │
│  │ Decide │  │ Phases │  │ Tasks  │  │  Loop  │  │Parallel│  │ Solve  │     │
│  └───┬────┘  └────────┘  └────────┘  └───┬────┘  └────────┘  └────────┘     │
│       │                            ↑      │    ↑              │         │
│       ├── "just do it" ────────────┤      │    │              │         │
│       ├── "plan it" ──┐            │      ↓    │              │         │
│       │               ↓            │ ┌────────┐│              │         │
│       │     ┌──────────────┐       │ │Fix     ││ ┌─────────┐ │         │
│       │     │   PLANNING   │       │ │Issues  │└─│ Fix     │←┘         │
│       │     └──────────────┘       │ └───┬────┘  │ Review  │           │
│       │                            │     ↓       │ Findings│           │
│       │                       ┌────┴─────────┐   └────┬────┘           │
│       │                       │   VERIFYING   │←──────┘                │
│       └── "research it" ─────┘  (re-verify)                            │
│            (comprehensive plan)                                         │
│                                                                  │
│  On Completion:                                                  │
│  Auto-compound: Capture solved problems → .claude/solutions/     │
│  Auto-suggest: /phx:document → /phx:learn-from-fix                       │
│                                                                  │
└──────────────────────────────────────────────────────────────────┘
```

## State Machine

```
STATES: INITIALIZING → DISCOVERING → PLANNING → WORKING →
        VERIFYING → REVIEWING → COMPLETED → COMPOUNDING | BLOCKED
```

### Claude Code nesting compatibility

Before delegating this cycle, determine the effective maximum nesting depth:

1. If `CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH` is a positive integer, use it.
2. Otherwise, inspect `claude --version`: the default is 1 in Claude Code
   2.1.217–2.1.218 and 3 in 2.1.219+.
3. If the version cannot be determined, conservatively use 1.

- **Depth 3+** — the full nested topology is available; delegate to
  `phx:workflow-orchestrator` as usual.
- **Depth 1–2** — execute the same state machine in this main
  session. Read `${CLAUDE_PLUGIN_ROOT}/agents/workflow-orchestrator.md` for the
  phase contract, but spawn leaf research/review specialists directly. Do not
  spawn `workflow-orchestrator`, `planning-orchestrator`, or
  `parallel-reviewer`, because those agents need to delegate again. Context
  supervision may still be spawned directly after its input files exist.

The fallback is a topology change only: preserve the same user decisions,
artifacts, verification gates, retry/cycle limits, and review-to-fix loop.
Never tell the user to set an environment variable just to make `/phx:full`
work.

Save state in `.claude/plans/{slug}/progress.md`. If `TaskCreate` is in
your tool list (Sonnet 5+ and Opus 4.8+ omit it unless
`CLAUDE_CODE_ENABLE_TODO_TOOLS=1`; never ToolSearch for it), also create one
task per phase at start, mark `in_progress` on entry and `completed` on exit:

```
TaskCreate({subject: "Discover & assess complexity", activeForm: "Discovering..."})
TaskCreate({subject: "Plan feature", activeForm: "Planning..."})
TaskCreate({subject: "Implement tasks", activeForm: "Working..."})
TaskCreate({subject: "Verify implementation", activeForm: "Verifying..."})
TaskCreate({subject: "Review with specialists", activeForm: "Reviewing..."})
TaskCreate({subject: "Capture solutions", activeForm: "Compounding..."})
```

Set up `blockedBy` dependencies between phases (sequential).

Run COMPOUNDING phase on COMPLETED to capture solved problems in `.claude/solutions/`.
Suggest `/phx:document` for docs and `/phx:learn-from-fix` for quick pattern capture.

## Cycle Limits

| Setting | Default | Description |
|---------|---------|-------------|
| `--max-cycles` | 10 | Max plan→review cycles |
| `--max-retries` | 3 | Max retries per task |
| `--max-blockers` | 5 | Max blockers before stopping |

Stop with INCOMPLETE status when limits exceeded. List remaining work and recommended action.

## Integration

```te

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 492f176

Download folder ↗
git clone https://github.com/oliver-kriska/claude-elixir-phoenix
git -C claude-elixir-phoenix checkout 492f17636999

The author documents no install command, so this uses the repository directly. Our verdict covers commit 492f17636999 only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
CodexMentioned in its text, not testedSkills for Codex · About Codex
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. !CAUTION C 79 / 100

    first audit · source 492f17636999

README badge

For maintainers · shows the latest audit

ModelsAtlas: CAUTION CMODELSATLASCAUTION · C
[![ModelsAtlas: CAUTION C](https://modelsatlas.com/skills/oliver-kriska/full/badge.svg)](https://modelsatlas.com/skills/oliver-kriska/full/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Assigns Audit✓SAFE

oliver-kriska/claude-elixir-phoenix

Inspect LiveView socket assigns for memory bloat — missing temporary_assigns, unused assigns, unbounded lists needing streams, memory estimates. Use when LiveView memory grows or you need to add temporary_assigns.

★ 567Grade B
Audit✓SAFE

oliver-kriska/claude-elixir-phoenix

Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.

★ 567Grade B
Boundaries✓SAFE

oliver-kriska/claude-elixir-phoenix

Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.

★ 567Grade B
Brainstorm✓SAFE

oliver-kriska/claude-elixir-phoenix

Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.

★ 567Grade B
Brief✓SAFE

oliver-kriska/claude-elixir-phoenix

Interactive briefing of a plan file — explains reasoning, schema decisions, component choices. Use when developers need to understand a plan before approving.

★ 567Grade B
Call Tracing✓SAFE

oliver-kriska/claude-elixir-phoenix

Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with parallel research agents, execute with automatic verification, review with…

★ 567Grade B

Add this badge to your README

[![ModelsAtlas: CAUTION C](https://modelsatlas.com/skills/oliver-kriska/full/badge.svg)](https://modelsatlas.com/skills/oliver-kriska/full/)

Questions about Full

What does the Full skill do?
Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with parallel research agents, execute with automatic verification, review with 4-agent parallel audits, and capture learnings as reusable knowledge.
Is Full safe to install?
With care. The audit graded it C (79/100) and found 1 thing worth knowing before you trust this skill, listed below with the exact line each was found on.
What can Full access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
What do I need installed to use Full?
Its own instructions reference codex. Dependencies are pinned to exact versions.
Which assistants does Full work with?
Its documentation mentions claude-code and codex. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (492f17636999), read on 2026-10-18. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.