Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Lev Sdlc

ASecurity

Thin skill documenting the `lev sdlc *` command surface, SDLC plugin profiles, and related work/review loop commands in Leviathan.

22 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agentsbashgitdocumentation

Works with

claude codecli

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add lev-os/agents --skill lev-sdlc --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Lev Sdlc?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Lev Sdlc
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/lev-os-lev-sdlc/badge)](https://www.skillsdirectory.com/skills/lev-os-lev-sdlc)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: lev-sdlc
description: Thin skill documenting the `lev sdlc *` command surface, SDLC plugin profiles, and related work/review loop commands in Leviathan.
---

# lev-sdlc — SDLC Poly Surface Reference

> Thin skill documenting all `lev sdlc *` commands and the SDLC plugin surface.
> Source: `plugins/core-sdlc/` in the Leviathan monorepo.

## Command Surface

### `lev sdlc exec`

Execute a chore/plan entity through the SDLC pipeline.

```bash
lev sdlc exec [entity] [--dry-run] [--json]
```

**Profile:** `sdlc.flowmind.exec`
**What it does:** Runs exec (opus-4-6) + validate (codex/gpt-5.4) phases on an entity.
**Source:** `plugins/core-sdlc/src/commands/sdlc.ts`

### `lev sdlc deepen`

Fan-out plan decomposition into parallel deep-research subagents.

```bash
lev sdlc deepen [entity] [--json]
```

**Profile:** `sdlc.flowmind.deepen`
**Source:** `plugins/core-sdlc/src/commands/sdlc.ts`

### `lev sdlc hygiene`

Periodic 3-axis scan: handoffs + chore-code alignment + spec update proposals.

```bash
lev sdlc hygiene [--json]
```

**Profile:** `sdlc.flowmind.hygiene`
**Source:** `plugins/core-sdlc/src/commands/sdlc.ts`

### `lev sdlc autodev`

Heartbeat-driven autonomous development loop.

```bash
lev sdlc autodev [--interval=5m] [--max-ticks=10] [--budget=50k] [--json]
```

Routes to `lev loop autodev`. See `/autodev-lev` skill for full documentation.
**Source:** `plugins/core-sdlc/src/commands/autodev.ts`

### `lev work`

SDLC work lifecycle router with stage-based dispatch.

```bash
lev work [query] [--stage=auto|find|gather|review|contract] [--dry-run] [--json] [--epic=ID]
```

**Stages:**
- `auto` — Classify intent and route automatically
- `find` — Discover entities and prior art
- `gather` — Collect context and evidence
- `review` — Review and validate entities
- `contract` — Generate/update BDD contracts

**Source:** `plugins/core-sdlc/src/commands/work.ts`

### `lev review`

Review queue for entities pending approval.

```bash
lev review [--limit=N] [--json]
lev review approve <id>
lev review reject <id>
lev review defer <id>
```

**Config:** `sdlc.gates.review_labels`, `sdlc.review.default_limit`
**Source:** `plugins/core-sdlc/src/commands/review.ts`

### `lev loop`

Entity queue management — discover, validate, promote, budget.

```bash
lev loop [--json]              # Show entity queue
lev loop autodev [flags]       # Start heartbeat loop
```

**Exports from `@lev-os/orchestration`:** `discoverPlans`, `loadLoopConfig`, entity types.
**Source:** `plugins/core-sdlc/src/commands/loop.ts`

### `lev instruct`

Append structured instructions (rules, learnings, corrections) to a project.

```bash
lev instruct "rule text" [--source=human|agent]
```

Append-only to `.lev/instructions.md`. Never rewrites.
**Source:** `plugins/core-sdlc/src/commands/instruct.ts`

## Entity Lifecycle

The SDLC plugin manages entities through this state machine:

```
draft → ready → in_progress → needs_validation → validated → done
                    │              │
                    │              └─ (fail) → ready (with feedback)
                    └─ (blocked) → blocked
```

Entity types: `plan-impl`, `plan-chore`, `plan-bugfix`, `plan-research`, `spec`, `chore`

## Exec Profiles

| Profile | Purpose | Model |
|---------|---------|-------|
| `sdlc.flowmind.exec` | Execute + validate entity | opus-4-6 + codex |
| `sdlc.flowmind.deepen` | Deep plan decomposition | opus-4-6 |
| `sdlc.flowmind.hygiene` | Periodic health scan | sonnet-4-6 |

## Configuration

Lives in `plugins/core-sdlc/config.yaml` under the `sdlc` namespace:

```yaml
sdlc:
  paths:
    instructions: .lev/instructions.md
    evidence: .lev/evidence/
    specs: docs/specs/
  mayor_mode:
    enabled: false
  entity_definitions:
    plan: { ... }
```

Config cascade: system → project → module → env (later wins).

## Validation Gates

Spec validation includes `.lev/validation-gates.yaml` cross-reference. All SDLC checkpoints
(spec-lint, pre-execute, post-validate) check applicable enforced gates before proceeding.

## Capabilities

- `git_events` — Git hook event providers
- `bd_events` — Beads task tracking events
- `spec_linting` — Spec validation
- `instruction_capture` — Append-only instruction log
- `mayor_mode` — Notification suppression
- `exec_profiles` — SDLC-specific execution profiles

## Integration

- **Control plane hierarchy (D8):** `lev exec` is THE execution plane, `lev loop` is scheduling, `.flow.yaml` is policy
- **Skills are shims (D12):** `/work`, `/autodev-loop` are Claude Code skill shims — real functionality lives in `lev sdlc *` commands
- **Entity queue:** `lev loop --json` returns the priority-sorted entity queue

## Related Skills

- `/work` — FSM lifecycle router (Claude Code skill shim)
- `/autodev-loop` — Cron-based tick scheduler (Claude Code skill shim)
- `/autodev-lev` — Heartbeat-based tick scheduler via `lev loop autodev`
- `lev` — Master CLI reference

Attribution

lev-oslev-os
View sourceMore from lev-os →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →