🌐 English | 한국어 | 日本語 | 中文 | Español

sovereign-skills v6.4

18 skills for the full Claude Code project lifecycle — from setup to daily workflow to code review to session management to governance. Each skill is useful standalone; the full sequence covers everything.

What changed in v6.4: New: full-audit (exhaustive area audit — deterministic sweep + content review, persistent coverage map, anti-false-positive kill-test), integration-intake (5-item screening gate for adopting external skills/agents/rules/plugins, with a provenance/injection check), clean-room (carves safety-adjacent requests into a safe scope executed by a genuinely isolated fresh-context subagent, adapted from LilMGenius/paperthin's "autobahn" skill under MIT with a filesystem-isolation and ledger-timing upgrade). Updated: goal-lock (a constraint re-echo check at long-task checkpoints, so CONSTRAINTS/SCOPE-Exclude don't quietly fall out of view during extended work), session-checkpoint (a new Attestation phase — an evidence-chain receipt log with a bundled handoff_attestation.py, so the next session's SessionStart hook can detect handoff tampering).

What changed in v6.3: New: skill-ops (snapshot/rollback + usage health + invocation tracking hub), next-action (reads handoff/git/lessons/STATE and proposes the top-3 next actions), project-overview (deterministic cross-project status map). code-autopsy → v7.1 (deeper sub-checks per question), pre-push → v3.5 (9 supply-chain IOC patterns), goal-lock/session-checkpoint/session-start/scope/stepback/freeze all strengthened. All 12 prior skills gained not_for and see_also frontmatter for better discoverability.

Quick Start

New project (15 min):

/project-init       →  CLAUDE.md + ROADMAP + .gitignore + .env.example
/setup              →  rules/ + hooks + memory/ + agent routing + team
then daily:
  /session-start      at the start of every session
  /scope              before each feature (define IN/OUT/exit criteria)
  /freeze             before implementation (declare editable zone)
  /goal-lock          lock the goal, enforce PLAN→DO→VERIFY loop
  /stepback           anytime — zoom out, check direction, 10 lines
  /next-action        anytime — reads current state, proposes top-3 next actions
  /code-autopsy       12Q code review with severity scoring + verdict
  /pre-push           before each push (secrets scan + agent review)
  /session-checkpoint at the end of every session

Existing project (5 min):

/project-check      →  Score across 4 dimensions + gap list by severity
/collab-audit       →  14-section AI collaboration diagnostic from your work patterns

Skills

Setup Phase

Daily Workflow

Perspective

Session Management

Code Review

Quality

Operations

Governance

Lifecycle Flow

┌─────────────────── Setup (once) ───────────────────┐
│  /project-init  →  /setup                           │
└────────────────────────────────────────────────────┘
         ↓
┌─────────────────── Daily Loop ─────────────────────┐
│  /session-start                                     │
│       ↓                                             │
│  /scope → /freeze → /goal-lock → work                │
│       → /stepback (anytime) → /code-autopsy           │
│       → /pre-push                                     │
│       ↓                                             │
│  /session-checkpoint                                │
└─────────────────────────────────────────────────────┘
         ↓
┌─────────────────── On Demand ──────────────────────┐
│  /stepback         (perspective reset — anytime)      │
│  /project-check    (health audit)                    │
│  /code-autopsy     (12Q code review — any LLM)       │
│  /collab-audit     (behavioral diagnostic)           │
└─────────────────────────────────────────────────────┘

Installation

Option A: Copy skills (simplest)

Each skill is a standalone directory with a SKILL.md file. Copy the ones you want:

# Install all skills
git clone https://github.com/AlexZio00/sovereign-skills.git
cd sovereign-skills
for d in */; do [ -f "$d/SKILL.md" ] && cp -r "$d" ~/.claude/skills/; done

# Or install one skill
cp -r goal-lock ~/.claude/skills/

Option B: Marketplace (sovereign-plugins)

This repo is a Claude Code marketplace. Register it once and browse/install skills:

# Add sovereign-plugins marketplace in Claude Code
# Settings → Plugins → Add Marketplace → https://github.com/AlexZio00/sovereign-skills.git

Each skill also includes standalone .claude-plugin/plugin.json metadata.

Skills are invoked by typing the trigger command (e.g., /goal-lock) in Claude Code. Claude reads the SKILL.md and follows the instructions.

Option C: Codex / Cursor (npx)

Each skill includes agents/openai.yaml for Codex compatibility:

# Install a skill for Codex
npx skills add AlexZio00/sovereign-skills --skill goal-lock --agent codex -g -y

# Install a skill for Cursor
npx skills add AlexZio00/sovereign-skills --skill goal-lock --agent cursor -g -y

# Install a skill for Claude Code (alternative to Option A)
npx skills add AlexZio00/sovereign-skills --skill goal-lock --agent claude-code -g -y

The SKILL.md content is universal — it works with any LLM that reads markdown instructions.

Requirements

• Claude Code: CLI, desktop app, or web app (claude.ai/code)
• Codex: OpenAI Codex with npx skills support
• Cursor: Cursor IDE with skill plugin support
• Skills directory: ~/.claude/skills/ (Claude Code) or agent-specific path
• pre-push requires Perl (for scan_secrets.pl — included)

Agentic Design Patterns Coverage

These 12 of the 18 skills (the original lifecycle set — the v6.3 operations additions and v6.4 governance additions aren't mapped here yet) implement 17 of the 25 known agentic design patterns (Gulli 2026, Sairahul 2026):

Design Principles

1. Interview over template — Skills ask questions and generate filled content, not empty skeletons
2. Verification over trust — DONE EVIDENCE must be executed, not assumed. "It should pass" is not verification
3. Scope before code — Define IN/OUT/exit criteria before touching files. Freeze what you're not changing
4. Honest reporting — WORKING / PARTIAL / BROKEN labels. No silent brokenness, no mock deception
5. Session continuity — Start with handoff, end with checkpoint. Context survives across sessions

How Skills Connect

Skills declare relationships via see_also (related) and not_for
(misuse guardrails) in their frontmatter. Key relationships:

Diagram (arrows = "hands off to" / "informs"):

setup ──> scope ──> freeze ──> goal-lock ──> pre-push
                                   │
                                stepback (anytime, any stage)
                                   │
session-start <──> session-checkpoint
                                   │
                            next-action (reads state, recommends)

Changelog

See CHANGELOG.md for the full version history (v3.0 → v6.4).

License

MIT — see LICENSE.

Contributing

Issues and PRs welcome. If you build a skill that fits the lifecycle, open a PR.

Contact

DM @AlexZio00 for custom skill development.