AgentStack
SKILL verified MIT Self-run

Claude Code Integration

skill-layer1labs-specsmith-claude-code-integration · by layer1labs

A Claude skill from layer1labs/specsmith.

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

Install

$ agentstack add skill-layer1labs-specsmith-claude-code-integration

✓ 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.

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

About

Claude Code — specsmith Governance Integration

One-time setup

specsmith integrate claude-code   # generates CLAUDE.md in project root

For MCP server (structured tool calls without shell roundtrips), add to .mcp.json:

{
  "mcpServers": {
    "specsmith-governance": {
      "command": "specsmith",
      "args": ["mcp", "serve", "--project-dir", "."]
    }
  }
}

Or run: specsmith mcp install-claude-code

Every Claude Code session — mandatory protocol

  1. Run at session start:
specsmith kill-session 2>/dev/null || true
specsmith audit --project-dir .
specsmith sync  --project-dir .
specsmith checkpoint --project-dir .
  1. Output the checkpoint block verbatim before any other response.
  2. Before every code change: specsmith preflight "" --json
  • decision == "accepted" → proceed with work_item_id in scope
  • decision == "needs_clarification" → surface instruction to user first
  1. Every 8–10 turns: specsmith checkpoint (output verbatim)
  2. Session end: specsmith save && specsmith kill-session

Via MCP (preferred when configured)

Claude can call governance_preflight, governance_audit, governance_checkpoint, governance_req_list, governance_phase, and governance_trace_seal as native tools.

Key files

  • CLAUDE.md — project-level governance instructions (read by Claude automatically)
  • .mcp.json — MCP server config (project root or ~/.claude/mcp.json for global)
  • .agents/skills/ — skill files auto-discovered by Claude Code 3.x+

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.