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.
npx agentmods add skills/layer1labs/specsmith/claude-code-integrationnpx skills add layer1labs/specsmith --skill claude-code-integrationgit clone --depth 1 https://github.com/layer1labs/specsmithWhat 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 | $0.00000 | $0.00409 |
| Opus 5 | $0.00000 | $0.00204 |
| Sonnet 5 | $0.00000 | $0.00082 |
| Haiku 4.5 | $0.00000 | $0.00041 |
Grade A, and why
claude-code-integration 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 2d 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.
What it actually says
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
- Run at session start:
specsmith kill-session # idempotent; safe when no processes exist
specsmith audit --project-dir .
specsmith sync --project-dir .
specsmith checkpoint --project-dir .
- Output the checkpoint block verbatim before any other response.
- Before every code change:
specsmith preflight "<intent>" --jsondecision == "accepted"→ proceed withwork_item_idin scopedecision == "needs_clarification"→ surface instruction to user first
- Every 8–10 turns:
specsmith checkpoint(output verbatim) - 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.jsonfor global).agents/skills/— skill files auto-discovered by Claude Code 3.x+
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.
- 2d ago First seen · 44 lines · 0 tokens per session scan A 2155d1ebb6df
claude-code-integration is a skill published in the GitHub repository layer1labs/specsmith (7 stars, last pushed 29d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 409 tokens. 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 2026-08-31.
Other skills, from other repositories
accessibility-audit
Unified accessibility audit - axe-core WCAG 2.2 scan, APCA contrast measurement, static a11y checks (aria-label, tabindex, form labels, focus visibility, onClick on non-interactive). Static and live modes.
arch-audit
Audit Claude Code architecture files against Anthropic docs and release notes, and verify internal ecosystem consistency. Run on demand to maintain compliance, catch new features, and keep the context system clean.
pr-review
Autonomous local code review. Reviews either an open PR's diff (via gh) or the local working diff against a base branch (--local, auto-selected when no PR exists yet), spawns a dedicated review subagent with universal + stack-specific severity criteria, posts the review as a comment on the PR (audit trail; skipped in…
security-audit
Security audit: auth/authz on API routes, input validation, row-level access control (RLS in Postgres, ORM scopes or app-level guards elsewhere), response shape review, secret exposure, HTTP headers. Native mode checks entitlements and Keychain. MCP-aware (v1.20+): when mcp-nvd server is wired, Step 3c queries live…
skill-db
Database audit: schema quality, index coverage, row-level access-control completeness, FK cascades, query patterns. Runs live SQL verification (PostgreSQL instance in PATTERNS.md; other engines verify the equivalent guard). Migration file safety → /migration-audit.
skill-dev
Code quality audit: detect cross-module coupling, N+1 queries, dead exports, antipatterns, over-large components. Cross-checks against refactoring backlog.