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/zoo-code-integrationnpx skills add layer1labs/specsmith --skill zoo-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 | $0.00839 |
| Opus 5 | $0.00000 | $0.00419 |
| Sonnet 5 | $0.00000 | $0.00168 |
| Haiku 4.5 | $0.00000 | $0.00084 |
Grade A, and why
zoo-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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zoo Code — Specsmith Governance Integration
Use this skill when working in Zoo Code or Roo Code on a Specsmith-governed repository.
Goal
Make Zoo/Roo behave like a governed local engineering agent, not an unconstrained chat assistant.
The required pattern is:
Architect plans
Coder edits
Debug/Tool runs and parses commands
Reviewer critiques
Specsmith preflight/verify/trace gates the work
The model that writes a patch must not be the only model that approves it.
Required local project files
Project-local Zoo/Roo integration lives in .roo/:
.roo/mcp.json— repo-local MCP server registration forspecsmith-governance.roo/specsmith-rules.md— mandatory agent protocol for Zoo/Roo.roo/modes.local.json— project-local reference mode definitions.roo/global-settings.copy-to-zoo-code.json— copyable global Zoo Code/OpenAI-compatible provider settings
Only .roo/mcp.json and .roo/specsmith-rules.md are intended to be active project files. Global provider/model settings must be copied into Zoo Code global settings by the operator.
Session start
- Read
AGENTS.mdand.roo/specsmith-rules.md. - Call the MCP tool
governance_checkpoint. - Call
governance_phaseandgovernance_req_listbefore changing code. - Summarize the current phase, failing checks, relevant requirements, and permitted scope.
Before any code change
Call governance_preflight with one sentence describing the intended change.
Do not edit files unless the decision is accepted.
If the decision is needs_clarification, ask a narrow question or reduce the change scope.
If the decision is rejected, stop and report why.
During implementation
Follow role separation:
- Architect mode may plan and inspect but should not directly edit production code.
- Code mode may edit only within the accepted preflight scope.
- Debug/Tool mode should run safe commands and parse outputs; it should not make large edits.
- Review mode should read diffs, requirements, and tests; it should not rewrite the patch unless explicitly promoted.
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 · 114 lines · 0 tokens per session scan A 280fd145ac01
zoo-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 839 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.