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/anatomia-dev/anatomia/ai-patternsnpx skills add anatomia-dev/anatomia --skill ai-patternsgit clone --depth 1 https://github.com/anatomia-dev/anatomiaWhat 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 | $0.00041 | $0.00300 |
| Opus 5 | $0.00020 | $0.00150 |
| Sonnet 5 | $0.00008 | $0.00060 |
| Haiku 4.5 | $0.00004 | $0.00030 |
Grade A, and why
ai-patterns 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
AI Patterns
Detected
Rules
- All LLM calls through a centralized client wrapper. Configure retry, timeout, and error handling once — not per-call.
- Never interpolate raw user input into system prompts. User content goes in user messages with clear role boundaries. System instructions stay immutable.
- Treat all LLM output as untrusted. Validate and sanitize before using in database queries, HTML rendering, or business logic.
- Handle LLM errors by type: retry rate limits with backoff, truncate input for context overflow, log content filter triggers, fail gracefully for API outages.
- Use structured output (JSON mode, tool_use) for data extraction. Never regex-parse free-text LLM responses for application data.
- Centralize prompt templates — don't scatter prompt strings across business logic. Prompts should be versionable, testable, and reviewable independently.
- Log model, token count, and latency per LLM call. You can't optimize cost or debug quality without knowing what each request consumed.
Gotchas
Not yet captured. Add as you discover them during development.
Examples
Not yet captured. Add short snippets showing the RIGHT way.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 25 lines · 41 tokens per session scan A 9de89df405b1
ai-patterns is a skill published in the GitHub repository anatomia-dev/anatomia (32 stars, last pushed 29d ago), licensed MIT. It adds 41 tokens to every session and 300 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-30.
Other skills, from other repositories
neus-integrate
Add NEUS access control to a host app. Install the SDK, drop in the gate widget, wire the server check, and test the flow. Use when a developer wants to gate content, sell access, or add proof-based checks to their application.
neus-trust-workflow
Checks identity, permissions, and reusable proofs before sensitive assistant actions. Use when verifying authority, mounting a Trusted Agent, managing Vault secrets, or when the user asks for NEUS Verify.
neus-setup
Add the hosted NEUS endpoint, sign in, and reuse profile, agents, and proofs.
agent-host-e2e-tests
Use when writing, recording, updating, or troubleshooting the agent host end-to-end tests under src/vs/platform/agentHost/test/node/e2e (black-box tests that drive the whole agent host over the AHP protocol, using a CapiReplayProxy record/replay system for Claude/Copilot/Codex). Covers adding a cross-provider test…
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
lint-js
Lint JS/TS code only. Use before opening a PR when only JavaScript or TypeScript files were changed (no Rust).