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/agent-hellboy/mcp-runtime/design-principlesnpx skills add Agent-Hellboy/mcp-runtime --skill design-principlesgit clone --depth 1 https://github.com/Agent-Hellboy/mcp-runtimeWhat 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 | $0.00113 | $0.01735 |
| Opus 5 | $0.00056 | $0.00868 |
| Sonnet 5 | $0.00023 | $0.00347 |
| Haiku 4.5 | $0.00011 | $0.00173 |
Grade A, and why
design-principles 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Principles
Apply these when designing or reviewing anything with a contract or a trust boundary in MCP Runtime: REST/JSON-RPC APIs, CRD shapes (api/v1alpha1), CLI flags, operator reconciliation, the gateway pipeline, Sentinel services, and MCP tool surfaces. Prefer these over ad-hoc choices; when two are in tension, make the tradeoff explicit (see Make tradeoffs explicit).
One-line north star:
Good design makes the right thing easy, the wrong thing hard, and future change less painful.
API design (the 12)
- RESTful resource naming — nouns, not verbs.
GET /users/{id}, notGET /getUser. - Simple, predictable URLs — guessable paths.
/users/{id}/orders, not/fetchAllOrdersForUser. - Correct HTTP methods —
GETread,POSTcreate,PUTfull update,PATCHpartial,DELETEdelete. - Proper status codes — 200/201, 400/401/403/404/409, 500. Don't return 200 with an error body.
- Consistent request/response shape — predictable JSON envelope (
{ "data": …, "error": … }). - Clear, coded errors —
{ "code": "INVALID_EMAIL", "message": "…", "field": "email" }, never just "failed". - Filtering, sorting, pagination on list APIs —
?status=active&sort=created_at&page=1&limit=20. Never return everything. - Don't abuse query params for identity — prefer nested paths (
/users/123/orders) over?user_id=123for core relationships. - Version your APIs —
/api/v1/…so breaking changes don't break old clients. - Clear actions for non-CRUD —
POST /orders/{id}/cancel,POST /payments/{id}/retryas explicit sub-resources. - Model meaningful state transitions —
CREATED → PAID → SHIPPED → DELIVERED; reject invalid jumps. - Security from the start — authN (who are you), authZ (what may you do), rate limiting, input validation, no sensitive-data leaks.
API design is about resources, behavior, state, errors, security, and future compatibility — not just endpoints.
System / generic design principles
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 · 77 lines · 113 tokens per session scan A 39cf120f73ec
design-principles is a skill published in the GitHub repository Agent-Hellboy/mcp-runtime (5 stars, last pushed 8d ago), licensed Apache-2.0. It adds 113 tokens to every session and 1,735 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
local-frontend-check
Smoke-test or verify UI behaviour on the local Jarvis Registry frontend running at http://localhost/gateway. Use for manual regression checks, bug-fix verification, and end-to-end confirmation of specific flows without running the automated test suite.
release-notes
Create release notes for a new version tag. Gathers all commits, PRs, issues fixed, and breaking changes since a previous release. Creates the release notes markdown file, tags the repo, and pushes. Asks the user to confirm the base version to diff against.
agentcore-register
Given an MCP server URL, probe the server via curl to discover its metadata and tools, then generate a markdown file with copy-pasteable content for each field in the Amazon Bedrock AgentCore "Create record" form.
debug
Debug issues in the MCP Gateway Registry using first-principles thinking. Invoke when something is broken, timing out, returning errors, or behaving unexpectedly. Forces structured root-cause analysis before any code change is proposed.
search-benchmark
Generate a search quality benchmark for the AI Registry. Generates ground truth from the registry's assets, runs 100+ queries against the semantic search API, evaluates results using NDCG@10/MRR/Recall, and produces a markdown report. Use when you want to measure search quality after changes to the scoring algorithm…
benchmark-report
Generate a benchmark report from stress test results (registration, API performance, search concurrency). Reads JSON result files and produces a markdown report suitable for docs/benchmarks/.