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/cyanheads/shift-mcp-server/api-testingnpx skills add cyanheads/shift-mcp-server --skill api-testinggit clone --depth 1 https://github.com/cyanheads/shift-mcp-serverWhat 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 | $0.00046 | $0.05902 |
| Opus 5 | $0.00023 | $0.02951 |
| Sonnet 5 | $0.00009 | $0.01180 |
| Haiku 4.5 | $0.00005 | $0.00590 |
Grade A, and why
api-testing 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.
This is a copy
100% identical to api-testing — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 528 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Tests target handler behavior directly — call handler(input, ctx), assert on the return value or thrown error. The framework's handler factory (try/catch, formatting, telemetry) is not involved. Use createMockContext from @cyanheads/mcp-ts-core/testing to construct the ctx argument.
Additional exports from /testing: createMockSession() binds a mock handler context to an HTTP session; createFetchMock() provides a strict upstream HTTP fake; runToolContract() executes a definition through schema, handler, formatting, enrichment/content, and production-shaped error-envelope checks. createMockLogger() returns a standalone MockContextLogger, and createInMemoryStorage(options?) provides a real StorageService backed by InMemoryProvider.
Philosophy: Test behavior, not implementation. Refactors should not break tests. Match the repo's existing test layout: fresh scaffolds use tests/, while colocated src/**/*.test.ts files are also supported. Integration tests at I/O boundaries over unit tests of internals.
mcpTest — fixture-based Vitest test
mcpTest is a test.extend-based Vitest test that provides ctx, session, fetchMock, and storage as per-test fixtures — fresh instances for every test, eliminating boilerplate and enforcing isolation automatically. fetchMock is installed as globalThis.fetch only when requested by a test and restored afterward.
import { mcpTest } from '@cyanheads/mcp-ts-core/testing/vitest';
mcpTest('echoes the message', async ({ ctx }) => {
const result = await echoTool.handler(echoTool.input.parse({ message: 'hi' }), ctx);
expect(result.message).toBe('hi');
});
mcpTest('uses storage fixture', async ({ ctx, storage }) => {
const svc = new MyService(config, storage);
const result = await svc.doWork(ctx);
expect(result).toBeDefined();
});
mcpTest('stubs an upstream HTTP boundary', async ({ fetchMock }) => {
fetchMock.route({
match: 'https://api.example.test/items/42',
respond: Response.json({ id: '42' }),
});
await expect(loadItem('42')).resolves.toMatchObject({ id: '42' });
});
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 · 528 lines · 46 tokens per session scan A 1958f0095306
api-testing is a skill published in the GitHub repository cyanheads/shift-mcp-server (1 stars, last pushed 11d ago), licensed Apache-2.0. It adds 46 tokens to every session and 5,902 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to api-testing, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
superagenticmcp
SuperAgenticMCP — the switchboard for your agent swarm. MCP-native router and multi-agent control plane that plans tasks, routes tool calls to racked MCP servers by capability and latency, streams execution, and files results into a memory-scope graph. Use when the user needs multi-agent orchestration over MCP, a…
agents
Coordinate with other AI agents on this machine via the Dibs board. Use when you need to see what other agents are doing, avoid stepping on their work (directory claims), or send/receive messages (questions, requests to approve/deny, FYIs, handoffs). Also use whenever a Dibs new-message notification appears.
memory-scope
Memory-scope constellation: persist run artifacts as a linked graph for later retrieval and board visualization.
multi-agent-workflow
Planner → workers → critic loop for SuperAgenticMCP missions. Use when coordinating multi-step agent work across racked MCP servers.
routing-capability
Capability-first routing with latency tie-break for racked MCP servers. Use when selecting which server handles a tool call.
multi-agent-workflow
Orchestrate sequential multi-agent workflows under a shared budget on OpenMesha. Use when a goal needs planner/researcher/worker roles or council-style decomposition.