Borrowing it
Nothing to install: this file belongs to getmasv/masv-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/getmasv/masv-mcp-server/main/.kiro/steering/testing.mdgit clone --depth 1 https://github.com/getmasv/masv-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/getmasv/masv-mcp-server/testing)<a href="https://agentmods.dev/instructions/getmasv/masv-mcp-server/testing"><img src="https://agentmods.dev/badge/instructions/getmasv/masv-mcp-server/testing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/getmasv/masv-mcp-server/testing"><img src="https://agentmods.dev/badge/instructions/getmasv/masv-mcp-server/testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.04292 | $0.04292 |
| Opus 5.5 | $0.01717 | $0.01717 |
| Sonnet 5.5 | $0.00858 | $0.00858 |
| Haiku 4.5 | $0.00429 | $0.00429 |
Grade A, and why
masv-mcp-server testing.md 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 25d 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing
How to write and run tests in this repo.
Run
npm test # offline suite. no credentials, no network
Run it before declaring work done. No build step is needed — everything, including the tests that spawn the server as a subprocess, runs straight from TypeScript under Node's type stripping.
Keep it that way. Pointing a test at build/index.js reintroduces a dependency that fails in the worst
possible way: a stale build does not error, it passes against code that is no longer in src/, so adding a
tool without recompiling would leave the manifest-parity test green. The emit step is covered by
npm run bundle in CI and by the release scripts instead.
npm run test:coverage # same suite, plus a per-file report for src/
Coverage is a "what did I forget" pass, not a target. There is no coverage gate in CI and should not be one — a number says nothing about whether the cases you wrote were the right ones. Read the uncovered lines and decide whether each is a case you forgot or code nobody needs.
Two details in that command worth knowing:
--test-coverage-include='src/**'scopes the report to production code. Without it the test files are measured too, which answers a question nobody asked.--experimental-test-coverageis Stability 1, so the flag name and the report format are exempt from semver and a Node bump can change them. Fine for a local tool; another reason not to gate on it.
src/index.ts reports well below the rest and that figure is honest, not an artefact. The subprocess that
surface.test.ts spawns inherits coverage collection, so registering the 20 tools is counted, but the
handler bodies are not — nothing calls a tool through the server. Each one is a thin
try { … return mcpOk(data) } catch { return mcpError(error) } wrapper around an API function that is
itself fully covered, so the untested part is the wiring. Covering it would mean driving tools/call over
the MCP client, which reaches real fetch in the child with no stub available.
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.
- 25d ago First seen · 329 lines · 4,292 tokens per session scan A 5e325d10dcb0
masv-mcp-server testing.md is an instructions file published in the GitHub repository getmasv/masv-mcp-server (5 stars, last pushed 21d ago), licensed MIT. It adds 4,292 tokens to every session, about $0.0172 per session on Opus 5.5. 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 2026-09-26.
Other instructions, from other repositories
vibetags com-example-indexed-app-DocumentService.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for documentservice, security audit requirements, rules for method render, test-driven requirements and rules for method storagekey.
vibetags com-example-service-NewAnnotationsShowcase-SandboxTestHelper.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for sandboxtesthelper and sandbox restriction.
vibetags com-example-testing-PaymentFixturesTest.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for paymentfixturestest and context & focus.
vibetags com-example-testing-GoldenPayloadFixtures.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for goldenpayloadfixtures and locked status.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.