Borrowing it
Nothing to install: this file belongs to gopalrajsuresh/covalent-bond. 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/gopalrajsuresh/covalent-bond/main/.claude/skills/covalent-bond-test/SKILL.mdgit clone --depth 1 https://github.com/gopalrajsuresh/covalent-bondWrote 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/skills/gopalrajsuresh/covalent-bond/covalent-bond-test)<a href="https://agentmods.dev/skills/gopalrajsuresh/covalent-bond/covalent-bond-test"><img src="https://agentmods.dev/badge/skills/gopalrajsuresh/covalent-bond/covalent-bond-test/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/skills/gopalrajsuresh/covalent-bond/covalent-bond-test"><img src="https://agentmods.dev/badge/skills/gopalrajsuresh/covalent-bond/covalent-bond-test.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 | $0.00000 | $0.01173 |
| Opus 5 | $0.00000 | $0.00587 |
| Sonnet 5 | $0.00000 | $0.00235 |
| Haiku 4.5 | $0.00000 | $0.00117 |
Grade A, and why
covalent-bond-test 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 11d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing Covalent Bond
npm test runs every test/*.test.js file as a separate process via
test/run-all.js. A suite passes when its process exits 0; use plain
assert and let a failed assertion crash the process. No test framework;
keep it that way (small surface is a feature).
Ground rules
- Every bug fix and every new behavior ships with a test. Put it in the
matching existing suite, or a new
*.test.js; the runner picks it up automatically. - The
mitmsuite is the security-model guardrail. It must stay green, and any change to the key schedule, handshake, or abort logic needs a case there (or a clearly linked one). - Tests must run offline: no network, no wrangler, no deployed relay. Everything talks to the in-process mock relay.
- Tests may
console.logfreely (they are standalone processes, not loaded by the MCP server).
Using the mock relay
import { startMockRelay, stopMockRelay, resetMockRelay } from './mock-relay-server.js';
await startMockRelay(PORT); // pick a UNIQUE port per suite (see below)
resetMockRelay(); // wipe sessions + rate limits between suites
// ... test ...
await stopMockRelay();
Port allocation: each suite binds its own port so suites can never
collide: 8791 handshake, 8792 mcp-routing, 8793 payload-hardening,
8794 rate-limiting, 8795 hardening-regressions. A new suite takes the next
free number. 8787 is reserved for npm run relay:dev.
The mock mirrors the production worker's API exactly (sequence numbers,
create-clobber refusal, rate limits, payload caps, security headers, error
codes). Protocol constants (TTL, caps, throttle, error codes) live once in
relay/constants.js; the mock imports them and the Worker keeps mirrored
copies that relay-parity.test.js verifies by reading worker.js. If you
change the worker's behavior, change the mock in the same PR, keep the shared
constants in sync, and cover the difference with a test.
Deterministic polling (never sleep)
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.
- 11d ago First seen · 104 lines · 0 tokens per session scan A 848e5e5faa67
covalent-bond-test is a skill published in the GitHub repository gopalrajsuresh/covalent-bond (0 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,173 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
front-vitest
Depth for Vitest tests of front- React 19 SPAs when DOM, RTL, TanStack Query hooks, or TanStack Router route-tree tests are needed. USE WHEN: adding jsdom or testing-library, writing tsx render or renderHook tests, testing createMemoryHistory plus RouterProvider, Suspense UI, or React 19 act fixtures. DO NOT USE WHEN…
review-vitest
Vitest review (@repo/vitest-config node/workers presets, Cloudflare Vitest pool, testing split) against current official Vitest and Cloudflare best practices. USE WHEN: user runs /review-vitest or explicitly asks for this review. DO NOT USE WHEN: reviewing app code, other dev dependencies, or implementing features.
agent-mailbox
Create and use disposable, token-scoped email addresses through a configured Agent Mailbox MCP server. Use for testing signups, email verification, magic links, password resets, one-time codes, inbound messages, attachments, and transactional email flows.
verification-loops
Verification Loops are systematic evaluation pipelines that validate agent outputs at every stage of execution.
test-driven-development
Test-Driven Development enforces the RED-GREEN-REFACTOR discipline on every code change an agent produces.
api-testing
Testing patterns for MCP tool/resource handlers using createMockContext and Vitest. Covers mock context options, handler testing, McpError assertions, format testing, Vitest config setup, and test isolation conventions.