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 instructions/mhaviv/pr-narrator-mcp/testinggit clone --depth 1 https://github.com/mhaviv/pr-narrator-mcpWrote 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/mhaviv/pr-narrator-mcp/testing)<a href="https://agentmods.dev/instructions/mhaviv/pr-narrator-mcp/testing"><img src="https://agentmods.dev/badge/instructions/mhaviv/pr-narrator-mcp/testing.svg" alt="Measured on agentmods" 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 | $0.01102 | $0.01102 |
| Opus 5 | $0.00551 | $0.00551 |
| Sonnet 5 | $0.00220 | $0.00220 |
| Haiku 4.5 | $0.00110 | $0.00110 |
Grade A, and why
pr-narrator-mcp testing.instructions.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 4d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test File Review Rules
Mock Setup (Critical Ordering)
vi.mock()calls MUST appear before any imports from the mocked module- This is a Vitest hoisting requirement — violations cause tests to use real implementations
// Correct: vi.mock BEFORE imports
vi.mock("../../src/utils/git.js", () => ({
getCurrentBranch: vi.fn(),
getStagedChanges: vi.fn(),
getGitInfo: vi.fn(),
getBranchChanges: vi.fn(),
getWorkingTreeStatus: vi.fn(),
extractTicketFromBranch: vi.fn(),
extractBranchPrefix: vi.fn(),
extractTicketsFromCommits: vi.fn(),
}));
// THEN import the module under test and mocked modules
import { analyzeGitChanges } from "../../src/tools/analyze-git-changes.js";
import {
getCurrentBranch,
getStagedChanges,
getWorkingTreeStatus,
} from "../../src/utils/git.js";
// Wrong: import before mock — mock is ignored
import { getCurrentBranch } from "../../src/utils/git.js";
vi.mock("../../src/utils/git.js", () => ({ ... })); // Too late!
Mock Completeness
- Each tool test file must mock ALL
git.tsfunctions used by that tool - Missing mocks cause real git operations against the developer's repo
- Use
vi.mocked(fn)for type-safe mock access — never useas jest.Mockor similar casts
// Correct
vi.mocked(getCurrentBranch).mockResolvedValue("feature/PROJ-123-add-login");
// Avoid
(getCurrentBranch as any).mockResolvedValue("feature/PROJ-123-add-login");
Mock Return Values
- Mock return values must match the actual interface exactly
- Do not skip required fields — this hides integration bugs
- For complex interfaces, define reusable fixtures
// Good: all required fields present
vi.mocked(getWorkingTreeStatus).mockResolvedValue({
modified: [],
untracked: [],
deleted: [],
modifiedCount: 0,
untrackedCount: 0,
deletedCount: 0,
totalUncommitted: 0,
});
// Bad: missing required fields
vi.mocked(getWorkingTreeStatus).mockResolvedValue({
modified: [],
});
Test Lifecycle
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.
- 4d ago First seen · 156 lines · 1,102 tokens per session scan A ba584a97487b
pr-narrator-mcp testing.instructions.md is an instructions file published in the GitHub repository mhaviv/pr-narrator-mcp (1 stars, last pushed 6mo ago), licensed MIT. It adds 1,102 tokens to every session, about $0.0055 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 instructions, from other repositories
Testing Instructions
Applied when writing or modifying test files.
coding-agent-safety-gate AGENTS.md
Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.
tegro-money-mcp CLAUDE.md
Claude Code instructions for TegroTON/tegro-money-mcp, covering claude.md — tegro-money-mcp, layout, run / build and rules.
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).