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/l0kifs/web-explorer-mcp/python-testing-rulesgit clone --depth 1 https://github.com/l0kifs/web-explorer-mcpWhat 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 | $0.01842 | $0.01842 |
| Opus 5 | $0.00921 | $0.00921 |
| Sonnet 5 | $0.00368 | $0.00368 |
| Haiku 4.5 | $0.00184 | $0.00184 |
Grade A, and why
web-explorer-mcp python-testing-rules.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 yesterday.
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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rules for an AI Agent Testing a Python Project (pytest)
Mandatory rules for writing and running tests. Primary framework: pytest.
Basic principles
- Use pytest. Entry points:
tests/directory; filestest_*.py; functionstest_*, classesTest*without__init__. - Tests are isolated and deterministic: no external network, real databases, or clocks; side effects only via fixtures.
- Fast and minimal: one behavior per test; eliminate duplication via parametrization and fixtures.
- Clear names:
test_<unit>_<condition>_<expectation>; assertion messages explain the reason.
pytest practices (minimal yet sufficient)
- Fixtures
- Use
@pytest.fixturefor setup/teardown; minimalscope(defaultfunction). - Use
tmp_path/monkeypatch/capsys/caploginstead of manual mocks of environment/files/IO. - Avoid
autouse=Trueexcept for truly global and safe setup.
- Use
- Parametrization
- Use
@pytest.mark.parametrize(..., ids=...)to cover variants instead of copy-paste. - Keep test data compact (tables, factories), not in long if-chains.
- Use
- Markers and stability
- Use
@pytest.mark.skipif(...)and@pytest.mark.xfail(reason=..., strict=True)for platform-specific/known cases. - Register custom markers (e.g.,
slow,integration) and mark long-running tests.
- Use
- Asynchrony
- For async functions —
@pytest.mark.asyncio. Isolate the event loop; don't mix sync/async in a single test.
- For async functions —
- Asserts
- Use built-in
assert; for floats —pytest.approx.
- Use built-in
Quality and coverage
- Run with code coverage (pytest-cov/coverage.py). Goal — a realistic, maintainable minimum for the project; don't chase 100%.
- Mandatory reports: overall %, per-file coverage, branch misses.
- Cover critical paths first; exclude tests themselves and generated code from the report.
- Minimum thresholds (CI): overall line coverage ≥ 85%; for new/changed code, aim for ≥ 90%.
Isolation and external effects
- FS: only via
tmp_path. Network: mock/fake layers (e.g., adapter/factory); do not call real services. - Time/UUID/environment: fix via fixtures/mocks (
monkeypatch). Reset global state after the test.
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.
- yesterday First seen · 200 lines · 1,842 tokens per session scan A 077bfef8d668
web-explorer-mcp python-testing-rules.instructions.md is an instructions file published in the GitHub repository l0kifs/web-explorer-mcp (2 stars, last pushed 10mo ago), licensed MIT. It adds 1,842 tokens to every session, about $0.0092 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
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.
buildNext
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
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.