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/gadicc/yahoo-finance2/agents-mdgit clone --depth 1 https://github.com/gadicc/yahoo-finance2Wrote 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/gadicc/yahoo-finance2/agents-md)<a href="https://agentmods.dev/instructions/gadicc/yahoo-finance2/agents-md"><img src="https://agentmods.dev/badge/instructions/gadicc/yahoo-finance2/agents-md.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 | $0.00738 | $0.00738 |
| Opus 5 | $0.00369 | $0.00369 |
| Sonnet 5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade B, and why
yahoo-finance2 AGENTS.md scanned grade B with 1 finding 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 5d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
if not sure. For Codex, ~/.codex/config.toml has top level `model` and How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Notes
This file applies to the whole repository. For fuller contributor guidance, read CONTRIBUTING.md; this file repeats the essentials agents are most likely to need during edits.
Project Context
- This is a Deno-first TypeScript library that is published to npm via generated output.
- Source code lives under
src/. Tests usually sit beside the module they cover and use fixtures fromtests/fixtures/http. - The
npm/directory is generated package output. Prefer editing source files undersrc/and regenerate npm output only when the task explicitly calls for it. - The default development branch is
dev.
Commands
- Run the full test suite with
deno task test. - Run a targeted test with
deno task test path/to/file.test.ts. - Run serial tests with
deno task test:serial path/to/file.test.tswhen debugging or limiting live Yahoo request concurrency. - Run schema generation with
deno task schemaafter changing exported interfaces marked with@yf-schema. - Use
deno fmtanddeno lintfor formatting and linting. - Build npm output with
deno task build:npmwhen generated npm artifacts are required.
Testing And Fixtures
- Tests use
fetch-mock-cacheand cached HTTP fixtures for repeatability. - New module tests should call
setupCache()fromtests/common.tswhen they touch Yahoo HTTP responses. FETCH_DEVEL=nocacheforces live network tests without cache.FETCH_DEVEL=recacheupdates cache for failing tests. Be careful with fixture churn, and do not recache files ending in.static.jsonor.fake.json.- Before committing recached fixtures, inspect their HTTP status and payload. Do not commit transient failures such as rate limits, consent interstitials, timeouts, or upstream 5xx responses as replacements for successful fixtures.
Schema And Validation
- TypeScript interfaces in module files are the source of truth for runtime validation schemas.
- If a module file has
@yf-schema, keep the generated.schema.jsonfile in sync withdeno task schema. - Prefer updating typed interfaces and validation schemas together with focused tests that cover the Yahoo response shape involved.
- When Yahoo adds a response field, model it as required first. Make it optional only when other cached valid responses demonstrate that the field is absent, and add descriptive JSDoc for newly exposed fields.
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.
- 5d ago First seen · 72 lines · 738 tokens per session scan B 589a4a1e44d5
yahoo-finance2 AGENTS.md is an instructions file published in the GitHub repository gadicc/yahoo-finance2 (795 stars, last pushed 26d ago), licensed MIT. It adds 738 tokens to every session, about $0.0037 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
typescript-sdk CLAUDE.md
Claude Code instructions for modelcontextprotocol/typescript-sdk, covering claude.md, build & test commands, run a single package script (examples), breaking changes and code style guidelines.
mcp-ts-core AGENTS.md
AGENTS.md instructions for cyanheads/mcp-ts-core, covering developer protocol, consumers, core rules, exports reference and import conventions.
frontmcp AGENTS.md
AGENTS.md instructions for agentfront/frontmcp, a project described as: TypeScript-first framework for the Model Context Protocol (MCP). You write clean, typed code; FrontMCP handles the protocol, transport, DI, session/auth, and execution flow.
turn-based-game-mcp typescript.instructions.md
TypeScript development patterns and best practices for the turn-based games platform.
zod-skill AGENTS.md
Instructions for anivar/zod-skill, covering zod v4 — complete guide, abstract, 1. parsing & type safety, rule: use safeparse() for user input and rule: use parseasync for async refinements.
mcp-zen-of-languages architecture.instructions.md
Instructions for Anselmoo/mcp-zen-of-languages, covering analyzer architecture refactoring, problem statement, solution: architectural patterns, 1. template method pattern (base structure) and 2. strategy pattern (detectors).