agentmods.dev

dexter-jp: Instructions file for Codex

AGENTS.md

dexter-jp AGENTS.md is an instructions file for Codex, OpenCode from edinetdb/dexter-jp. It costs 2,004 tokens per session, scanned A, original, MIT.

Repository guidance for Dexter JP, a command-line AI agent for researching Japanese listed companies using financial data, web search, browser access, and multiple language-model providers.

In plain words
What is it for?
Use it when developing Dexter JP's research workflows, financial queries, web scraping, model providers, command-line interface, skills, or evaluations.
Why use it?
It maps the agent, terminal interface, finance tools, search tools, browser, skills, and evaluation code so changes can be made in the right area.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is edinetdb/dexter-jp's own configuration. It tells Codex and OpenCode how to work on dexter-jp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dexter-jp configures →

not rated 314repo changed 29d ago A scan 2,004 tokens original MIT
View source ↗ edinetdb/dexter-jp edinetdb.jp
Reuse

Borrowing it

Nothing to install: this file belongs to edinetdb/dexter-jp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/edinetdb/dexter-jp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/edinetdb/dexter-jp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for dexter-jp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/edinetdb/dexter-jp/agents-md/github.svg)](https://agentmods.dev/instructions/edinetdb/dexter-jp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/edinetdb/dexter-jp/agents-md"><img src="https://agentmods.dev/badge/instructions/edinetdb/dexter-jp/agents-md/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.

agentmods 80×15 button for dexter-jp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/edinetdb/dexter-jp/agents-md"><img src="https://agentmods.dev/badge/instructions/edinetdb/dexter-jp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,004 This file is loaded in full into every session.
When invoked 2,004 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02004 $0.02004
Opus 5.5 $0.00802 $0.00802
Sonnet 5.5 $0.00401 $0.00401
Haiku 4.5 $0.00200 $0.00200

Measured 29d ago against content hash ee5d0c059670, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dexter-jp AGENTS.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 29d 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.

AGENTS.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

  • Repo: https://github.com/edinetdb/dexter-jp
  • Dexter JP is a CLI-based AI agent for deep financial research on Japanese listed companies, built with TypeScript, Ink (React for CLI), and LangChain. Powered by EDINET DB API.

Project Structure

  • Source code: src/
    • Agent core: src/agent/ (agent loop, prompts, scratchpad, token counting, types)
    • CLI interface: src/cli.ts (Ink/React), entry point: src/index.tsx
    • Components: src/components/ (Ink UI components)
    • Model/LLM: src/model/llm.ts (multi-provider LLM abstraction)
    • Tools: src/tools/ (financial search, web search, browser, skill tool)
    • Finance tools: src/tools/finance/ (financials, text-blocks, earnings, shareholders, key-ratios, screening)
    • Search tools: src/tools/search/ (Exa preferred, Tavily fallback)
    • Browser: src/tools/browser/ (Playwright-based web scraping)
    • Skills: src/skills/ (SKILL.md-based extensible workflows, e.g. DCF valuation)
    • Utils: src/utils/ (env, config, caching, token estimation, markdown tables)
    • Evals: src/evals/ (LangSmith evaluation runner with Ink UI), src/evals/judge/ (judge-layer benchmark)
    • Judge layer: src/judge/ (typed questions answered with probabilities; jev / llm / replay backends)
    • /check: src/check/ (assembly, panel, record) and src/check/core/ (pure claim/paragraph/numeric helpers)
    • /watch: src/watch/ (+ src/tools/finance/events.ts for the disclosure feed)
    • Guards: src/guard/ (input guard, output linter) — see "Guards" below
    • Egress ledger: src/config/egress.ts (single source for the README table and the startup screen)
    • Bundled disclosure data: src/data/ (schema + build gate) and src/data/materials/
    • Deep links: src/links/deeplink.ts (URL construction only)
  • Config: .dexter/settings.json (persisted model/provider selection)
  • Environment: .env (API keys; see env.example)

Build, Test, and Development Commands

  • Runtime: Bun (primary). Use bun for all commands.
  • Install deps: DEXTER_SKIP_BROWSER=1 bun install (skips the ~130MB Chromium download; drop the flag when you need the browser tool)
  • Run: bun run start or bun run src/index.tsx
  • Dev (watch mode): bun run dev
  • Type-check: bun run typecheck
  • Tests: bun test
  • Demo (no keys, no network): bun run demo
  • Bundled-data gate: bun run check:data
  • Judge benchmark: bun run bench:judge
  • Evals: bun run src/evals/run.ts (full) or bun run src/evals/run.ts --sample 10 (sampled)

Read the full file on GitHub · 128 lines

Changes

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.

  1. 29d ago Changed · +28 lines · +627 tokens per session ee5d0c059670
  2. 1mo ago Changed · +2 lines · +82 tokens per session 1a75aba0c116
  3. 1mo ago First seen · 98 lines · 1,295 tokens per session scan A d569f6c8a675

Subscribe to this mod's changes

dexter-jp AGENTS.md is an instructions file published in the GitHub repository edinetdb/dexter-jp (314 stars, last pushed 14d ago), licensed MIT. It adds 2,004 tokens to every session, about $0.0080 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 2026-08-30.

LangChainai-agentedinetfinancial-analysisjapanese-stocksjquants
Related

Other instructions, from other repositories

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).

microsoft/vscode · 9,649 tokens

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.

vercel/next.js · 7,384 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens