sec-opendata-th AGENTS.md

sec-opendata-th AGENTS.md is an instructions file for Codex, OpenCode from nutdnuy/sec-opendata-th. It costs 689 tokens per session, scanned A, original, MIT.

Repository instructions and a Python client for Thailand's Securities and Exchange Commission open-data service. The service provides public financial-market data, including funds, digital assets, bonds, equities, and company reports.

In plain words
What is it for?
Use them to list available data categories or send GET requests for SEC Thailand data, including financial statements, fund performance, and other supported market-data endpoints.
Why use it?
They give coding agents one documented way to discover categories and request data from the SEC service. This avoids guessing endpoint paths and supports both older and newer API versions.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/nutdnuy/sec-opendata-th/agents-md
Clone the repo
git clone --depth 1 https://github.com/nutdnuy/sec-opendata-th

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 sec-opendata-th AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nutdnuy/sec-opendata-th/agents-md.svg)](https://agentmods.dev/instructions/nutdnuy/sec-opendata-th/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/nutdnuy/sec-opendata-th/agents-md"><img src="https://agentmods.dev/badge/instructions/nutdnuy/sec-opendata-th/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 689 This file is loaded in full into every session.
When invoked 689 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00689 $0.00689
Opus 5 $0.00345 $0.00345
Sonnet 5 $0.00138 $0.00138
Haiku 4.5 $0.00069 $0.00069

Measured 5d ago against content hash 70ed7c069c51, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sec-opendata-th 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 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.

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 · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions — sec-opendata-th

This repository is the shared source of truth for the SEC Open Data Thailand client and plugin. It must work for Codex, Claude Code, Antigravity/Gemini, and GitHub Copilot.

Goal

Provide a Python CLI/client and reusable agent skill for pulling data from api.sec.or.th across all SEC Open Data portal categories:

  • digital assets
  • funds
  • Licence Check
  • One Report
  • provident funds
  • debt
  • bonds
  • equity
  • ESG
  • capital-market operators/professionals
  • investors
  • any future /v1/... or /v2/... endpoint copied from secopendata.sec.or.th

Core Commands

Use the virtual environment when available:

.venv/bin/python -m pytest -q
.venv/bin/python -m secopendata categories
.venv/bin/python -m secopendata request --method GET --path /v1/one-report/fs/2021/financial_statement/C0000000013
.venv/bin/python -m secopendata request --method GET --path /v2/fund/factsheet/performance --cursor-paginate

Generic endpoint access must go through:

python -m secopendata request --method GET --path /v1/<category>/<path>
python -m secopendata request --method GET --path /v2/<category>/<path> --cursor-paginate
python -m secopendata request --method POST --path /v1/<category>/<path> --json '{"Name":""}'

Keep legacy fund helpers, but do not build new category-specific helpers unless they remove repeated real usage. The generic request command is the canonical coverage mechanism for all categories.

Keys

Never commit subscription keys. Key resolution is:

  1. explicit value in code
  2. SEC_<PRODUCT_OR_CATEGORY>_KEY
  3. SEC_API_KEY
  4. ~/.config/secopendata/keys.toml

Examples: SEC_ONE_REPORT_KEY, SEC_DIGITAL_ASSET_KEY, SEC_FUND_KEY, SEC_BOND_KEY, SEC_PVD_KEY, SEC_LICENSE_CHECK_KEY.

Plugin Surfaces

  • Codex plugin manifest: .codex-plugin/plugin.json
  • Codex marketplace manifest: .agents/plugins/marketplace.json
  • Claude plugin manifest: .claude-plugin/plugin.json
  • Claude marketplace manifest: .claude-plugin/marketplace.json
  • Shared skill: skills/sec-open-api/SKILL.md
  • Claude slash commands: commands/*.md
  • GitHub Copilot instructions: .github/copilot-instructions.md
  • Antigravity/Gemini instructions: GEMINI.md

Read the full file on GitHub · 85 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. 5d ago First seen · 85 lines · 689 tokens per session scan A 70ed7c069c51

Subscribe to this mod's changes

sec-opendata-th AGENTS.md is an instructions file published in the GitHub repository nutdnuy/sec-opendata-th (8 stars, last pushed 1mo ago), licensed MIT. It adds 689 tokens to every session, about $0.0034 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.

Related

Other instructions, from other repositories