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/nutdnuy/sec-opendata-th/agents-mdgit clone --depth 1 https://github.com/nutdnuy/sec-opendata-thWrote 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/nutdnuy/sec-opendata-th/agents-md)<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>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 | $0.00689 | $0.00689 |
| Opus 5 | $0.00345 | $0.00345 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
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.
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 fromsecopendata.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:
- explicit value in code
SEC_<PRODUCT_OR_CATEGORY>_KEYSEC_API_KEY~/.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
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 · 85 lines · 689 tokens per session scan A 70ed7c069c51
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.
Other instructions, from other repositories
ClawRouter CLAUDE.md
Claude Code instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
LLM-TradeBot copilot-instructions.md
Copilot instructions for EthanAlgoX/LLM-TradeBot, covering repository instructions, core rules, validation and ai asset governance.
Convertible-Bond-Pricing-Research CLAUDE.md
Instructions for ericxuzhesheng/Convertible-Bond-Pricing-Research, covering claude.md — convertible bond pricing research, current published state and routine commands.
bukio-cli AGENTS.md
AGENTS.md instructions for erikvankempen/bukio-cli, covering agents.md — bukio-cli agent manual, 1. house rules (non-negotiable), 2. environment, 3. command quick reference and 3.1 jurisdiction profiles (16 markets).
swiss-snb-mcp CLAUDE.md
Claude Code instructions for malkreide/swiss-snb-mcp, covering claude.md, teil 1 — konventionen (portfolio-weit), vor der arbeit, tests and wenn etwas rot ist.