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 skills/nutdnuy/sec-opendata-th/sec-open-apinpx skills add nutdnuy/sec-opendata-th --skill sec-open-apigit 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/skills/nutdnuy/sec-opendata-th/sec-open-api)<a href="https://agentmods.dev/skills/nutdnuy/sec-opendata-th/sec-open-api"><img src="https://agentmods.dev/badge/skills/nutdnuy/sec-opendata-th/sec-open-api.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 | $0.00111 | $0.02977 |
| Opus 5 | $0.00056 | $0.01489 |
| Sonnet 5 | $0.00022 | $0.00595 |
| Haiku 4.5 | $0.00011 | $0.00298 |
Grade A, and why
sec-open-api scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
prefer the bundled Python CLI/client over raw `curl` because it handles key How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEC Open API (Thailand)
Wrapper skill for calling the Thai SEC's Open Data API. In this repository,
prefer the bundled Python CLI/client over raw curl because it handles key
resolution, retry/backoff, rate limiting, JSON output, and v2 cursor pagination.
0. Resolve fund and AMC names offline first
The plugin bundles a compact SEC fund-profile snapshot so name lookup does not
need a subscription key or a network request. Use it before asking for a key
when the user gives a fund name, abbreviation, AMC name, proj_id, or AMC
unique_id:
python -m secopendata catalog-info
python -m secopendata amc-search "กสิกร"
python -m secopendata fund-search "K-CHANGE" --status Registered
python -m secopendata fund-search "หุ้นไทย" --amc "SCB" --limit 20
Search supports Thai/English names, abbreviations, IDs, AMC filters, and fund
status filters. Report the snapshot's as_of date when freshness matters. Use
the live API only after resolving IDs locally or when the user needs newer data.
1. Get the API key — every time, from the conversation only
This rule applies to live API requests, not the bundled offline catalog. This skill is shared/portable, so never read or write the key to disk and never hardcode it in commands you save to files.
- If the user has already given a key earlier in this conversation, reuse it.
- Otherwise, ask the user directly: "ขอ Ocp-Apim-Subscription-Key ของคุณเพื่อใช้เรียก SEC Open API" before making any request.
- If the user instead says it's in an environment variable (e.g.
SEC_API_KEY), use that env var in the command rather than asking again. - Never echo the raw key back in your own commentary; only pass it inside the request header.
2. Base URL & headers
https://api.sec.or.th
Every request needs this header; the bundled CLI adds it automatically from the resolved env var/key store:
-H "Ocp-Apim-Subscription-Key: <key>"
-H "Content-Type: application/json"
Preferred CLI examples:
SEC_PVD_KEY="$SEC_API_KEY" python -m secopendata request \
--method GET \
--path /v1/pvd/factsheet/amc
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 190 lines · 111 tokens per session scan A 3fabae3b6dcc
sec-open-api is a skill published in the GitHub repository nutdnuy/sec-opendata-th (8 stars, last pushed 1mo ago), licensed MIT. It adds 111 tokens to every session and 2,977 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sector-rotation
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.