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/20twenty/publicgoods/frednpx skills add 20twenty/publicgoods --skill fredgit clone --depth 1 https://github.com/20twenty/publicgoodsWrote 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/20twenty/publicgoods/fred)<a href="https://agentmods.dev/skills/20twenty/publicgoods/fred"><img src="https://agentmods.dev/badge/skills/20twenty/publicgoods/fred.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 5.1 | $0.00073 | $0.03131 |
| Opus 5 | $0.00036 | $0.01566 |
| Sonnet 5 | $0.00015 | $0.00626 |
| Haiku 4.5 | $0.00007 | $0.00313 |
Grade A, and why
fred 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 6d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FRED Economic Data Skill
This skill gives you direct access to the Federal Reserve Bank of St. Louis (FRED) API via a local Node.js CLI — no MCP server required.
The CLI lives at <SKILL_DIR>/scripts/cli.js. Replace <SKILL_DIR> with the absolute path to this skill's base directory (sometimes shown in the Base directory header when the skill loads). It requires Node 18+ (for built-in fetch). No npm install needed.
About FRED
FRED hosts over 800,000 economic time series from ~100 sources — BLS, BEA, Census, Federal Reserve, IMF, World Bank, and others. It covers US macroeconomic indicators (GDP, inflation, unemployment, interest rates, money supply), regional and state-level data, international comparisons, and financial market series. Most series are free and publicly available.
Discovery pattern: If you don't have a series ID, search first to find candidates, then get-series to pull the data. If you're exploring a topic area, browse lets you navigate the category tree or find everything within a release (e.g., all CPI series from the BLS CPI release).
Key concepts:
- A series ID is the stable identifier for a data series (e.g.,
UNRATE,GDP,CPIAUCSL). These are the primary thing to find and use. - A release groups related series published together (e.g., the BLS publishes UNRATE, labor force participation, and dozens of other series in a single monthly release).
- A category is FRED's own topical organization of series (e.g., "Prices > CPI").
- Seasonal adjustment matters —
UNRATE(seasonally adjusted) andUNRATENSA(not) have different behavior; check theseasonal_adjustmentfield to know what you have. - Missing values appear as
nullin observations — common at the start of transformed series (e.g., year-over-year change has no value for the first year).
Commands
1. Search for series
Use this when you have a topic or concept but don't know the series ID. Sort by popularity to surface the most-used series first — for common indicators, the top result is usually what you want.
What ships with it
1 file 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.
- 6d ago First seen · 184 lines · 73 tokens per session scan A c6864094917c
fred is a skill published in the GitHub repository 20twenty/publicgoods (11 stars, last pushed 4mo ago), licensed MIT. It adds 73 tokens to every session and 3,131 once invoked, about $0.0004 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 2026-08-30.
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.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
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…
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.