What is ferc-elibrary?

A workflow for using an MCP server that searches and reads FERC eLibrary filings. FERC eLibrary is the Federal Energy Regulatory Commission’s online collection of regulatory documents.

It is for searching filings and dockets, syncing documents into a cache, locating relevant passages, and analyzing regulatory records.

It helps find relevant filings and read large documents in manageable sections instead of loading an entire document at once.

ferc-elibrary — Skill for Claude Code and Codex by PowerLaw-Technology

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.

Any agent

npx skills add PowerLaw-Technology/ferc-elibrary-mcp --skill ferc-elibrary

Clone the repo

git clone --depth 1 https://github.com/PowerLaw-Technology/ferc-elibrary-mcp

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/powerlaw-technology/ferc-elibrary-mcp/ferc-elibrary/github.svg)](https://agentmods.dev/skills/powerlaw-technology/ferc-elibrary-mcp/ferc-elibrary)

Your own site

<a href="https://agentmods.dev/skills/powerlaw-technology/ferc-elibrary-mcp/ferc-elibrary"><img src="https://agentmods.dev/badge/skills/powerlaw-technology/ferc-elibrary-mcp/ferc-elibrary/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/powerlaw-technology/ferc-elibrary-mcp/ferc-elibrary"><img src="https://agentmods.dev/badge/skills/powerlaw-technology/ferc-elibrary-mcp/ferc-elibrary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 646 The whole file, excluding the scripts and references it only reads on demand.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00055	$0.00646
Opus 5.5	$0.00022	$0.00258
Sonnet 5.5	$0.00011	$0.00129
Haiku 4.5	$0.00006	$0.00065

Measured 2mo ago against content hash d696604407a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ferc-elibrary 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 2mo 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.

skills/ferc-elibrary/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FERC eLibrary MCP workflow

Principles

Never request full document text. Large orders and tariffs can exceed a million characters.
Cache before re-fetching. Check cached flags on search and docket results; use sync_docket for incremental updates.
Locate, then read. Use get_document_outline and search_within_document before read_document.

Standard workflow

1. Discover

search_filings for keywords, document types, or parties
get_docket for a full proceeding sheet
Note cached: true/false on each accession

2. Populate the store

sync_docket for everything new on a docket (preferred for bulk)
download_file for a single accession or attachment
cache_status to confirm what is already stored

3. Read substance (bounded)

For each file you need to analyze:

get_document_outline(accession, filename) — bookmarks or heuristic sections
search_within_document(accession, filename, query) — jump to relevant passages
read_document(accession, filename, pages=[...]) or char_start / char_end — read only what you need
If truncated: true, continue with next_char_start or the next page range

4. Summarize large filings

Summarize section by section, not in one pass
Each section: outline → search → bounded read → short summary
Merge section summaries at the end

Anti-patterns

Do not use get_filing_text on 100+ page filings (deprecated; bounded and may truncate)
Do not call read_document without pages or char_range on unknown-size documents
Do not re-download accessions already marked cached: true

Configuration (firm shared cache)

Point FERC_STORE_ROOT at a folder the whole team can access:

Local: shared network drive or SharePoint-synced directory (FERC_STORE_BACKEND=local)
AWS: FERC_STORE_BACKEND=s3 and FERC_STORE_ROOT=s3://bucket/prefix (Phase 2)

Tool quick reference

Goal	Tool
Find filings	`search_filings`, `get_docket`
Fill cache	`sync_docket`, `download_file`
Inspect cache	`cache_status`
Table of contents	`get_document_outline`
Find a phrase	`search_within_document`
Read a section	`read_document` with bounds

Read the full file on GitHub · 70 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.

2mo ago First seen · 70 lines · 55 tokens per session scan A d696604407a1

Subscribe to this mod's changes

ferc-elibrary is a skill published in the GitHub repository PowerLaw-Technology/ferc-elibrary-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 646 once invoked, about $0.0002 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 2026-08-31.

Legal and compliance Research

ferc-elibrary next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ferc-elibraryPowerLaw-Technology/ferc-elibrary-mcp	Skill	0	2mo ago	MIT	A	55	Claude Code, Codex
fto-triageanthropics/claude-for-legal	Skill	9.9k	yesterday	Apache-2.0	A	81	Claude Code
legal-holdanthropics/claude-for-legal	Skill	9.9k	yesterday	Apache-2.0	A	68	Claude Code
specification-writingwanshuiyin/Auto-claude-code-research-in-sleep	Skill	19k	2d ago	MIT	A	49	Claude Code
regulatory-research-fallbackHKUDS/OpenSpace	Skill	7.9k	yesterday	MIT	A	20	Claude Code, Codex
terms-of-servicegenspark-ai/genoffice	Skill	12k	today	Apache-2.0	A	32	Claude Code, Codex
x-scorecardx-cmd/x-cmd	Skill	4.7k	8d ago	Apache-2.0	A	57	Claude Code, Codex