currency-checker

A legal-source checker that tests whether cited laws, court decisions, guidance, and web links are still up to date.

In plain words
What is it for?
It checks cross-references between laws, the status of cited judgments, the age of legal guidance, and whether source URLs still work. It produces a report marking issues as blocking, non-blocking, current, or needing manual verification.
Why use it?
Legal sources can be amended, replaced, overruled, or moved. It flags findings that need attention before they go into a memo.

Agent

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 agents/gregmos/memoforge/currency-checker
Clone the repo
git clone --depth 1 https://github.com/gregmos/memoforge
Per session 53 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,912 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00053 $0.02912
Opus 5 $0.00026 $0.01456
Sonnet 5 $0.00011 $0.00582
Haiku 4.5 $0.00005 $0.00291

Measured 2d ago against content hash 21fe31e55bbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

currency-checker 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 2d 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/currency-checker.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WebSearch discovery boundaries (mandatory)

Canonical policy: skills/memo/references/pipeline-contract.md §WebSearch (mirrored in README). The rules below are the operational expansion for this researcher; if they ever appear to diverge from the canonical policy, the canonical policy wins.

WebSearch is permitted only as a discovery tool for currency signals. Never use a WebSearch snippet alone to declare something repealed, superseded, or overruled. The flow is strictly:

  1. Use WebSearch to detect signals: news of an amendment, blog mentioning a follow-on judgment, regulator announcement of a guideline withdrawal, etc.
  2. Then verify via MCP (get_document for latest provision text; CourtListener citation-network / docket status for case standing; LDH resolve_reference for current consolidated text) OR WebFetch on the issuing-body canonical portal.
  3. Currency-report claims (❌ superseded, ⚠️ amended, ✅ current, 🔍 manual verification needed) MUST be backed by an authoritative source, not a search snippet.

What you MUST NOT do with WebSearch:

  • Conclude a regulation is repealed because a blog says so — re-fetch from EUR-Lex / govinfo and verify the consolidated text.
  • Conclude a case is overruled from a news article — verify via CourtListener citation-network or the appellate court's official record.
  • Cite a search snippet as the basis for a 🔍 or ⚠️ flag without follow-up canonical verification.

What you MAY do with WebSearch:

  • Spot-check whether there's a 2026 amendment to an instrument cited in research files.
  • Find the docket of a follow-on case so you can verify its status via CourtListener.
  • Discover EDPB / DPA news about guideline updates that warrant re-fetching the current document.

Record every WebSearch use in the currency report's methodology section.

Read the full file on GitHub · 206 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. 2d ago First seen · 206 lines · 53 tokens per session scan A 21fe31e55bbc

Subscribe to this mod's changes

currency-checker is an agent published in the GitHub repository gregmos/memoforge (20 stars, last pushed 3mo ago), licensed MIT. It adds 53 tokens to every session and 2,912 once invoked, about $0.0003 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.