shellcheck

A registry-based check that estimates whether a company shows signs of being a shell company. Shell companies may have little visible business activity, though the score is not proof of wrongdoing.

In plain words
What is it for?
Use it to review director counts, filed accounts, registered addresses, employee figures, ownership overlaps, appointment history, company age, and name patterns.
Why use it?
It gathers several warning signs from government records and shows the evidence behind each one instead of relying on a single suspicion.

Command

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 commands/sophymarine/openregistry/shellcheck
Clone the repo
git clone --depth 1 https://github.com/sophymarine/openregistry
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 553 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 $0.00044 $0.00553
Opus 5 $0.00022 $0.00277
Sonnet 5 $0.00009 $0.00111
Haiku 4.5 $0.00004 $0.00055

Measured 2d ago against content hash ffdabc5d81b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shellcheck 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.

commands/shellcheck.md · 32 lines

What it actually says

Score shell-probability for "$1" in $2. Every signal must be backed by a live government-registry lookup — cite the record for each.

Step 1 — Resolve search_companies + get_company_profile → company_id.

Step 2 — Signal collection (live calls)

  • SIG-1 single director: get_officers, count active = 1?
  • SIG-2 zero accounts: list_filings(category="accounts") → count == 0 after required filing date?
  • SIG-3 micro-entity only: profile.accounts type = "micro-entity"?
  • SIG-4 overseas registered office: profile.address.country ≠ incorporation country?
  • SIG-5 shared-address concentration (where jurisdiction supports reverse-lookup): 50+ companies at same office?
  • SIG-6 nominee director: for each director in GB, get_officer_appointments — 10+ appointments = flag
  • SIG-7 PSC = director: cross-reference get_persons_with_significant_control with get_officers — same natural person?
  • SIG-8 zero employees: fetch_document on latest accounts → parse XBRL average-number-of-employees
  • SIG-9 young + dormant: inc date <18mo + filing count 0
  • SIG-10 name patterns: "Nominees Ltd", number-only, typical offshore templates

Step 3 — Score (0-100) Strong (SIG-1/2/3): 20pts each · Multipliers (SIG-4/5/6/7): 10pts each · Weak (SIG-8/9/10): 5pts each. Cap at 100.

Step 4 — Report Shell probability: X/100 with each contributing signal's evidence cited (e.g. "SIG-6 (nominee director pattern): director John Smith holds 47 active appointments — see get_officer_appointments response for officer_id YYY"). Missing data for a signal is explicitly marked "❌ Signal Z: insufficient data".

Step 5 — Caveats Shell signals ≠ proof of fraud. Score is a screening heuristic, one layer in AML pipeline. Many legitimate holding vehicles tick several boxes.

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 · 32 lines · 44 tokens per session scan A ffdabc5d81b8

Subscribe to this mod's changes

shellcheck is a command published in the GitHub repository sophymarine/openregistry (17 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 44 tokens to every session and 553 once invoked, about $0.0002 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.