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 skills add hamzabellouch/agent-skills --skill double-entry-ledger-architecturegit clone --depth 1 https://github.com/hamzabellouch/agent-skillsWrote 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/hamzabellouch/agent-skills/double-entry-ledger-architecture)<a href="https://agentmods.dev/skills/hamzabellouch/agent-skills/double-entry-ledger-architecture"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/double-entry-ledger-architecture/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.
<a href="https://agentmods.dev/skills/hamzabellouch/agent-skills/double-entry-ledger-architecture"><img src="https://agentmods.dev/badge/skills/hamzabellouch/agent-skills/double-entry-ledger-architecture.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00078 | $0.01267 |
| Opus 5.5 | $0.00031 | $0.00507 |
| Sonnet 5.5 | $0.00016 | $0.00253 |
| Haiku 4.5 | $0.00008 | $0.00127 |
Grade A, and why
double-entry-ledger-architecture 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 18d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Double-Entry Ledger Architecture Skill Guide
This skill governs the design, data structures, and mathematical invariants required to build production-grade double-entry financial ledgers.
1. Double-Entry Mathematical Invariants
In double-entry bookkeeping, every financial transaction consists of at least two balanced entries.
$$\sum \text{Debits} = \sum \text{Credits}$$
The fundamental accounting equation must hold true at every millisecond:
$$\text{Assets} = \text{Liabilities} + \text{Equity} + (\text{Revenue} - \text{Expenses})$$
[ Account Classifications & Normal Balances ]
+------------------+------------------+------------------+
| Account Type | Debit (Dr) | Credit (Cr) |
+------------------+------------------+------------------+
| Assets | Increases (+) | Decreases (-) |
| Liabilities | Decreases (-) | Increases (+) |
| Equity | Decreases (-) | Increases (+) |
| Revenue | Decreases (-) | Increases (+) |
| Expense | Increases (+) | Decreases (-) |
+------------------+------------------+------------------+
2. Production Database Schema (PostgreSQL)
-- 1. Chart of Accounts
CREATE TYPE account_classification AS ENUM ('ASSET', 'LIABILITY', 'EQUITY', 'REVENUE', 'EXPENSE');
CREATE TABLE accounts (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
account_code VARCHAR(32) NOT NULL UNIQUE, -- e.g. '1010-CASH-USD'
name VARCHAR(128) NOT NULL,
classification account_classification NOT NULL,
currency VARCHAR(3) NOT NULL DEFAULT 'USD',
is_active BOOLEAN NOT NULL DEFAULT TRUE,
created_at TIMESTAMPTZ DEFAULT clock_timestamp()
);
-- 2. Journal Transactions (Header)
CREATE TABLE journal_transactions (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
reference_id VARCHAR(128) NOT NULL UNIQUE, -- Idempotency key from payment/checkout
description TEXT NOT NULL,
posted_at TIMESTAMPTZ NOT NULL DEFAULT clock_timestamp()
);
-- 3. Journal Entries (Lines: Debits & Credits)
CREATE TABLE journal_entries (
id UUID PRIMARY KEY DEFAULT gen_random_uuid(),
transaction_id UUID NOT NULL REFERENCES journal_transactions(id) ON DELETE RESTRICT,
account_id UUID NOT NULL REFERENCES accounts(id) ON DELETE RESTRICT,
amount NUMERIC(18, 4) NOT NULL CHECK (amount > 0),
is_debit BOOLEAN NOT NULL,
entry_sequence INT NOT NULL,
CONSTRAINT uq_txn_entry_seq UNIQUE (transaction_id, entry_sequence)
);
CREATE INDEX idx_journal_entries_account ON journal_entries(account_id);
CREATE INDEX idx_journal_entries_txn ON journal_entries(transaction_id);
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.
- 18d ago First seen · 139 lines · 78 tokens per session scan A dc88b2bd1ce5
double-entry-ledger-architecture is a skill published in the GitHub repository hamzabellouch/agent-skills (8 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 1,267 once invoked, about $0.0003 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 2026-09-29.
Other skills, from other repositories
biofuels-biodiesel-technology-manager
Use when a task needs the judgment of a Biofuels/Biodiesel Technology and Product Development Manager — deciding whether a lab/bench-scale process is ready to scale up, evaluating feedstock flexibility tradeoffs in process design, pricing a technology's value against regulatory credit pathways (RFS RIN, LCFS CI…
biofuels-production-manager
Use when a task needs the judgment of a Biofuels Production Manager — running a biofuel production facility (ethanol, biodiesel, renewable diesel), managing feedstock supply and quality variability, evaluating a yield or efficiency problem, or balancing production economics against commodity price swings.
bookkeeping-accounting-clerk
Use when a task needs the judgment of a Bookkeeping, Accounting, and Auditing Clerk — reconciling a bank or credit card account, resolving an AP three-way-match discrepancy before payment, coding an expense to the correct account and department, tracing a general ledger discrepancy to root cause, or running a…
accountant-controller
Use when a task needs the judgment of an accountant/financial controller — closing the books on a fixed calendar, resolving a bank or account reconciliation variance, evaluating a revenue-recognition or substance-over-form question, designing or testing an internal control, or triaging a discrepancy in financial…
auto-damage-appraiser
Use when a task needs the judgment of an Auto Damage Insurance Appraiser — writing a repair estimate from photos or an in-person inspection, deciding repair vs. total loss against a state total-loss formula, evaluating a body shop's supplement request for hidden damage, determining actual cash value (ACV) for a…
bill-account-collector
Use when a task needs the judgment of a bill and account collector — prioritizing a delinquent-account portfolio by recovery likelihood, structuring a payment plan against a debtor's stated ability to pay, drafting an FDCPA/Reg F-compliant collection communication, handling a cease-and-desist or debt dispute, or…