bookkeeper-starter: Skill for Claude Code

.claude/skills/bk-import/SKILL.md

bk-import is a skill for Claude Code from audrey-560/bookkeeper-starter. It costs 63 tokens per session (519 once invoked), scanned A, original, MIT.

A skill for importing a bookkeeper client's waiting financial statements and checking whether transaction records cover the expected period. It normalizes duplicates and reports missing files without writing to the ledger.

In plain words
What is it for?
Use it to scan an inbox folder, fetch supported bank statements, import and deduplicate transactions, check coverage, and explain which statements are still needed.
Why use it?
It turns scattered statement files and available bank data into a clear import report and identifies the smallest remaining manual task.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: positional $N argument.

This is audrey-560/bookkeeper-starter's own configuration. It tells Claude Code how to work on bookkeeper-starter itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bookkeeper-starter configures →

Reuse

Borrowing it

Nothing to install: this file belongs to audrey-560/bookkeeper-starter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/audrey-560/bookkeeper-starter/main/.claude/skills/bk-import/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/audrey-560/bookkeeper-starter

Made for: Claude Code.

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.

agentmods badge for bk-import

README.md
[![agentmods](https://agentmods.dev/badge/skills/audrey-560/bookkeeper-starter/bk-import/github.svg)](https://agentmods.dev/skills/audrey-560/bookkeeper-starter/bk-import)
Your own site
<a href="https://agentmods.dev/skills/audrey-560/bookkeeper-starter/bk-import"><img src="https://agentmods.dev/badge/skills/audrey-560/bookkeeper-starter/bk-import/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.

agentmods 80×15 button for bk-import

Your own site · 80×15
<a href="https://agentmods.dev/skills/audrey-560/bookkeeper-starter/bk-import"><img src="https://agentmods.dev/badge/skills/audrey-560/bookkeeper-starter/bk-import.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 519 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.00519
Opus 5 $0.00032 $0.00260
Sonnet 5 $0.00013 $0.00104
Haiku 4.5 $0.00006 $0.00052

Measured 9d ago against content hash 34457f8feaf3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

bk-import 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 9d 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.

.claude/skills/bk-import/SKILL.md · 42 lines

What it actually says

What This Skill Does

Turns "files in a folder" into recorded, deduplicated, coverage-checked transactions — and tells the user the smallest remaining manual action, with per-institution download instructions. Local-state only (no ledger writes), so it's safe to run any time.

Steps

  1. cd to the project root. Client = $1 or the default client; pass --client <slug> everywhere for any other client.
  2. API pulls first: for accounts with "acquisition": "api" in the profile (e.g. Wise): python3 tools/fetch_wise_statement.py [--month YYYY-MM].
  3. Scan the inbox: python3 tools/import_statement.py --scan-inbox — per file: adapter detection, wrong-account guard, hash dedupe, import-ledger record; ingested files move to inbox/processed/.
  4. Coverage report: python3 tools/coverage_check.py (add --period YYYY-MM if the user named a month; --online to also compare ledger cash vs statement closing balances).
  5. Report to the user:
    • what was ingested (account, txn count, date range, duplicates skipped)
    • files that failed and why (wrong account? unreadable? → fix or map)
    • remaining gaps/stale accounts, each with its exact next action: the institution card from institutions/<inst>/instructions.md, the account, and the date range to download
  6. If everything is covered, suggest the natural next step: /monthly-close for the period, or resolving open exceptions (python3 tools/exceptions_queue.py list).

Guardrails

  • Never edit or delete a statement file; failed files stay in inbox/ untouched.
  • A 0-transaction parse is treated as a wrong-account/wrong-currency signal, not success — nothing is recorded and the user is told.
  • This skill never writes to Google Sheets.
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. 9d ago First seen · 42 lines · 63 tokens per session scan A 34457f8feaf3

Subscribe to this mod's changes

bk-import is a skill published in the GitHub repository audrey-560/bookkeeper-starter (13 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 519 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.

Related

Other skills, from other repositories