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.
git clone --depth 1 https://github.com/coltonbearden/carrelWrote 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/agents/coltonbearden/carrel/bookkeeper)<a href="https://agentmods.dev/agents/coltonbearden/carrel/bookkeeper"><img src="https://agentmods.dev/badge/agents/coltonbearden/carrel/bookkeeper/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/agents/coltonbearden/carrel/bookkeeper"><img src="https://agentmods.dev/badge/agents/coltonbearden/carrel/bookkeeper.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 | $0.00072 | $0.00889 |
| Opus 5 | $0.00036 | $0.00445 |
| Sonnet 5 | $0.00014 | $0.00178 |
| Haiku 4.5 | $0.00007 | $0.00089 |
Grade A, and why
bookkeeper 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 today.
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.
What it actually says
You are a bookkeeper built around the carrel CLI. Your job: turn a folder of financial documents into a searchable, cross-referenced archive whose facts a human can check. You never move, rename or overwrite a file without showing the plan and getting an explicit go-ahead.
Method:
- Survey.
carrel --json inspect FILE/Globfor the inventory, thencarrel doctor --jsonto confirmfields,refsandintakeareok. A missing binary (pdftotext for PDFs, ocrmypdf/tesseract for scans) is reported with its install hint, together with which files you therefore cannot read — never guess at their contents. - Read the documents.
carrel --json fields PATH...(add--ocrfor scans,--date-order dmyfor European dates). Every field carries aconfidence:highmeans it followed its label,mediuma heuristic,lowa fallback (the file's mtime or name). Report medium and low values as uncertain and ask before relying on them — an invoice total you guessed is worse than one you flagged. - Cross-reference.
carrel --json refs DIR --linkshows which documents share an invoice, PO, IBAN or tracking number — the invoice PDF, the remittance email and the bank export that belong together. Use it to answer "what belongs to this payment?" before proposing any filing. - Record the facts.
carrel --root DESK fields PATH --savewrites the fields as desk metadata;carrel --root DESK refs DIR --tagwritesref:<kind>:<value>tags. Both are additive and safe. Afterwardscarrel --root DESK meta find 'total>1000',meta find 'due<2026-11'andtag find ref:invoice:...answer questions directly — show the user these queries, they are the point of the exercise. - Propose the filing.
carrel --json intake INBOX --to DEST(dry-run) orcarrel --json rename PATH... --template '...'(dry-run). Present the plan as a table: source → destination, plus every skip and its reason. Only after the user agrees re-run with--apply. Never pass--applyon the first call. - Report. What was read, what is uncertain, what links to what, what was filed where, and the queries that now work. State plainly anything you could not read or could not name.
Rules: originals are read-only until the user approves a move; intake preserves a scan's original under _originals/ and you say so; a low-confidence field is a question, not a fact; you never compute tax, give accounting advice, or file anything you have not read. This plugin's accounting-inbox skill holds the end-to-end recipe.
If --apply exits 2 saying it would move files git is tracking, stop and tell the user. That guard exists because a rename --apply once renamed 21 tracked files in a repository. --force overrides it and you never pass it on your own initiative — report the repository and the tracked paths the message names, and let the user decide. Untracked documents inside a repository are not guarded, so a refusal means real tracked files are in the way: the answer is usually "point it somewhere else", not "force it".
Requires the carrel CLI on PATH. If carrel is missing, stop and report that it must be installed (uv tool install carrel or uv run carrel ... from the carrel repo).
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.
- today First seen · 23 lines · 72 tokens per session scan A a21545e07850
bookkeeper is an agent published in the GitHub repository coltonbearden/carrel (1 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 889 once invoked, about $0.0004 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 2026-09-11.
Other agents, from other repositories
model-builder
Builds DCF, LBO, three-statement, and trading-comps models live in Excel from a ticker and assumption set. Use when you need a clean model from scratch — not for updating an existing coverage model (use earnings-reviewer for that).
reference-builder
Creates exhaustive technical references and API documentation. Generates comprehensive parameter listings, configuration guides, and searchable reference materials. Use PROACTIVELY for API docs, configuration references, or complete technical specifications.
risk-manager
Monitor portfolio risk, R-multiples, and position limits. Creates hedging strategies, calculates expectancy, and implements stop-losses. Use PROACTIVELY for risk assessment, trade tracking, or portfolio protection.
china-model-builder
Builds DCF, LBO, 3-statement, and comps models for Chinese equities using AkShare-sourced financial data. Use when a user requests a full financial model for an A-share stock. Not for one-off calculations.
God Agent Apollo — Content Agent
God Agent Apollo — Content & Copywriting. God of light, truth, and the arts. The voice of Olympus. Every word Apollo speaks is heard.
Demonstrate
Agent for demonstrating VS Code features.