Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add rossumai/claude-marketplace/plugin install rossum-saWrote 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/rossumai/claude-marketplace/b2brouter-reconciliation)<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/b2brouter-reconciliation"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/b2brouter-reconciliation/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/rossumai/claude-marketplace/b2brouter-reconciliation"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/b2brouter-reconciliation.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 | $0.00089 | $0.04350 |
| Opus 5 | $0.00044 | $0.02175 |
| Sonnet 5 | $0.00018 | $0.00870 |
| Haiku 4.5 | $0.00009 | $0.00435 |
Grade A, and why
b2brouter-reconciliation 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 7d 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
B2Brouter Reconciliation
Overview
Drives python3 ${CLAUDE_PLUGIN_ROOT}/skills/b2brouter-reconciliation/recon.py
to prove whether every invoice B2Brouter handed to an importer hook actually
landed in Rossum, exactly once. The CLI is deterministic; this skill supplies
the judgement it cannot encode — what the discovered scope means, when the
credentials are too weak to trust the report, and what an operator must never
do with the result. Full note taxonomy, all flags, and the CSV column list
live in reference.md next to this file — read that alongside this skill,
don't expect this document to restate it.
Never guess the target or hunt for credentials. Always ask the operator for the environment and token; never search the filesystem for them.
Credentials
Keys must never be pasted into this chat. Use the credentials file:
run --init-credentials, tell the operator to open the printed path
themselves and fill it in, then run normally with --credentials <path>
(or nothing, once a file exists at the default path — see below). The tool
never prints a token or key value back, in any message, at any point.
python3 ${CLAUDE_PLUGIN_ROOT}/skills/b2brouter-reconciliation/recon.py --init-credentials
This writes a template (owner-only permissions) to
~/.config/rossum-b2brouter-recon/credentials.json by default — deliberately
outside any repository, so a filled-in file can't be committed by accident —
and refuses to overwrite one that already exists. Tell the operator to paste
their Rossum token and B2Brouter key(s) into that file directly, in their own
editor, not into this conversation. Once it's filled in, every run picks it
up automatically (or point --credentials at a different path).
For each B2Brouter account group, that file needs a restricted API key
with accounts-read and invoices-read only — nothing else. B2Brouter keys
are scoped per account group, not per organization, so a real organization
normally supplies several keys, one per group, one entry per group under the
file's b2brouter.keys.
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- b2brouter.py 37 KB runs code
- credentials.py 9.7 KB runs code
- discovery.py 3.1 KB runs code
- match.py 14 KB runs code
- recon.py 67 KB runs code
- reference.md 47 KB
- rossum.py 15 KB runs code
- tests/conftest.py 235 B runs code
- tests/test_b2brouter.py 7.4 KB runs code
- tests/test_credentials.py 6.6 KB runs code
- tests/test_discovery.py 3.4 KB runs code
- tests/test_match.py 2.7 KB runs code
- tests/test_recon.py 11 KB runs code
- tests/test_rossum.py 4.4 KB runs code
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.
- 7d ago First seen · 299 lines · 89 tokens per session scan A f50f3b387663
b2brouter-reconciliation is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed yesterday), licensed MIT. It adds 89 tokens to every session and 4,350 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 2026-09-05.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.