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/bankbridge-money/bankbridge-pluginWrote 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/commands/bankbridge-money/bankbridge-plugin/category-deep-dive)<a href="https://agentmods.dev/commands/bankbridge-money/bankbridge-plugin/category-deep-dive"><img src="https://agentmods.dev/badge/commands/bankbridge-money/bankbridge-plugin/category-deep-dive/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/commands/bankbridge-money/bankbridge-plugin/category-deep-dive"><img src="https://agentmods.dev/badge/commands/bankbridge-money/bankbridge-plugin/category-deep-dive.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 | $0.00022 | $0.00385 |
| Opus 5.5 | $0.00009 | $0.00154 |
| Sonnet 5.5 | $0.00004 | $0.00077 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
category-deep-dive 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 1mo 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.
What it actually says
You have access to BankBridge MCP tools. The user wants to zoom in on ONE category.
$ARGUMENTS should be the category name (BankBridge uses uppercase underscore names like FOOD_AND_DRINK, TRANSPORTATION, GENERAL_MERCHANDISE). If the user typed a friendly name ("food", "restaurants", "groceries") map it to the closest category. If unclear, run list_categories first and ask which they meant.
Window: default last 90 days, or honor anything in $ARGUMENTS ("last 6 months", "this year", "march").
Steps:
- Call
list_categoriesif needed to confirm the category exists in the user's data. - Call
list_transactionswithcategory: "<CATEGORY>", the resolved date range,limit: 200. - Aggregate: total, transaction count, average, median, largest, most frequent merchant, top 5 merchants.
- Compute weekly cadence (transactions per week over the window).
Output:
🔎 <CATEGORY> — <window>
Total: $ X
Count: N
Average: $ X.XX
Median: $ X.XX
Largest: $ X at <merchant> on <date>
Most frequent: <merchant> (N times)
Top 5 merchants
<merchant> $ X (N)
...
Weekly cadence: N.N transactions / week
Full list (date — merchant — amount)
<date> <merchant> $ X
...
If more than 50 transactions, show the top 25 by amount in the full list and note the total count.
Relay any warnings above the output.
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.
- 1mo ago Changed f5af62adf95b
- 2mo ago First seen · 43 lines · 22 tokens per session scan A 7526e60bb900
category-deep-dive is a command published in the GitHub repository bankbridge-money/bankbridge-plugin (2 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 385 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
search-flights
Search award flight availability across airlines.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.