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 JOSETRA44/BCRP-mcp --skill bcrpgit clone --depth 1 https://github.com/JOSETRA44/BCRP-mcpWrote 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/josetra44/bcrp-mcp/bcrp)<a href="https://agentmods.dev/skills/josetra44/bcrp-mcp/bcrp"><img src="https://agentmods.dev/badge/skills/josetra44/bcrp-mcp/bcrp/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/josetra44/bcrp-mcp/bcrp"><img src="https://agentmods.dev/badge/skills/josetra44/bcrp-mcp/bcrp.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 | $0.00225 | $0.02125 |
| Opus 5 | $0.00112 | $0.01063 |
| Sonnet 5 | $0.00045 | $0.00425 |
| Haiku 4.5 | $0.00022 | $0.00213 |
Grade A, and why
bcrp 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 11d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BCRP — Peruvian central bank economic data
BCRPData is the open statistics database of Peru's central bank. It is fully public — no API key, no account, no rate limit to negotiate. This skill covers how to pull data from it reliably and how to avoid the handful of quirks that silently produce wrong answers.
Which interface to use
The same functionality is exposed two ways, backed by identical code:
- MCP tools (
bcrp_get_series,bcrp_get_latest, …) — use these when thebcrpMCP server is connected. Preferred: structured data comes straight back to you. bcrpCLI — use when there is no MCP server but the command exists in the shell. Add--jsonto any data command to get the exact same payload the MCP tool returns, which is what you want when you plan to parse it.
Check which is available before planning a multi-step analysis. If neither exists, the
underlying API is a plain public GET — see references/api.md to call it directly.
| Task | MCP tool | CLI |
|---|---|---|
| Historical range | bcrp_get_series |
bcrp series get CODE --start P --end P |
| Current values | bcrp_get_latest |
bcrp series latest CODE --n 5 |
| Verify a code / date range | bcrp_describe_series |
bcrp series describe CODE |
| Find a code by keyword | bcrp_search_catalog |
bcrp catalog search "query" |
| Browse categories | bcrp_list_catalog_categories |
bcrp catalog categories |
| Everything at once | bcrp_get_macro_snapshot |
bcrp macro snapshot |
Core workflow
- Find the code. Search the catalog by keyword rather than guessing a code —
invented codes fail with a "not found" error, and the code format (
PD04637PD) is not guessable. The catalog covers ~35 of the most-used series; the full database has 8,000+ monthly, 2,700+ quarterly and 800+ daily series browsable at https://estadisticas.bcrp.gob.pe/estadisticas/series/. - Describe before fetching a long range.
describereturns the frequency and the real first/last available period without pulling every data point. This tells you which period format to use and stops you requesting years that don't exist. - Fetch. Use
latestfor "what is it now",getwith a range for history. - Report the period alongside the value. These series are revised and published on a lag; a number without its period is not a usable answer.
What ships with it
2 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.
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.
- 11d ago First seen · 158 lines · 225 tokens per session scan A 41435abefc2b
bcrp is a skill published in the GitHub repository JOSETRA44/BCRP-mcp (0 stars, last pushed 15d ago), licensed MIT. It adds 225 tokens to every session and 2,125 once invoked, about $0.0011 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 2026-08-31.
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.