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 mercadopago/mercadopago-claude-marketplace --skill mp-reviewgit clone --depth 1 https://github.com/mercadopago/mercadopago-claude-marketplaceWrote 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/mercadopago/mercadopago-claude-marketplace/mp-review)<a href="https://agentmods.dev/skills/mercadopago/mercadopago-claude-marketplace/mp-review"><img src="https://agentmods.dev/badge/skills/mercadopago/mercadopago-claude-marketplace/mp-review/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/mercadopago/mercadopago-claude-marketplace/mp-review"><img src="https://agentmods.dev/badge/skills/mercadopago/mercadopago-claude-marketplace/mp-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 87 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00040 | $0.02802 |
| Opus 5 | $0.00020 | $0.01401 |
| Sonnet 5 | $0.00008 | $0.00560 |
| Haiku 4.5 | $0.00004 | $0.00280 |
Grade A, and why
mp-review 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 12d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mp-review
This skill audits a Mercado Pago integration. The security floor is evaluated locally. Official quality criteria are pulled live only when an MCP-backed scope reaches that step.
Step 0 — Connect only for the MCP-backed review step
Do not inspect MCP state when the review starts. Discover the integration and run all requested local checks first.
| Review operation | MCP required? | Tool |
|---|---|---|
Security floor (scope=security) |
No | — |
| Code discovery and legacy detection | No | — |
| Official quality checklist | Yes | quality_checklist |
| Payment-level quality evaluation | Yes | quality_evaluation |
| Get or submit homologation form | Yes | form_homologation |
Immediately before an MCP-backed operation:
- Attempt the intended tool directly if callable. Never call
application_listmerely to test the connection. - If it is unavailable or returns an authentication error, call
mcp__plugin_mercadopago_mcp__authenticateand show the OAuth link in the developer's language. - Instruct the developer to Cmd+Click (Mac) or Ctrl+Click (Windows/Linux), without copying the URL into an external browser.
- When the developer returns, retry the intended tool directly. Never request the callback URL.
- After two authentication failures, continue with completed local checks and mark the MCP-backed section as not verified.
Step 1 — Discover the integration
Use Grep/Glob to find:
- Files importing
mercadopago(any SDK). - References to
MP_ACCESS_TOKENor hardcodedAPP_USR-/TEST-strings. - Endpoint patterns:
/v1/payments,/checkout/preferences,/v1/orders,payment.create,preference.create,order.create,preapproval.create,disbursement. - Webhook handlers (paths matching
webhook,notification,ipn).
Determine:
- API in use: Payments API (
/v1/payments) vs Orders API (/v1/orders). Both can coexist.- If the integration uses legacy Instore APIs, it is on the legacy path. Always include a
Needs attentionitem in the Implementation Report with the file:line, and suggest the migration command: "Run/mp-integrate migrateto automate the migration to the Orders API." Do not treat it as a Blocker (existing code still works), but flag it as forward-looking technical debt. Legacy Instore patterns to flag:/mpmobile/instore/qr(QR Instore)/instore/qr/seller/collectors(QR Instore V2)/instore/orders/qr/seller/collectors(QR Dinámico)/point/integration-api/devices/{id}/payment-intents(Point)
- If the integration uses
/v1/payments(Online): flag as technical debt if it is a server-side card payment (Checkout API / Marketplace). Do not suggest/mp-integrate migratefor Online — migration for those products is out of scope for this plugin. - Exception 1: Checkout Pro stays on preferences (the Orders API does not exist for Checkout Pro). Do not flag
/checkout/preferencesas legacy. - Exception 2: Bricks uses
/v1/paymentscorrectly (server-side afterCardPaymenttokenization). Do not flag/v1/paymentscalls in files that also containCardPaymentoronSubmitas legacy.
- If the integration uses legacy Instore APIs, it is on the legacy path. Always include a
- Products in use: Checkout Pro/API, Bricks, Subscriptions, Marketplace, etc. — derive from endpoint patterns and request payloads.
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.
- 12d ago First seen · 225 lines · 40 tokens per session scan A c1e222757852
mp-review is a skill published in the GitHub repository mercadopago/mercadopago-claude-marketplace (26 stars, last pushed 8d ago), licensed Apache-2.0. It adds 40 tokens to every session and 2,802 once invoked, about $0.0002 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.
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.