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 beel-es/claude-plugins --skill upgradegit clone --depth 1 https://github.com/beel-es/claude-pluginsWrote 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/beel-es/claude-plugins/upgrade)<a href="https://agentmods.dev/skills/beel-es/claude-plugins/upgrade"><img src="https://agentmods.dev/badge/skills/beel-es/claude-plugins/upgrade/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/beel-es/claude-plugins/upgrade"><img src="https://agentmods.dev/badge/skills/beel-es/claude-plugins/upgrade.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 | $0.00066 | $0.02084 |
| Opus 5.5 | $0.00026 | $0.00834 |
| Sonnet 5.5 | $0.00013 | $0.00417 |
| Haiku 4.5 | $0.00007 | $0.00208 |
Grade A, and why
upgrade scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://docs.beel.es/api/changelog # every entry as JSON, newest first How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BeeL. Integration Upgrade Check
Read what changed, find what the project does today, propose the migration. Report first — only modify code if the user asks.
The order matters: the changelog tells you what moved and what it became, the project tells you where. Doing it the other way round produces a list of endpoints with no idea which ones are a problem.
Procedure
1. Read what changed
Start with the changelog feed. It is one surface: the small entries and the big migrations live in the same stream, newest first. The migrations that can break you carry note: true and have a page of their own — route-by-route old→new tables, sunset calendars, and the traps where the successor is not a drop-in.
curl -s https://docs.beel.es/api/changelog # every entry as JSON, newest first
The response is { "entries": [ … ] }. Read the note: true ones first — those are the migrations; the rest are usually additions. Per entry, the fields worth reading:
| Field | What you get from it |
|---|---|
date, title, slug, url |
Identity, and the page to cite in the report. url is already resolved: /changelog/<slug> for a migration, /changelog#<slug> for a short entry |
note |
true = big migration with its own page. Start here |
breaking |
Whether this one can break the project at all |
breakingChanges[] |
Read every one. Prose, one entry per thing that breaks — this is where semantic changes hide |
endpoints[] |
{method, path, description} for the routes the entry adds or touches — carried by about half the current entries, and usually the fastest thing to grep the project for |
routeMigration.groups[].rows[] |
The equivalence table: methods, path (old), successor (new — absent, or status: "removed", means no replacement), note |
timeline.phases[], timeline.ifYouDoNotMigrate |
When the old way stops answering and what happens then |
audience.checks[] |
Concrete checks BeeL. itself suggests — usually greps and headers. Run them |
highlights[], links[] |
Non-breaking additions, and where to read more |
assistant |
Guidance BeeL. wrote for this exact job, when the entry carries it |
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 First seen · 113 lines · 66 tokens per session scan A 6cd95ba35b7c
upgrade is a skill published in the GitHub repository beel-es/claude-plugins (4 stars, last pushed 11d ago), licensed MIT. It adds 66 tokens to every session and 2,084 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
liter-llm-running-the-proxy
Use when running the liter-llm api OpenAI-compatible gateway — virtual keys, per-key rate limits, budgets, cost tracking, and model routing. Covers the TOML config and the 22 REST endpoints.
payment-integration
Stripe, RevenueCat, subscription billing, webhooks, PCI compliance, and tax. Use when integrating payments or subscriptions, handling payment webhooks, or reviewing billing and PCI scope.
bitcoin-infrastructure-electrs
Electrs: Roman Zeyde's Electrum-protocol indexer in Rust. Lightweight, serves Electrum clients; BIP157 filter scan stays on Bitcoin Core. USE WHEN: deploying personal Electrum server, integrating LN with Electrum backend, evaluating indexers.
bitcoin-infrastructure-esplora
Esplora: Blockstream's HTTP-based block explorer + indexer. REST API at /api/ . Powers blockstream.info, mempool.space's earlier versions, and self-hosted explorers. USE WHEN: deploying a personal block explorer, integrating with Esplora REST API, building wallet / monitoring on Esplora-style endpoint.
bitcoin-infrastructure-fulcrum
Fulcrum: Calin Culianu's Electrum-protocol indexer in C++. Faster than electrs for high-volume queries. Serves Electrum clients + LN nodes. USE WHEN: deploying high-load Electrum server, comparing with electrs.
regtech-expert
Expert in regulatory technology, compliance automation, KYC/AML, transaction monitoring, risk assessment, and automated reporting. Use when the user mentions compliance, KYC, AML, transaction monitoring, risk assessment, or regulatory reporting, or when the task involves KYC/AML Compliance, KYC/AML Program, Regulatory…