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 agentmods add skills/beel-es/claude-plugins/implementnpx skills add beel-es/claude-plugins --skill implementgit clone --depth 1 https://github.com/beel-es/claude-pluginsWhat 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 | $0.00059 | $0.01135 |
| Opus 5 | $0.00030 | $0.00567 |
| Sonnet 5 | $0.00012 | $0.00227 |
| Haiku 4.5 | $0.00006 | $0.00113 |
Grade A, and why
implement 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 2d 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.
| Node.js / TypeScript | **Official SDK** `@beel_es/sdk` — fetch the live SDK docs (find via `curl -s https://docs.beel.es/llms.txt \| grep -i sdk`) for the current API surface before writing SDK code | How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement a BeeL Integration
Build a correct BeeL API integration in the current project. Correct means: typed where possible, idempotent, retry-safe, envelope-aware, and validated against the live API reference — never against remembered schemas. The golden rules in the beel-api skill apply throughout.
Procedure
1. Detect the stack and choose the integration path
Inspect the project (package.json, pyproject.toml/requirements.txt, go.mod, …):
| Stack | Path |
|---|---|
| Node.js / TypeScript | Official SDK @beel_es/sdk — fetch the live SDK docs (find via curl -s https://docs.beel.es/llms.txt | grep -i sdk) for the current API surface before writing SDK code |
| Python | Typed client generated from the OpenAPI spec — see ../beel-api/recipes/typed-client.md |
| Anything else | Raw HTTP following the invariants in the beel-api skill |
If an integration already partially exists, extend it in its style rather than introducing a second client.
2. Scope the flows
If the user named a flow (e.g. "invoice my Stripe payments", "monthly recurring invoices"), implement that. If not, ask which flows they need rather than guessing — typical ones:
- Create + issue invoices (the core flow — see
../beel-api/recipes/invoice-flow.md) - Customer / product management or import (CSV, Holded)
- Recurring invoices
- Mark paid / send by email / PDF download
- Exports (Excel, bulk PDF)
- Webhook-driven reactions → hand off to
/beel-api:webhooks
3. Fetch the live reference for each flow
For every endpoint you are about to call, fetch its doc page (discover via https://docs.beel.es/llms.txt) or its OpenAPI definition. Field names, required fields and enums must come from the live spec — never invented.
4. Environment setup
- API key in
BEEL_API_KEYenv var; add to.env.example(placeholder only), never to committed files - Start against sandbox (
beel_sk_test_); make the production switch a deployment concern, not a code change - Base URL is always
https://app.beel.es/api— the key prefix selects the environment, there is no separate test URL. The/v1/belongs to the path, not to the base URL: every documented path already starts with it, so configuring a generated client with/api/v1produces/api/v1/v1/…and a uniform 404
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.
- 2d ago First seen · 74 lines · 59 tokens per session scan A 89942119dbf6
implement is a skill published in the GitHub repository beel-es/claude-plugins (4 stars, last pushed 6d ago), licensed MIT. It adds 59 tokens to every session and 1,135 once invoked, about $0.0003 per session on Opus 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
upgrading-golang
Upgrades Go version across the entire Chainloop codebase including source files, Docker images, CI/CD workflows, and documentation. Use when the user mentions upgrading Go, golang version, or updating Go compiler version.
custom-builtin-functions
Create a custom builtin function to be used in the Rego policy engine.
agt-policy-authoring
Create and validate a minimal AGT Copilot CLI policy tailored to the repository being inspected.
catalyst-center-readonly
Query Cisco Catalyst Center read-only — device inventory, site hierarchy, wireless, assurance health, compliance, software images, events. All 514 read-only API operations reachable through 8 grouped dispatchers. Use when asked what Catalyst Center manages, where a device sits, what its health or compliance state is…
aws-security-audit
AWS security auditing — IAM users/roles/policies, CloudTrail API events, security posture analysis. Use when auditing IAM permissions, investigating security incidents, checking MFA compliance, or tracing API activity in CloudTrail.
github-awesome-copilot-git-commit
Generate high-quality, atomic Conventional Commits by analyzing Git changes, recommending logical commit boundaries, validating commit messages, and assisting with PRs, changelogs, and releases.