audit

audit is a skill for Claude Code, Codex from beel-es/claude-plugins. It costs 66 tokens per session (760 once invoked), scanned A, original, MIT.

A report-only skill for checking a project's BeeL invoicing API integration against current requirements. BeeL is an invoicing service, and the review covers areas such as request deduplication, API-key security, errors, limits, webhooks, invoices, and outdated patterns.

In plain words
What is it for?
Use it to audit or review BeeL API code and receive findings with severity and suggested fixes. It refreshes relevant BeeL documentation before checking the code and does not modify files unless asked.
Why use it?
It finds integration mistakes that could cause duplicate requests, exposed credentials, rejected API calls, unverified webhook data, or incorrect invoice handling.

Skill for Claude CodeCodex

Part of the beel-api plugin — 6 skills, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add skills/beel-es/claude-plugins/audit
Any agent
npx skills add beel-es/claude-plugins --skill audit
Clone the repo
git clone --depth 1 https://github.com/beel-es/claude-plugins

Made for: Claude Code, Codex.

Or install beel-api, the plugin that ships this one along with the rest of its 6 skills, 1 MCP server.

Wrote 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.

agentmods badge for audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/beel-es/claude-plugins/audit.svg)](https://agentmods.dev/skills/beel-es/claude-plugins/audit)
Your own site
<a href="https://agentmods.dev/skills/beel-es/claude-plugins/audit"><img src="https://agentmods.dev/badge/skills/beel-es/claude-plugins/audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 760 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00066 $0.00760
Opus 5 $0.00033 $0.00380
Sonnet 5 $0.00013 $0.00152
Haiku 4.5 $0.00007 $0.00076

Measured 3d ago against content hash 5a6fa112c7c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit 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 3d 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.

The checklist in `checklist.md` (this folder) encodes the stable rules, but limits and details drift. Before auditing, fetch what's relevant to the code you find — discover pages via `curl -s https://docs.beel.es/llms.tx
plugins/beel-api/skills/audit/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BeeL Integration Audit

Audit the project's BeeL API integration code against the current rules and report findings with severity and proposed fixes. This is a report-only skill — do not modify code unless the user explicitly asks for fixes afterwards.

Procedure

1. Refresh the rules from live docs

The checklist in checklist.md (this folder) encodes the stable rules, but limits and details drift. Before auditing, fetch what's relevant to the code you find — discover pages via curl -s https://docs.beel.es/llms.txt | grep -i <topic>:

  • The idempotency guide — current header name and rules
  • The rate limits guide — current limits and headers
  • The webhook signature/deduplication pages — only if the project receives webhooks
  • The OpenAPI spec (https://docs.beel.es/api/openapi) — to confirm endpoints the project calls still exist

2. Locate the integration surface

Search the project for BeeL touchpoints (case-insensitive where sensible):

app.beel.es            # raw HTTP calls
@beel_es/sdk           # official SDK usage
Idempotency-Key        # manual idempotency (also matches legacy X- prefix)
BEEL_API_KEY           # env var convention
beel_sk_               # key prefix: hardcoded literals (instant CRITICAL) or auth code
X-API-Key              # not a BeeL header — a call sending it is unauthenticated, see checklist 2
BeeL-Signature / BeeL-Event-Id  # webhook handling

Map every file that calls the API, handles its responses, or receives its webhooks. If nothing is found, say so and stop — don't invent findings.

3. Run the checklist

Work through checklist.md category by category against the located code. For each check, record: pass / fail / not applicable, with file:line evidence for failures.

4. Report

Output a structured report:

  1. Summary — one paragraph: overall state, count of findings by severity
  2. Findings — ordered by severity (CRITICAL → HIGH → MEDIUM → LOW), each with:
    • What is wrong and where (file:line)
    • Why it matters (consequence: duplicate invoices, leaked key, rejected webhook…)
    • The concrete fix (code-level, ready to apply)
  3. Passed checks — brief list, so the user knows what was verified, not just what failed
  4. Not applicable — e.g. "no webhook receiver found, webhook checks skipped"

Read the full file on GitHub · 68 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 3d ago First seen · 68 lines · 66 tokens per session scan A 5a6fa112c7c5

Subscribe to this mod's changes

audit is a skill published in the GitHub repository beel-es/claude-plugins (4 stars, last pushed 8d ago), licensed MIT. It adds 66 tokens to every session and 760 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.

Related

Other skills, from other repositories

dora

Expert DORA (Regulation (EU) 2022/2554 — Digital Operational Resilience Act) compliance advisor for EU financial entities. Use this skill whenever a user asks about DORA compliance, ICT risk management frameworks, ICT incident classification or reporting, threat-led penetration testing (TLPT), ICT third-party risk…

Sushegaad/Claude-Skills-Governance-Risk-and-Compliance · 207 tokens

pci-compliance

Expert PCI DSS compliance advisor covering PCI DSS v4.0.1 (current) and v4.0. Use this skill whenever a user asks about PCI DSS, payment card security, cardholder data protection, CDE scoping, SAQ types (A, A-EP, B, B-IP, C, C-VT, P2PE, D), ROC, AOC, QSA assessments, ASV scans, merchant levels, service provider…

Sushegaad/Claude-Skills-Governance-Risk-and-Compliance · 191 tokens

product-architect

Complete product development system with 80 agents and 36 frameworks. Use when the user wants to build a product, write a PRD, plan an MVP or roadmap, design an app, research a market or check whether a feature already exists or is novel, do competitive analysis, run a security audit, build a financial model, plan…

ankitjha67/product-architect · 253 tokens

starknet-tongo

Confidential ERC20 payments on Starknet using Tongo protocol. Fund, transfer, withdraw, and rollover encrypted token balances with zero-knowledge proofs. Use when the user needs privacy-preserving transactions, confidential payments, encrypted balances, or auditable private transfers on Starknet.

keep-starknet-strange/starknet-agentic · 61 tokens

stp-automation

Measure and raise straight-through processing (STP) rates in securities operations through zero-touch, exception-based processing. Use when measuring STP rates and analyzing manual touchpoints in an existing process, replacing review-all workflows with exception-based processing, evaluating RPA vs API-based vs hybrid…

JoelLewis/finance_skills · 118 tokens

fee-billing

Build and manage advisory fee billing operations from fee schedule design through calculation, collection, revenue recognition, and compliance disclosure. Use when the user asks about tiered or breakpoint fee schedules, billing cycle configuration, AUM valuation for billing, direct-debit vs invoice collection, GAAP…

JoelLewis/finance_skills · 146 tokens