agentmods.dev

totvs-tickets-mcp: Instructions file for Claude Code

CLAUDE.md

totvs-tickets-mcp CLAUDE.md is an instructions file for Claude Code from Guipegoraro/totvs-tickets-mcp. It costs 2,270 tokens per session, scanned A, original, MIT.

Repository instructions for working on a local Python server that lets an AI read TOTVS customer-support tickets. TOTVS is a business software company, and the server exposes its support portal without allowing changes.

In plain words
What is it for?
Use them when developing, reviewing, or operating the ticket-reading server, especially when handling login recordings, cached credentials, support-ticket tools, or undocumented status codes.
Why use it?
They document the project structure and important safety rules, including that login recordings can contain passwords and that uncertain meanings in portal data must not be treated as facts.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Guipegoraro/totvs-tickets-mcp's own configuration. It tells Claude Code how to work on totvs-tickets-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything totvs-tickets-mcp configures →

not rated 0repo 2mo ago A scan 2,270 tokens original MIT
View source ↗ Guipegoraro/totvs-tickets-mcp
Reuse

Borrowing it

Nothing to install: this file belongs to Guipegoraro/totvs-tickets-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Guipegoraro/totvs-tickets-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Guipegoraro/totvs-tickets-mcp

Made for: Claude Code.

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 totvs-tickets-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/guipegoraro/totvs-tickets-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/guipegoraro/totvs-tickets-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/guipegoraro/totvs-tickets-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/guipegoraro/totvs-tickets-mcp/claude-md/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.

agentmods 80×15 button for totvs-tickets-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/guipegoraro/totvs-tickets-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/guipegoraro/totvs-tickets-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,270 This file is loaded in full into every session.
When invoked 2,270 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02270 $0.02270
Opus 5 $0.01135 $0.01135
Sonnet 5 $0.00454 $0.00454
Haiku 4.5 $0.00227 $0.00227

Measured 9d ago against content hash 0952e0762d27, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

totvs-tickets-mcp CLAUDE.md 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 9d 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.

CLAUDE.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guia pra Claude Code trabalhando neste repositorio.

O que e este projeto

MCP server local em Python que expoe os tickets de suporte da TOTVS (Portal do Cliente, suporte.totvs.com) como tools read-only pra LLMs. Mesmo molde do tspace-mcp (keyring, cache cifrado com Fernet, headers de browser).

Read-only e escopo deliberado. Nao ha tools de escrita. Se um dia houver, elas exigem autorizacao expressa por chamada (padrao do tspace) e revisao antes.

⚠ Regra de seguranca: HAR do login vaza a senha

O POST /api/auth/v1/login do Fluig manda a senha em texto puro no body (password=...). Qualquer HAR que capture o login contem a senha em claro.

  • Nunca commitar .har (ja no .gitignore).
  • Ao pedir HAR pro usuario, avisar pra trocar a senha depois / apagar o .har.
  • Preferir o totvs-tickets-probe (nao grava nada, redige segredos) a pedir HAR.

⚠ Hipotese vs fato (load-bearing)

O portal retorna varios codigos/enums sem dicionario (status como new_open_hold, flags de organizacao). Ao inferir significado sem evidencia (HAR, doc oficial, observacao reproduzivel), trate como hipotese — nao afirme ao usuario nem codifique como verdade em docstring/pos-processamento.

Codigos com semantica observada (mas confirmar via tool quando possivel):

  • Status de ticket (filtro): new_open_hold=Aberto, pending=Pendente cliente, solved=Validacao cliente. Lista oficial: totvs_tickets_status.

Arquitetura

Cliente MCP (stdio) <-> server.py <-> TotvsTicketsClient (client.py) <-> HTTPS
                                             |
                     keyring do OS (user/senha/seed TOTP)  +  cache Fernet do token de 13h

Fluxo de auth (essencial pra debug) — client.py _run_saml_login

SP-initiated SAML com MFA/TOTP. 7 passos, um cookie jar httpx compartilhado:

  1. GET suporte.totvs.com/.../dashboard/tickets -> HTML com form auto-post (SAMLRequest).
  2. POST esse form ao Fluig (cloudpass/.../receiveSSORequest) -> 302 com samlRequestId no forward.
  3. POST /api/auth/v1/login (domain=totvs, grant_type=password, user, senha, captchaReturnedValue="") -> 403 + mfa_token.
  4. POST /api/auth/v1/token (grant_type=http://fluigidentity.com/api/mfa/totp, mfa_token, totp_token) -> 200, sessao Fluig (cookies).
  5. GET receiveSSORequest?samlRequestId=X -> HTML com form auto-post (SAMLResponse).
  6. POST suporte.totvs.com/portal/idp/ACS (SAMLResponse, RelayState) -> 302, sessao do portal (cookies).
  7. GET .../portal/jwt/create -> token (JWT Zendesk HS256, ~13h). Cacheado cifrado.

Read the full file on GitHub · 147 lines

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. 9d ago First seen · 147 lines · 2,270 tokens per session scan A 0952e0762d27

Subscribe to this mod's changes

totvs-tickets-mcp CLAUDE.md is an instructions file published in the GitHub repository Guipegoraro/totvs-tickets-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 2,270 tokens to every session, about $0.0113 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.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens