Borrowing it
Nothing to install: this file belongs to giltiq/giltiq-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.
curl -O https://raw.githubusercontent.com/giltiq/giltiq-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/giltiq/giltiq-mcpWrote 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/instructions/giltiq/giltiq-mcp/agents-md)<a href="https://agentmods.dev/instructions/giltiq/giltiq-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/giltiq/giltiq-mcp/agents-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.
<a href="https://agentmods.dev/instructions/giltiq/giltiq-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/giltiq/giltiq-mcp/agents-md.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 | $0.00424 | $0.00424 |
| Opus 5.5 | $0.00170 | $0.00170 |
| Sonnet 5.5 | $0.00085 | $0.00085 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
giltiq-mcp AGENTS.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 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.
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.
What it actually says
giltiq-mcp — Agent Rules
Client-side MCP server for the Giltiq VAT validation API, published as @giltiq/mcp on npm. Stdio transport only: an MCP host (Claude Desktop, Cursor, Claude Code) launches it as a subprocess on the user's machine and it calls api.giltiq.de over HTTPS like any REST client. No server-side infrastructure.
- Exposes the same tool set as the hosted
giltiq-mcp-server(mcp.giltiq.de): validate, status, usage, register, plus qualified-confirmation and receipt retrieval. The two repos are kept in lockstep; neither supersedes the other (DECISIONS.md, DECISION-007 in the workspace root). - TypeScript ESM, Biome (tabs), Vitest (
npm test). Quality gates before commit:npx biome check .,npm run build,npm test. - Agent commits:
agent: <type>(<scope>): <description>. - Workspace-wide rules (protected paths, production SSH freeze, API-parity pre-flight) live in
../CLAUDE.mdand../giltiq-agent/CLAUDE.md.
Project memory (Hindsight)
This repo is scoped to the shared giltiq Hindsight bank (see .pi/hindsight.json), which holds both engineering context and company strategy (business plan, DECISIONS.md, hypotheses, gate state). Before scouting the codebase or re-deriving architecture, check the hindsight_knowledge tool (action "search" or "tree", then "get") for existing pages — component map, core concepts, conventions, key decisions, initiatives. They refresh automatically from project memory. Use hindsight_recall for dated facts (what was decided when, what shipped vs. what a card claims). When you learn something durable — a decision, a root cause, an incident, a market signal — retain it with hindsight_retain and name the source.
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 · 14 lines · 424 tokens per session scan A 70f3d39bf36e
giltiq-mcp AGENTS.md is an instructions file published in the GitHub repository giltiq/giltiq-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 424 tokens to every session, about $0.0017 per session on Opus 5.5. 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 2026-09-09.
giltiq-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| giltiq-mcp AGENTS.mdgiltiq/giltiq-mcp | Instructions file | 0 | 1mo ago | MIT | A | 424 | Codex, OpenCode |
| vibetags com-example-service-EvidenceBasedShowcase.instructions.mdPIsberg/vibetags | Instructions file | 25 | yesterday | MIT | A | 443 | GitHub Copilot |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |