Borrowing it
Nothing to install: this file belongs to iseppo/e-arveldaja-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/iseppo/e-arveldaja-mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/iseppo/e-arveldaja-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/iseppo/e-arveldaja-mcp/agents-md)<a href="https://agentmods.dev/instructions/iseppo/e-arveldaja-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/iseppo/e-arveldaja-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/iseppo/e-arveldaja-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/iseppo/e-arveldaja-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 | $0.01310 | $0.01310 |
| Opus 5.5 | $0.00524 | $0.00524 |
| Sonnet 5.5 | $0.00262 | $0.00262 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
e-arveldaja-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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Codex Instructions for e-arveldaja-mcp
Project
This repository is e-arveldaja-mcp, a TypeScript MCP server for the Estonian e-arveldaja / RIK e-Financials REST API.
The actual git repo root is:
/home/seppo/Dokumendid/e_arveldaja/e-arveldaja-mcp
Do not treat /home/seppo/Dokumendid/e_arveldaja as the repo root for git, tests, builds, or diffs.
Domain reference lives in
CLAUDE.md. This file carries only the Codex-specific working conventions. For API endpoint semantics, accounting concepts, the D/C balance model, Estonian tax rules, tool-exposure flags, and the full OCR/untrusted-text sandbox policy, readCLAUDE.md— it is the single source of truth. Do not duplicate those facts here; updateCLAUDE.mdinstead.
How To Work Here
- Read the existing code before changing behavior. Prefer local patterns over new abstractions.
- Keep changes scoped to the user request. Do not rewrite unrelated accounting workflows or generated metadata.
- This project touches live accounting data. Preserve dry-run defaults, approval gates, audit logging, path validation, and untrusted-text sandboxing unless the user explicitly asks for a reviewed change. (Full rationale and the specific invariants are in
CLAUDE.md.) - Never commit credentials or local accounting inputs. In particular, do not add
.env,apikey*.txt, company exports, bank statements, receipts, or localaccounting-rules.mdunless the user explicitly asks and the file is safe. - Use
rg/rg --filesfor search. - Use
apply_patchfor manual edits. - If a command fails because of sandboxing or network restrictions, rerun with the proper approval request rather than working around it.
Verification
For normal code changes, run:
npm test
npm run typecheck:tests
npm run build
npm run test:integration
Test typing ratchet: npm run typecheck:tests also counts explicit any and untyped parseMcpResponse calls in
test sources (codes ANY / UNTYPED_PAYLOAD); they may only go down. Parse tool payloads with
parseToolPayload<T>() from src/__fixtures__/mcp-response.ts, where T is the payload type the producing
presenter exports. After removing loose typing, run npm run typecheck:tests:update.
A change that alters a tool's output shape also exports or updates that payload's type (in the producing
presenter/tool module) in the same commit, so producer types appear where output changes, not only where tests are added.
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.
- 4d ago Changed · +8 lines · +161 tokens per session 1fc5b583a5f5
- 2mo ago First seen · 81 lines · 1,149 tokens per session scan A e46d4230a384
e-arveldaja-mcp AGENTS.md is an instructions file published in the GitHub repository iseppo/e-arveldaja-mcp (39 stars, last pushed today), licensed Apache-2.0. It adds 1,310 tokens to every session, about $0.0052 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 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.