Borrowing it
Nothing to install: this file belongs to ADIKANT/datalens-dev-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/ADIKANT/datalens-dev-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/ADIKANT/datalens-dev-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/adikant/datalens-dev-mcp/agents-md)<a href="https://agentmods.dev/instructions/adikant/datalens-dev-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/adikant/datalens-dev-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/adikant/datalens-dev-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/adikant/datalens-dev-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 | $0.00630 | $0.00630 |
| Opus 5.5 | $0.00252 | $0.00252 |
| Sonnet 5.5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
datalens-dev-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.
How it starts
The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository owns the local datalens-dev-mcp Python stdio server.
Ordinary dashboard work
- Work from the exact dashboard project or subproject root. Use its local context; do not substitute the server repository.
- Use the installed DataLens domain skills and typed public tools. Do not read server source or run server tests for an ordinary dashboard request.
- Use scoped API reads, save/readback, publish-from-saved, and published readback. When rendered evidence is required, use Browser read-only after API and applicable data checks.
- An explicit request authorizes its clear target, scope, and delivery steps. Show a compact plan for substantial changes and continue without repeated plan/save/publish questions. Read-only means no writes; save-only means no publish. Stop for an unresolved target, conflicting constraints, expanded scope, or a real access boundary.
- Scoped cleanup retains fresh dependency preview, exact machine
confirmed_delete, preserve checks, and readback. A clear request for those deletions is authorization; the machine scope is not proof of a new human reply. Reconcile preview drift and ask only if it creates a real scope conflict. - Preserve an existing object's technology. Use Wizard for new standard charts, Editor/JavaScript only by direct request or a documented gap, and QL only by direct request.
- Never guess IDs or expose secrets. Work on user-authorized DataLens objects within current technical rights, including working dashboards. A dashboard request does not authorize ACL changes, upstream production database writes, or changes to unowned objects.
- Distinguish a model question, native permission event, and automatic reviewer result.
outcome=allowis not a pending human prompt. Respect real host restrictions; do not change global approval settings or external skills to bypass them.
Server maintenance
- Read only the owners and documentation causally required for the defect. Preserve useful dirty work and keep raw corpora, sessions, runtime receipts, caches, credentials, and private object data out of Git.
- Keep one typed backend and the direct authoring/read/write services. Do not add a task compiler, journal/workflow, generic executor, or parallel runtime framework.
- Verify a real fail-before, apply one coherent owner fix, then run focused and affected tests. Do not run a full suite or build repeatedly while diagnosing.
- Treat commits, pull requests, issues, and release notes as public. Use generic behavior and synthetic evidence; never publish private names, IDs, prompts, local paths, or credential material.
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 Changed · +2 lines · +161 tokens per session 06805c994dff
- 1mo ago Changed · -19 tokens per session 19283ba7c338
- 1mo ago Changed · -47 lines · -512 tokens per session c40f6a07a5e0
- 2mo ago First seen · 73 lines · 1,000 tokens per session scan A c40c497f572c
datalens-dev-mcp AGENTS.md is an instructions file published in the GitHub repository ADIKANT/datalens-dev-mcp (7 stars, last pushed 11d ago), licensed Apache-2.0. It adds 630 tokens to every session, about $0.0025 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 2026-08-31.
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.