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.
npx agentmods add instructions/adikant/datalens-dev-mcp/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.svg" alt="Measured on agentmods" 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 | $0.01000 | $0.01000 |
| Opus 5 | $0.00500 | $0.00500 |
| Sonnet 5 | $0.00200 | $0.00200 |
| Haiku 4.5 | $0.00100 | $0.00100 |
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 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Scope
This repository contains the local datalens-dev-mcp Python MCP stdio server.
The server is a client-independent MCP interface for DataLens dashboard development: object discovery, planning, validation, guarded save and publish, project workflows, visual QA, diagnostics, and operator context. It runs locally and can be connected to Codex, Claude, or another MCP client.
Read Order
AGENTS.mdREADME.mdREADME_en.mddocs/README.mddocs/access.mddocs/codex_setup.mddocs/usage-flow.mddocs/configuration.mddocs/local-only-safety-model.mddocs/route-policy.mddocs/safe-apply.mddocs/tools.mddocs/mcp/tools.mddocs/mcp/response_contracts.mddocs/sources.mddocs/source_provenance.mddocs/autonomous-workflow.mddocs/project-journal.mddocs/portfolio-style-registry.mddocs/data-validation.mddocs/evidence-levels.mddocs/migration-v1-to-v2.md
Local Material Policy
- Runtime behavior lives in MCP code, configs, schemas, templates, examples, tests, and distilled documentation.
- Raw source corpora, long copied pages, course or book extracts, and complete extraction artifacts do not belong in the tracked repository.
- Keep compact attributable registries, distilled rules, schemas, templates, curated examples, and tests.
- Never commit IAM tokens, env files, live authorization headers, passwords, private keys, or other credential material.
Public Change Hygiene
- Treat commit messages, pull requests, issues, release notes, and review replies as public product documentation.
- Describe generic capabilities, contracts, and synthetic test evidence only.
- Do not name private dashboards, workbooks, customers, internal projects, source logs, local absolute paths, or live object IDs.
- State the product change directly. Do not narrate private-source handling, sanitization work, or removed internal material.
- Use a public-safe author identity for commits and verify commit and pull-request metadata before publishing; do not expose an employer or private email address.
- Run the public-release, sensitive-artifact, and repository-size gates before publishing.
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 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 (4 stars, last pushed 5d ago), licensed Apache-2.0. It adds 1,000 tokens to every session, about $0.0050 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.
Other instructions, from other repositories
printyourduck-mcp AGENTS.md
AGENTS.md instructions for printyourduck/printyourduck-mcp, covering agent guide, product boundary, commands, repo ownership and release truth.
bizinsight-agent AGENTS.md
Instructions for sAjAd-2006/bizinsight-agent, covering agents.md — bizinsight agent project context, project overview, stack, project conventions and spec-driven development (day 5).
homelab-asset-db-mcp CLAUDE.md
Claude Code instructions for McCavity/homelab-asset-db-mcp, covering homelab-asset-db-mcp — conventions for ai agents, what this project is, key design choices, parser contract and coding conventions.
context-usage-mcp AGENTS.md
AGENTS.md instructions for beeltec/context-usage-mcp, covering agent guidelines, project wiki, when to consult it, when to update it and how to update it.
wikipedia-mcp-server AGENTS.md
AGENTS.md instructions for cyanheads/wikipedia-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.
wikipedia-mcp-server CLAUDE.md
Claude Code instructions for cyanheads/wikipedia-mcp-server, covering developer protocol, what's next?, core rules, patterns and tool.