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 skills add ADIKANT/datalens-dev-mcp --skill datalens-inspectgit 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/skills/adikant/datalens-dev-mcp/datalens-inspect)<a href="https://agentmods.dev/skills/adikant/datalens-dev-mcp/datalens-inspect"><img src="https://agentmods.dev/badge/skills/adikant/datalens-dev-mcp/datalens-inspect/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/skills/adikant/datalens-dev-mcp/datalens-inspect"><img src="https://agentmods.dev/badge/skills/adikant/datalens-dev-mcp/datalens-inspect.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 | $0.00047 | $0.00643 |
| Opus 5.5 | $0.00019 | $0.00257 |
| Sonnet 5.5 | $0.00009 | $0.00129 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
datalens-inspect 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 22d 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DataLens Inspect
Start from the exact project and target URL or ID. Reuse its configured installation, API endpoint and organization; consult installation and interfaces when those are unclear or the request concerns SDK scripting. Read only dependencies needed for the question. Reuse already established runtime identity; SDK documentation is needed only for an unknown contract or changed version, not after each call. A metadata audit needs neither new project files nor an SDK bootstrap; a legacy manifest is not required.
For a known target confirmed by the current project and API, read that object and only the bindings needed for the question. A workbook URL alongside an exact dashboard/chart ID does not require another workbook card or inventory. Use the workbook's card and paginated inventory when selecting an unknown target, discovering a requested set or proving completeness/absence. Retain the returned completeness boundary; absence from a partial listing proves nothing. Classify actual type/subtype and renderer metadata, distinguishing Wizard, Editor, QL and HTML Page; resolve unknown subtypes with addressed reads. Project examples and browser tabs cannot replace the requested container.
Use direct reads for tool selection, compact projections, pagination and completeness. Distinguish saved and published branches, target and reference, source/static validation and live data or Browser evidence. A rendered-result request can use read-only Browser inspection after scoped API and applicable data checks.
For HTTP 429 follow rate-limit recovery, retaining the same payload and bounded read scope.
For token renewal or a credential failure, follow authentication recovery: dl_auth_refresh supports the existing profile's external-browser sign-in. A noninteractive timeout alone is not a login prohibition.
For cloud identity lookup load RLS resolution. For changes route to datalens-dataset-wizard, datalens-editor or datalens-dashboard; backup, standalone HTML Page and cleanup belong to datalens-maintenance. Load only the addressed reference.
Upstream provenance records the selectively adapted sources; load it only for a version/provenance question.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 22d ago Changed · +4 lines 975f94af1cd6
- 1mo ago Changed · +2 lines 59e2bbd740fb
- 1mo ago Changed · +2 lines ca6885d22499
- 1mo ago Changed aace80c91c85
- 1mo ago Changed · +2 lines 6296eb22f59d
- 1mo ago Changed · +2 lines · +15 tokens per session 267b0f3a8921
- 1mo ago Changed · +2 lines 18c03969dc86
- 1mo ago First seen · 11 lines · 32 tokens per session scan A c95c9f3edf1e
datalens-inspect is a skill published in the GitHub repository ADIKANT/datalens-dev-mcp (7 stars, last pushed 11d ago), licensed Apache-2.0. It adds 47 tokens to every session and 643 once invoked, about $0.0002 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 2026-09-08.
Other skills, from other repositories
quantum-vqe
A runnable guide to the variational quantum eigensolver (VQE), a quantum algorithm that estimates the lowest energy of a mathematical system by adjusting a parameterized circuit. It uses Pauli Hamiltonians, a specified circuit form, and SciPy optimization.
quantum-vqls
A runnable guide to the variational quantum linear solver (VQLS), a quantum method that estimates a solution to a system of linear equations by optimizing a parameterized circuit. It uses Qiskit and reports the numerical residual and why optimization stopped.
octave-compression
Workflow for transforming prose into semantic OCTAVE structures. Covers tier selection, transformation phases, loss accounting, and decision rules. REQUIRES octave-literacy.
octave-chatter
OCTAVE on the wire — read and emit OCTAVE in agent-to-agent messages without authoring files. Syntax kernel, operator table, and the OCTAVEWIRE primer v1.3 (provenance, hedges, verbatim IDs). For agents outside the workbench matrix.
@elad12390/web-research-assistant
Comprehensive MCP server for web research with 16 tools: SearXNG + Exa AI search, batch search and batch crawling, URL crawling, stealth scraping (Cloudflare bypass), package registry lookup (npm/PyPI/crates), GitHub stats, changelog fetching, tech comparison, error translation, API docs discovery, stock image search…
inbox
Show the Relaydeck inbox and act on it. Use when the person asks what is new in Relaydeck, or asks for new tasks, answers, or messages from the app or from other agents.