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-dashboardgit 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-dashboard)<a href="https://agentmods.dev/skills/adikant/datalens-dev-mcp/datalens-dashboard"><img src="https://agentmods.dev/badge/skills/adikant/datalens-dev-mcp/datalens-dashboard/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-dashboard"><img src="https://agentmods.dev/badge/skills/adikant/datalens-dev-mcp/datalens-dashboard.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 | $0.00046 | $0.00645 |
| Opus 5.5 | $0.00018 | $0.00258 |
| Sonnet 5.5 | $0.00009 | $0.00129 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
datalens-dashboard 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 17d 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
DataLens Dashboard
For new elements, use the effective authoring profile: current explicit requirements override project and user choices; references supply structure/technology below the common visual policy. visible_title is canonical (title remains an input alias). Keep object name, visible title, hint and geometry separate. Preserve current tabs, widgets, relations and manual layout outside the requested change.
If the dashboard is known, confirm its current identity, parent and affected bindings through addressed reads; a supplied workbook URL does not add a full inventory step. Establish the workbook card and complete inventory when the target or requested group must be discovered, or completeness/absence must be proved. Reuse sufficient current evidence. Route dependencies by actual subtype/renderer; keep unknown types explicit. Project examples and browser tabs supply context, never a replacement target.
For a single metadata field, follow the narrow change sequence; no graph traversal or Browser tour is needed. For existing tab items, globalItems, grouped control children, layout or connections, use dl_object_update with dashboard_patch and the fresh expected_revision; send only changes addressed by native IDs. Read composition for this shape and only the affected bindings. For new composition, validate the complete draft batch with dl_editor_validate(drafts=...); carry a compiled recipe's visual_contract into item presentation. Use a meaningful hint when it helps explain the metric; missing hint text does not block placement or require invented prose. Use native selector_group for grouped Dataset/parameter controls. Retain raw snapshots for exact imports or documented adapter gaps.
Follow authorized scope and delivery for mutations, continuation and completion across projects. For a visual or semantic choice, load the relevant part of visualization decisions. For visible changes, check the affected rendered state with Browser read-only after API and applicable data checks; a correct readback alone does not prove correct layout. An API error or review-size rejection does not authorize switching dashboard edits to Browser, shell or an opaque payload. If the request is too large, use the supported compact delta through the same reviewed tool route. If that route is unavailable or fails, report the exact contract or access limitation; keep Browser read-only unless the user explicitly requests UI editing.
Route field/native chart changes to datalens-dataset-wizard, JavaScript runtime changes to datalens-editor, discovery to datalens-inspect, and backup/cleanup or standalone Page work to datalens-maintenance.
For unknown effects follow repeat-effect recovery: only proven non-application or separate informed repeat authorization permits another attempt. Failed reconciliation, absent inventory and a new operation_id do not make a retry safe.
What ships with it
3 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.
- 17d ago Changed 7eacc467a0cd
- 22d ago Changed d18ed2bd7de3
- 27d ago Changed ea595bcc7227
- 1mo ago Changed 8ef6b0c328eb
- 1mo ago Changed 5b8ad2cfe641
- 1mo ago Changed · +2 lines 9b6d02f25d42
- 1mo ago Changed · +2 lines baeae600b03c
- 1mo ago Changed · -2 lines · +17 tokens per session 26dc6522a256
- 1mo ago Changed · +2 lines 0f9d1dc2bdf3
- 1mo ago First seen · 15 lines · 29 tokens per session scan A 775225b132f8
datalens-dashboard is a skill published in the GitHub repository ADIKANT/datalens-dev-mcp (7 stars, last pushed 11d ago), licensed Apache-2.0. It adds 46 tokens to every session and 645 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.