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-maintenancegit 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-maintenance)<a href="https://agentmods.dev/skills/adikant/datalens-dev-mcp/datalens-maintenance"><img src="https://agentmods.dev/badge/skills/adikant/datalens-dev-mcp/datalens-maintenance/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-maintenance"><img src="https://agentmods.dev/badge/skills/adikant/datalens-dev-mcp/datalens-maintenance.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 | $0.00027 | $0.00312 |
| Opus 5 | $0.00014 | $0.00156 |
| Sonnet 5 | $0.00005 | $0.00062 |
| Haiku 4.5 | $0.00003 | $0.00031 |
Grade A, and why
datalens-maintenance 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 yesterday.
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 Maintenance
Paginate inventory completely within the requested scope and describe backup completeness honestly. Before cleanup compute the dependency preserve closure and show the exact delete set. Use documented HTML Page, workbook, access, and license operations only; never invent a revoke route or browser write fallback.
Read references/boundaries.md before backup, cleanup, HTML Page, or license work.
Cleanup identity is the provider entry ID regardless of inventory aliases. Preview reads both dependency directions, preserves the original roots, orders consumers before dependencies and rejects incomplete or external-consumer scope. Apply revalidates the original scope before any write; preview_changed requires reconciling the fresh preview with the authorized scope and preserve requirements. Failed/uncertain deletion stops all remaining objects and returns per-object skipped/partial effects. Do not retry an uncertain write or recreate deleted objects. A previous authorization covers only its exact scope; a destructive scope outside the current request requires user authorization. confirmed_delete records the exact machine scope; an already explicit deletion request needs no new human reply. Preview is bounded to API-visible relations and must not be described as proof of tenant-wide completeness.
Follow authorized scope and delivery for mutations: explicit scoped work continues without repeated permission questions; read-only and save-only limits remain binding.
What ships with it
1 file 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.
- yesterday Changed · +2 lines a8909291ed33
- 2d ago First seen · 13 lines · 27 tokens per session scan A 47d6520051a4
datalens-maintenance is a skill published in the GitHub repository ADIKANT/datalens-dev-mcp (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 27 tokens to every session and 312 once invoked, about $0.0001 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 2026-09-08.
Other skills, from other repositories
style-guide
Dedalus style guide quick reference. Key rules for writing code that lasts. Use when writing or reviewing Python code.
scrape-batch
Extract many known URLs in one polite, rate-limited pass. Use when the user hands over a list of links, a set of search hits to read in full, or asks to "scrape these pages" / "pull the content from all of them". Drives extract(action="batch"), which fans out with per-domain rate limiting and returns partial results…
compare
Structured comparison of 2+ alternatives with consistent criteria and decision matrix.
knowledge-audit
Review and clean up stored memories — find duplicates, contradictions, stale entries, and consolidate.
temporal-query
Answer time-travel questions over stored memory — what was believed at a past point in time, when a belief changed, and what replaced it. Use when the user says "as of", "back in", "at the time", "history of", "timeline", "what did I think then", or asks why a current memory contradicts an older one.
memory-commit
Use when the user explicitly says "remember this", "save this", "ghi nho", "luu lai", "save for next time", or otherwise asks to persist the immediately preceding context. Captures with the appropriate contexttype (decision, preference, fact, skill, task, conversation) so future sessions can retrieve it accurately.