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 lidonation/Cardano-mcp --skill ground-in-docsgit clone --depth 1 https://github.com/lidonation/Cardano-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/lidonation/cardano-mcp/ground-in-docs)<a href="https://agentmods.dev/skills/lidonation/cardano-mcp/ground-in-docs"><img src="https://agentmods.dev/badge/skills/lidonation/cardano-mcp/ground-in-docs/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/lidonation/cardano-mcp/ground-in-docs"><img src="https://agentmods.dev/badge/skills/lidonation/cardano-mcp/ground-in-docs.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 | $0.00074 | $0.00669 |
| Opus 5.5 | $0.00030 | $0.00268 |
| Sonnet 5.5 | $0.00015 | $0.00134 |
| Haiku 4.5 | $0.00007 | $0.00067 |
Grade A, and why
ground-in-docs 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ground concept answers in the repo's own docs
This repo ships three curated reference docs specifically so an agent's
explanations of Cardano concepts stay accurate and consistent with how the
cardano-mcp server itself models these ideas, rather than drifting toward
generic, possibly-outdated blockchain explanations from general training
data:
src/resources/eutxo-context.md— the eUTxO model: UTxOs, validators, datums vs redeemers, how balances work without accounts.src/resources/governance-context.md— CIP-1694 / Conway-era governance: DReps, the constitutional committee, SPOs, the seven governance action types, treasury withdrawals, voting.src/resources/aiken-stdlib.md— Aiken standard library reference used by thecontractsmodule's tools (get_aiken_stdlib_docs,scaffold_validator,explain_eutxo_model).
Workflow
- Before answering a question about eUTxO mechanics, Aiken/validator
concepts, or CIP-1694 governance, read the relevant file(s) above with
the
Readtool. - Base the answer on what those docs actually say. If the docs and your
general knowledge would suggest different framing or terminology, prefer
the docs — they're what this project's own tools (
explain_eutxo_model, the governance module,get_aiken_stdlib_docs) are aligned with, so answers should stay consistent with what the server itself would tell a caller. - If the question goes beyond what these docs cover (e.g. a very specific protocol parameter, a recent CIP not yet reflected here, an Aiken language feature outside the stdlib doc), say so explicitly rather than quietly filling the gap from general knowledge — the point is to be honest about the boundary between "grounded in this project's docs" and "my general understanding."
- When these docs would benefit from an update (they're missing something a user needed), say so — don't silently patch the answer without flagging that the source doc could be extended.
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 First seen · 54 lines · 74 tokens per session scan A 5c3bce66c49f
ground-in-docs is a skill published in the GitHub repository lidonation/Cardano-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 669 once invoked, about $0.0003 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 2026-09-21.
ground-in-docs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ground-in-docslidonation/Cardano-mcp | Skill | 2 | 1mo ago | MIT | A | 74 | Claude Code |
| midnight-dapp-devmzf11125/midnight_agent_skills | Skill | 5 | 4mo ago | MIT | A | 374 | Claude Code, Codex |
| midnight-compactmzf11125/midnight_agent_skills | Skill | 5 | 4mo ago | MIT | A | 91 | Claude Code, Codex |
| midnight-apimzf11125/midnight_agent_skills | Skill | 5 | 4mo ago | MIT | A | 104 | Claude Code, Codex |
| midnight-conceptsmzf11125/midnight_agent_skills | Skill | 5 | 4mo ago | MIT | A | 76 | Claude Code, Codex |
| midnight-networkmzf11125/midnight_agent_skills | Skill | 5 | 4mo ago | MIT | A | 80 | Claude Code, Codex |
| midnight-walletmzf11125/midnight_agent_skills | Skill | 5 | 4mo ago | MIT | B | 287 | Claude Code, Codex |