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 skills/kuiralabs/ada-dev-cli/docsnpx skills add kuiralabs/ada-dev-cli --skill docsgit clone --depth 1 https://github.com/kuiralabs/ada-dev-cliWhat 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 | $0.00000 | $0.04146 |
| Opus 5 | $0.00000 | $0.02073 |
| Sonnet 5 | $0.00000 | $0.00829 |
| Haiku 4.5 | $0.00000 | $0.00415 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ada-dev-cli — Agent Skill
You have access to Cardano through this tool, either as the ada CLI or as the ada-mcp MCP
server. Read this once at the start of a session; use it as reference throughout.
Over MCP, prefer the tools: ada_status, ada_balance, ada_transfer_preview,
ada_transfer + ada_confirm, and so on. Tool descriptions carry the same rules as this document
and the annotations tell you what is safe to call unasked. The two-step send flow below is
enforced there — ada_transfer cannot send on its own, whatever arguments you pass.
Over the CLI, every command takes --json. The rules are identical.
Scope note: everything below works — wallets, balances, funding, ADA transfers, native assets, two-party atomic swaps, the devnet lifecycle and chain inspection. Never invent a command. Ask the tool what it has:
ada help --json
If ada is not found, it has not been linked yet — the project is not on npm. From a clone:
npm install && npm run build && npm link.
Every entry carries implemented: true|false. Trust that over this document if they ever disagree.
The output contract
Always pass --json. Then every invocation returns exactly one JSON document on stdout, on
success and on failure alike. ada tip --json | jq works either way.
Success:
{ "ok": true, "command": "tip", "height": 158, "slot": 758, "epoch": 1, "hash": "..." }
Failure:
{ "ok": false, "error": true, "command": "tip",
"code": "devnet_not_running",
"message": "cannot reach the devnet at http://localhost:8080/api/v1/blocks/latest",
"hint": "start it with: ada localnet up" }
Rules that will not change:
- Branch on
ok.error: trueis also present on failures if you prefer that shape. codeis the contract. Branch on it.messageis prose and may be reworded — never pattern-match it.hint, when present, is the suggested next action. It is usually exactly what to do.commandechoes what you asked for, so a result can be correlated.- Stderr carries progress and chrome only. Ignore it unless diagnosing.
- Exit codes:
0ok ·2bad arguments ·3config ·4devnet not running ·5network ·6chain rejected ·7a required tool is missing ·70internal.
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.
- yesterday First seen · 269 lines · 0 tokens per session scan A 2e9c37d25d01
docs is a skill published in the GitHub repository kuiralabs/ada-dev-cli (2 stars, last pushed 5d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 4,146 tokens. 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…