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 instructions/kuiralabs/ada-dev-cli/claude-mdgit 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 | $0.00625 | $0.00625 |
| Opus 5 | $0.00313 | $0.00313 |
| Sonnet 5 | $0.00125 | $0.00125 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
ada-dev-cli CLAUDE.md 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 2d 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.
ada-dev-cli
A Cardano development CLI, with a built-in MCP server so agents are first-class users. It is a developer instrument, not a consumer wallet — testnets only, mainnet refused.
Read docs/COMMANDS.md before adding or changing a command. It holds the output contract, and
the contract is the product — a command that prints a spinner into stdout has broken the tool for
its second audience.
The core constraint
Part of this tool's value is checking whether another implementation is behaving — comparing what it produces against what a chain accepts. That only works while this tool stays an independent implementation. It is built on MeshJS, and it must never be rebuilt on top of something it is used to check: a reference built from the code under test can only confirm that code's own bugs.
If a change would make this tool share an implementation with something it validates, that change is wrong regardless of how much duplication it removes.
Compose, don't rewrite
Yaci DevKit owns the local chain. MeshJS owns wallet and transaction construction.
cardano-address owns derivation. This tool owns the surface: one command vocabulary, one
config, one agent interface, and the pieces nobody ships — transfers between arbitrary addresses,
asset bundles, and atomic swaps.
Before writing anything that looks like chain logic, check whether one of those three already does it correctly.
Rules
--jsonoutput is a contract. Clean stdout, stable error reasons on stderr, deterministic ordering. Breaking it is a breaking change even if the human output looks fine.- No interactive prompts on any path an agent needs. Flags instead.
--yesalways bypasses a confirmation. - Secrets never on argv. Command lines land in shell history and process listings.
- Derivation is not reimplemented here. Delegate to the ground-truth tool. It is the highest-consequence cryptography in the stack and a second implementation can only disagree.
- Tests reproduce failures. A regression test must fail before the fix and pass after it, not assert the happy path.
- Public repo, consumer voice. No internal narrative, no issue numbers, no debugging history in user-facing docs. Internal reasoning belongs in the private planning repo.
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.
- 2d ago First seen · 54 lines · 625 tokens per session scan A acddcaadb529
ada-dev-cli CLAUDE.md is an instructions file published in the GitHub repository kuiralabs/ada-dev-cli (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 625 tokens to every session, about $0.0031 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 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.