What is skills AGENTS.md?

Repository instructions for a documentation project containing reusable coding-agent skills for the Algorand ecosystem.

Creating or editing skill folders, maintaining their SKILL.md and reference files, and validating one skill or the complete collection.

They identify the required layout and the validation command, so new or changed skills can be checked consistently.

skills AGENTS.md — Instructions file by TxnLab

Install

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.

agentmods

npx agentmods add instructions/txnlab/skills/agents-md

Clone the repo

git clone --depth 1 https://github.com/TxnLab/skills

Made for: Codex, OpenCode.

Per session 474 This file is loaded in full into every session.

When invoked 474 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00474	$0.00474
Opus 5	$0.00237	$0.00237
Sonnet 5	$0.00095	$0.00095
Haiku 4.5	$0.00047	$0.00047

Measured 2d ago against content hash 727eaf6d7b48, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skills AGENTS.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.

AGENTS.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to AI coding agents working with code in this repository.

Project Overview

This is a documentation repository containing Agent Skills for TxnLab's Algorand ecosystem. Skills extend AI coding agents with specialized knowledge about NFDomains, use-wallet, and Haystack Router. There is no build step or compiled output — the deliverables are markdown files.

Commands

# Validate all skills
node scripts/validate.js

# Validate a specific skill
node scripts/validate.js <skill-name>

There are no build, test, or lint commands. Validation is the only check.

Architecture

Each skill lives in skills/<skill-name>/ and follows the Agent Skills specification:

SKILL.md — Entry point with YAML frontmatter (name and description required). The name field must match the directory name.
references/ — Detailed markdown guides for specific tasks (API usage, framework integration, etc.)
assets/ — Optional static assets (none currently used)

The validation script (scripts/validate.js) checks frontmatter structure using only Node.js built-ins (no dependencies). It parses YAML frontmatter manually and verifies required fields.

Current Skills

Skill	Package
`nfd`	`@txnlab/nfd-sdk` — Algorand Name Service (.algo domains)
`use-wallet`	`@txnlab/use-wallet` v4.x — Multi-framework wallet connections
`haystack-router`	`@txnlab/haystack-router` — DEX aggregator and swap routing

Adding a New Skill

Create skills/<skill-name>/SKILL.md with YAML frontmatter containing name (matching directory) and description
Add references/*.md files for detailed task-specific documentation
Run node scripts/validate.js to verify
Use conventional commits

Local Testing

Symlink a skill directory to test with Claude Code directly:

ln -s $(pwd)/skills/nfd ~/.claude/skills/nfd

Read the full file on GitHub · 53 lines

Changes

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 · 53 lines · 474 tokens per session scan A 727eaf6d7b48

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository TxnLab/skills (6 stars, last pushed 6mo ago), licensed MIT. It adds 474 tokens to every session, about $0.0024 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.

agent-skills ai algorand claude-code nfd use-wallet

vibekit AGENTS.md

Instructions for initlabsai/vibekit, covering agents.md, what runs where, how a call flows, glossary and rules.

initlabsai/vibekit · 3,319 tokens

algorand-mcp AGENTS.md

Instructions for GoPlausible/algorand-mcp, covering algorand mcp — agent guide, calling mcp tools, session start, network selection and amounts and decimals.

GoPlausible/algorand-mcp · 5,347 tokens

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).

microsoft/vscode · 6,785 tokens

skills AGENTS.md