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/algorand-devrel/algorand-agent-skills/algorand-pythonnpx skills add algorand-devrel/algorand-agent-skills --skill algorand-pythongit clone --depth 1 https://github.com/algorand-devrel/algorand-agent-skillsWrote 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/algorand-devrel/algorand-agent-skills/algorand-python)<a href="https://agentmods.dev/skills/algorand-devrel/algorand-agent-skills/algorand-python"><img src="https://agentmods.dev/badge/skills/algorand-devrel/algorand-agent-skills/algorand-python.svg" alt="Measured on agentmods" 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 | $0.00103 | $0.00925 |
| Opus 5 | $0.00051 | $0.00463 |
| Sonnet 5 | $0.00021 | $0.00185 |
| Haiku 4.5 | $0.00010 | $0.00093 |
Grade A, and why
algorand-python 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 4d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Algorand Python
Write, test, deploy, and troubleshoot Algorand Python smart contracts.
Quick Start
# Create Python project
algokit init -n my-project -t python --answer preset_name production --defaults
# Development cycle
cd my-project
algokit project run build # Compile contracts with PuyaPy
algokit project run test # Run pytest tests
algokit localnet start # Start local network
algokit project deploy localnet # Deploy
Critical Rules
- Understand AVM constraints first — see
algorand-coreskill for the foundational mental model - NEVER use PyTEAL or Beaker — use Algorand Python (PuyaPy) with
algopyimports - Use
@arc4.abimethodfor public ABI methods,@arc4.baremethodfor bare calls - Always search docs first — use Kapa MCP or web search before writing contract code
- Always include tests — use pytest with AlgoKit Utils
- Fund app account before box operations — box storage requires MBR funding
- Always
.copy()mutable values — call.copy()when appending to or storing mutable types: ARC-4 (arc4.Struct,arc4.DynamicArray) and native (algopy.Array,algopy.FixedArray,algopy.Struct)
Reference Guide
Read the specific reference file for your task. Each file is self-contained.
Contract Syntax
- syntax-types.md — AVM types (
arc4.UInt64,arc4.String,Bytes,UInt64), ARC-4 encoding, native vs ARC-4 conversions - syntax-storage.md —
GlobalState,LocalState,Box,BoxMap,BoxRef, MBR funding patterns - syntax-methods.md —
@arc4.abimethod,@arc4.baremethod,@subroutine, lifecycle methods, visibility,ARC4ContractvsContract - syntax-transactions.md — Inner transactions (
itxn), group transactions, fee pooling
Testing
- testing.md — Pytest patterns,
AlgorandClientsetup, typed client testing, box funding, multi-user tests
What ships with it
7 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.
- 4d ago First seen · 71 lines · 103 tokens per session scan A e002084239a4
algorand-python is a skill published in the GitHub repository algorand-devrel/algorand-agent-skills (33 stars, last pushed 17d ago), licensed MIT. It adds 103 tokens to every session and 925 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
runtime-behavior-probe
Plan and, after explicit approval, execute runtime-behavior probes for local or live integrations. Use only when explicitly invoked to verify behavior that code review and normal tests cannot settle; define a controlled validation matrix and report observed evidence.
building-pydantic-ai-agents
Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydanticai, or asks to build an AI agent, add tools/capabilities, defer capability loading, stream output, define agents…
e2e-cucumber-playwright
Use when writing, changing, or reviewing Cucumber and Playwright tests under e2e/, including feature files, step definitions, support code, scenario tags, locators, and assertions. Do not use for Vitest, React Testing Library, backend tests, or generic browser automation outside the E2E suite.
adopting-generated-api-types
Use when migrating frontend code from manual API client calls (api.get, api.create, api.surveys.get, api.dashboards.list, new ApiRequest()) and handwritten TypeScript interfaces to generated API functions and types. Triggers on files importing from lib/api, files with api.get . , manual interface definitions that…
implementing-mcp-tools
Guide for exposing PostHog product endpoints as MCP tools. Use when creating new or updating API endpoints, adding MCP tool definitions, scaffolding YAML configs, or writing serializers with good descriptions. Covers the full pipeline from Django serializer to generated TypeScript tool handler.
adding-personhog-rpc
Guide for adding a new RPC to personhog-replica and personhog-router. Covers eligibility checks, proto definition, code generation for Python and Node.js clients, Rust implementation (storage trait, postgres queries, service handler, router wiring), and index compatibility validation. Use when adding a new gRPC…