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 algorand-devrel/algorand-agent-skills --skill algokit-utils-pygit 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/algokit-utils-py)<a href="https://agentmods.dev/skills/algorand-devrel/algorand-agent-skills/algokit-utils-py"><img src="https://agentmods.dev/badge/skills/algorand-devrel/algorand-agent-skills/algokit-utils-py/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/algorand-devrel/algorand-agent-skills/algokit-utils-py"><img src="https://agentmods.dev/badge/skills/algorand-devrel/algorand-agent-skills/algokit-utils-py.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 | $0.00218 | $0.02113 |
| Opus 5 | $0.00109 | $0.01056 |
| Sonnet 5 | $0.00044 | $0.00423 |
| Haiku 4.5 | $0.00022 | $0.00211 |
Grade A, and why
algokit-utils-py 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 9d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AlgoKit Utils Python — Quick Reference
This skill targets version 5.x of algokit-utils.
This skill provides idiomatic patterns for algokit-utils (Python).
When helping users, prefer the patterns below over raw algosdk calls — AlgoKit Utils wraps the
SDK with higher-level, type-safe abstractions.
How to use this skill
Reference docs are split into individual files under references/. Only read the file(s) relevant
to the user's question — this keeps context lean. The table below maps topics to filenames.
Key concepts
- AlgorandClient is the single entry point. Create one via
AlgorandClient.default_localnet(),.testnet(),.mainnet(),.from_config(),.from_clients(), or.from_environment(). - AlgoAmount provides type-safe Algo/microAlgo values. Use
algo(5),micro_algo(1000),AlgoAmount.from_algo(5), orAlgoAmount(algo=5). - AccountManager (
algorand.account.*) handles key generation, mnemonics, multisig, logic sigs, rekeyed accounts, funding, and signer registration. - TransactionComposer (
algorand.new_group()) builds atomic groups with fluent chaining. Supports.add_payment(),.add_asset_transfer(),.add_app_call_method_call(), etc. - AppFactory creates and deploys smart contracts from ARC-56/ARC-32 app specs. Supports
idempotent deploy with
on_update/on_schema_breakstrategies and template variable substitution. - AppClient interacts with deployed contracts — ABI method calls, state reads (global, local,
box), bare calls, and the
paramsbuilder for deferred composition. - Raw app calls via
algorand.send.app_call(),.app_create(),.app_update(),.app_delete(),.app_call_method_call(),.app_create_method_call()when you don't have an app spec. - TEAL compilation via
algorand.app.compile_teal()and.compile_teal_template()with caching and template variable substitution. - Crypto primitives live in the standalone
algokit_cryptopackage that ships alongsidealgokit-utils. This module carries Ed25519 keypair generation/signing/verification (ed25519_generator,ed25519_verifier), the Peikert xHD BIP44 wallet (peikert_hd_wallet_generator), and the wrapped-secret pattern for HSM/KMS-backed keys (WrappedEd25519Seed,WrappedHdExtendedPrivateKey,ed25519_signing_key_from_wrapped_secret). The Algorand SHA-512/256 primitive lives inalgokit_commonassha512_256. Reach for these when you are building a customRawEd25519Signer, deriving deterministic accounts from a seed, or computing Algorand-compatible hashes outside the transaction path.
What ships with it
19 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.
- references/account-management.md 7.3 KB
- references/algoamount-and-value-handling.md 2.7 KB
- references/asset-operations.md 6.8 KB
- references/client-initialization.md 3.8 KB
- references/compile-teal.md 1.4 KB
- references/configuration-and-global-settings.md 1.3 KB
- references/ed25519.md 7.7 KB
- references/error-handling.md 3.6 KB
- references/getting-started.md 635 B
- references/hashing.md 3.1 KB
- references/hd-wallets.md 5.5 KB
- references/key-registration.md 1.9 KB
- references/network-and-client-management.md 2.6 KB
- references/payment-transactions.md 3.9 KB
- references/raw-app-calls.md 4.6 KB
- references/smart-contract-deployment.md 5.3 KB
- references/smart-contract-interaction.md 5.8 KB
- references/transaction-composition.md 6.8 KB
- references/wrapped-secrets.md 7.7 KB
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.
- 9d ago First seen · 120 lines · 218 tokens per session scan A 72bc4c35842b
algokit-utils-py is a skill published in the GitHub repository algorand-devrel/algorand-agent-skills (33 stars, last pushed today), licensed MIT. It adds 218 tokens to every session and 2,113 once invoked, about $0.0011 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
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…
geopipe-agent
Use when building AI-driven GIS data pipelines with YAML-defined steps — format conversion, spatial validation, QC reporting, PostGIS loading, WMS publishing. GeoPipe Agent: YAML-driven GIS ETL pipeline agent with quality control.
bitcoin-libraries-bdk-python
Python bindings for BDK. Same API as Rust BDK exposed via UniFFI.
bitcoin-libraries-bitcoinlib-py
High-level wallet library by 1200WD. Aims to be a complete solution for Python Bitcoin (and altcoin) wallets.
writing-sdks
Create a Python SDK using Ape Framework to simplify using a given blockchain-based protocol. Use when users need specific best practices and guidance on developing a new integration with the given protocol. Do not use if such a Python SDK already exists that is designed to work with Ape.
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.