Cougr: Skill for Claude Code

.claude/skills/soroban/SKILL.md

soroban is a skill for Claude Code from salazarsebas/Cougr. It costs 91 tokens per session (17,113 once invoked), scanned A, original, MIT.

A development guide for Soroban, the smart-contract platform on the Stellar blockchain, using Rust.

In plain words
What is it for?
Use it to build and test Soroban contracts, review authorization and storage risks, design advanced contract systems, and investigate platform-specific errors.
Why use it?
It brings contract design, testing, security checks, and Stellar-specific troubleshooting into one reference for on-chain software.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is salazarsebas/Cougr's own configuration. It tells Claude Code how to work on Cougr itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Cougr configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is file = "../token/target/wasm32-unknown-unknown/release/token.wasm".

Reuse

Borrowing it

Nothing to install: this file belongs to salazarsebas/Cougr. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/salazarsebas/Cougr/main/.claude/skills/soroban/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/salazarsebas/Cougr

Made for: Claude Code.

Wrote 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.

agentmods badge for soroban

README.md
[![agentmods](https://agentmods.dev/badge/skills/salazarsebas/cougr/soroban/github.svg)](https://agentmods.dev/skills/salazarsebas/cougr/soroban)
Your own site
<a href="https://agentmods.dev/skills/salazarsebas/cougr/soroban"><img src="https://agentmods.dev/badge/skills/salazarsebas/cougr/soroban/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.

agentmods 80×15 button for soroban

Your own site · 80×15
<a href="https://agentmods.dev/skills/salazarsebas/cougr/soroban"><img src="https://agentmods.dev/badge/skills/salazarsebas/cougr/soroban.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 17,113 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00091 $0.17113
Opus 5.5 $0.00036 $0.06845
Sonnet 5.5 $0.00018 $0.03423
Haiku 4.5 $0.00009 $0.01711

Measured today against content hash c3daeb8097f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

soroban scanned grade A with 1 finding 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 today.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl "http://localhost:8000/friendbot?addr=G..."
.claude/skills/soroban/SKILL.md · 2,581 lines

How it starts

The opening of the file, as written. The whole thing — 2,581 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Soroban Smart Contracts

End-to-end guide for building Soroban contracts: writing them, testing them, securing them, and shipping advanced architectures. This skill bundles five concerns that live and die together - the contract code, the tests, the security posture, the design patterns, and the gotchas.

When to use this skill

  • Writing a Soroban contract in Rust
  • Setting up unit, integration, fuzz, or property tests
  • Reviewing a contract for security issues (authorization, reentrancy-adjacent bugs, storage hygiene, TTL, overflow)
  • Architecting upgradeable contracts, factories, governance, or DeFi primitives
  • Debugging a Soroban-specific error (auth, storage, archival, resource limits)
  • Assets, trustlines, and SAC bridge → ../assets/SKILL.md
  • Frontend/wallets that call your contract → ../dapp/SKILL.md
  • Chain data queries (RPC/Horizon) → ../data/SKILL.md
  • ZK cryptography (BLS12-381, BN254, Poseidon) → ../zk-proofs/SKILL.md
  • SEP/CAP standards and ecosystem links → ../standards/SKILL.md

Part 1: Contract Development

When to use Soroban

Use Soroban when you need:

  • Custom on-chain logic beyond Stellar's built-in operations
  • Programmable escrow, lending, or DeFi primitives
  • Complex authorization rules
  • State management beyond account balances
  • Interoperability with Stellar Assets via SAC

Quick Navigation

Read the full file on GitHub · 2,581 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.

  1. today First seen · 2,581 lines · 91 tokens per session scan A c3daeb8097f6

Subscribe to this mod's changes

soroban is a skill published in the GitHub repository salazarsebas/Cougr (53 stars, last pushed 17d ago), licensed MIT. It adds 91 tokens to every session and 17,113 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-07.

Related

soroban compared with skills from other repositories

soroban next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
sorobansalazarsebas/CougrSkill5317d agoMITA91Claude Code
smart-contractsrylsherdamz-rgb/stellar-forgeSkill175d agoMITA44Claude Code
jolta16z/joltSkill1.1ktodayApache-2.0A15Claude Code
solana-toolkit-guidenirholas/three.wsSkill269yesterdayApache-2.0A50Claude Code, Codex
solanaquicknode/solana-finance-claude-pluginSkill101yesterdayMITA76Claude Code
smart-contractsstellar/stellar-dev-skillSkill57todayApache-2.0A151Claude Code
solana-developmenttenequm/skillsSkill392d agoMITA53Claude Code, Codex