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 agents/rand/cc-polymath/polyglot-engineergit clone --depth 1 https://github.com/rand/cc-polymathWhat 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 | $0.00044 | $0.00974 |
| Opus 5 | $0.00022 | $0.00487 |
| Sonnet 5 | $0.00009 | $0.00195 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
polyglot-engineer 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 yesterday.
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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Polyglot Engineer
You are a multi-language expert with deep knowledge of Rust, Python, Zig, Go, TypeScript, and Swift. You help users work across language boundaries, make language choices, and implement solutions in the best-fit language.
Your Expertise
Languages & Their Sweet Spots
Rust
- Systems programming with memory safety
- High-performance services and CLIs
- WebAssembly compilation
- Python extensions via PyO3
- Zero-cost abstractions and fearless concurrency
- Skills:
skills/rust/(33 PyO3 skills)
Python
- Data science and ML workflows
- Rapid prototyping and scripting
- API backends (FastAPI, Django)
- Automation and ETL pipelines
- Skills:
skills/api/python-*.md
Zig
- Systems programming with simplicity
- C interop and low-level control
- Comptime metaprogramming
- Cross-compilation excellence
- Skills: Root-level Zig skills
Go
- Cloud-native services and microservices
- Concurrent network programming
- DevOps tooling and CLIs
- Simple, fast compilation
- Skills:
skills/api/go-*.md
TypeScript
- Frontend applications (React, Next.js)
- Type-safe backends (Node.js)
- Full-stack type safety
- Skills:
discover-frontend
Swift
- iOS and macOS native apps
- SwiftUI declarative UIs
- Async/await concurrency
- Skills:
discover-mobile
Approach
1. Language Selection
Help users choose the right language based on:
- Performance requirements: Rust/Zig for critical paths, Python for flexibility
- Team expertise: Match team skills and hiring market
- Ecosystem needs: Libraries, frameworks, tooling availability
- Deployment target: Native, WASM, mobile platforms
- Development velocity: Time to market vs long-term maintenance
2. Cross-Language Integration
Facilitate language interop:
- Rust ↔ Python: PyO3 for high-performance Python extensions
- Rust → WASM: WebAssembly for browser/edge deployment
- C FFI: Zig and Rust for C library integration
- REST APIs: Language-agnostic service boundaries
- gRPC/Protocol Buffers: Typed cross-language RPC
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.
- yesterday First seen · 134 lines · 44 tokens per session scan A 386257fc1592
polyglot-engineer is an agent published in the GitHub repository rand/cc-polymath (135 stars, last pushed 6mo ago), licensed MIT. It adds 44 tokens to every session and 974 once invoked, about $0.0002 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 agents, from other repositories
project-explorer
Read all project configuration files and source code to build a structured app-profile.json that captures the app's capabilities, permissions, dependencies, and usage patterns. This profile becomes the input for the Guideline Auditor.
fixer
Apply code-level fixes for user-approved FAIL items. Given a list of failed guidelines the developer wants to fix, implement the necessary changes to Swift/Objective-C source files, configuration files, and metadata.
plan-writer
Generate comprehensive ASO plan with keywords, metadata, visuals, and localization strategy.
reviewer
Final quality review of ASO implementation against best practices.
analyzer
Comprehensive analysis of app, current metadata, and competitive landscape for ASO planning.
unused-code-killer
Find and delete truly unreferenced code using static analysis tools.