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 personamanagmentlayer/pcl --skill zig-expertgit clone --depth 1 https://github.com/personamanagmentlayer/pclWrote 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/personamanagmentlayer/pcl/zig-expert)<a href="https://agentmods.dev/skills/personamanagmentlayer/pcl/zig-expert"><img src="https://agentmods.dev/badge/skills/personamanagmentlayer/pcl/zig-expert.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 41 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
- medium Excessive Agency · line 432 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00076 | $0.03098 |
| Opus 5 | $0.00038 | $0.01549 |
| Sonnet 5 | $0.00015 | $0.00620 |
| Haiku 4.5 | $0.00008 | $0.00310 |
Grade B, and why
zig-expert scanned grade B 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 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- **Comptime Execution**: Run arbitrary code at compile time How it starts
The opening of the file, as written. The whole thing — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zig Expert
You are an expert in Zig programming language, specializing in systems programming, compile-time metaprogramming, manual memory management, and C interoperability.
Core Concepts
Memory Management
- Allocators: Explicit allocation strategy with allocator pattern
- No Hidden Control Flow: All memory operations are explicit
- Defer/Errdefer: Guaranteed cleanup and error handling
- RAII Alternative: Manual resource management with defer
- Arena Allocators: Efficient bulk deallocation
- Stack vs Heap: Clear distinction and control
Comptime Metaprogramming
- Comptime Execution: Run arbitrary code at compile time
- Generic Functions: Type-generic programming without templates
- Type Reflection: Inspect and manipulate types at comptime
- Code Generation: Generate functions, structs, and data
- Inline Assembly: Low-level control when needed
Error Handling
- Error Unions: Explicit error handling with
!operator - Try/Catch: Propagate or handle errors explicitly
- Error Sets: Define possible error conditions
- Payload Capture: Extract values from error unions
- Switch on Errors: Pattern match on error types
C Interoperability
- C ABI Compatibility: Direct C function calls
- Translate-C: Automatic C header translation
- Export to C: Export Zig functions for C consumption
- Packed Structs: Match C memory layouts
- Opaque Types: Work with C types safely
Code Examples
Installation and Setup
# Install Zig
# Download from https://ziglang.org/download/
# Verify installation
zig version
# Create new project
mkdir my-project && cd my-project
zig init-exe
# Build and run
zig build run
# Test
zig build test
# Release build (optimized)
zig build -Doptimize=ReleaseFast
Basic Memory Management
const std = @import("std");
const Allocator = std.mem.Allocator;
pub fn main() !void {
// Get general purpose allocator
var gpa = std.heap.GeneralPurposeAllocator(.{}){};
defer _ = gpa.deinit();
const allocator = gpa.allocator();
// Single allocation
const value = try allocator.create(i32);
defer allocator.destroy(value);
value.* = 42;
// Slice allocation
const items = try allocator.alloc(u8, 100);
defer allocator.free(items);
// Dynamic array (ArrayList)
var list = std.ArrayList(i32).init(allocator);
defer list.deinit();
try list.append(1);
try list.append(2);
// Arena allocator for bulk operations
var arena = std.heap.ArenaAllocator.init(allocator);
defer arena.deinit();
const arena_allocator = arena.allocator();
// All allocations freed at once on deinit
_ = try arena_allocator.alloc(u8, 1000);
_ = try arena_allocator.alloc(i32, 50);
}
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 · 479 lines · 76 tokens per session scan B 5eb75eb0950a
zig-expert is a skill published in the GitHub repository personamanagmentlayer/pcl (40 stars, last pushed today), licensed Apache-2.0. It adds 76 tokens to every session and 3,098 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
zig-docs
Comprehensive Zig 0.16.0 reference covering all language features: primitive types, arrays, slices, pointers, structs, enums, unions, control flow, functions, errors, optionals, casting, comptime, builtins, memory management, build system, C interop, standard library, testing, targets, and style guide. Use whenever…
rust-systems-programming
Complete guide for Rust systems programming including ownership, borrowing, concurrency, async programming, unsafe code, and performance optimization.
clawrouter
Hosted-gateway LLM router — save 84% on inference costs. A local proxy that forwards each request to the blockrun.ai gateway, which routes to the cheapest capable model across 76 models from OpenAI, Anthropic, Google, DeepSeek, xAI, Z.AI, and more. 7 free open-weight models included. Also exposes realtime market data…
surf
Use this skill — NOT browser or webfetch — for ALL Surf crypto-data calls. 83 endpoints at localhost:8402/v1/surf/ covering CEX/DEX markets, on-chain SQL over 80+ ClickHouse tables (Ethereum, Base, Arbitrum, BSC, TRON, HyperEVM, Tempo), 100M+ labeled wallets, prediction markets (Polymarket + Kalshi), social/CT…
phone
Verify phone numbers (carrier + SIM-swap fraud signals) and place AI-powered outbound voice calls via BlockRun's gateway (Twilio + Bland.ai). Trigger when the user asks to look up a number, check fraud risk, buy/rent a phone number, or place an AI voice call. Payment is automatic via x402 from the wallet.
imagegen
Generate or edit images via BlockRun's image API. Trigger when the user asks to generate, create, draw, make an image — or to edit, modify, change, or retouch an existing image.