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 mohitmishra786/low-level-dev-skills --skill hare-langgit clone --depth 1 https://github.com/mohitmishra786/low-level-dev-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/mohitmishra786/low-level-dev-skills/hare-lang)<a href="https://agentmods.dev/skills/mohitmishra786/low-level-dev-skills/hare-lang"><img src="https://agentmods.dev/badge/skills/mohitmishra786/low-level-dev-skills/hare-lang/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/mohitmishra786/low-level-dev-skills/hare-lang"><img src="https://agentmods.dev/badge/skills/mohitmishra786/low-level-dev-skills/hare-lang.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 | $0.00067 | $0.01578 |
| Opus 5 | $0.00034 | $0.00789 |
| Sonnet 5 | $0.00013 | $0.00316 |
| Haiku 4.5 | $0.00007 | $0.00158 |
Grade B, and why
hare-lang 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 8d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo make install How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hare
Purpose
Guide agents through the Hare programming language: design philosophy (simple, stable, compiled), hare build/test/run workflows, stdlib overview, C FFI with @extern, the type system (tagged unions, slices), error handling with (T | error!), and comparison with C and Zig for systems utilities.
When to Use
- Writing small system utilities with C-like control and modern safety
- Building CLI tools or daemons with minimal dependencies
- Calling C libraries from Hare or exporting Hare functions to C
- Preferring explicit error handling over exceptions
- Evaluating Hare vs C or Zig for a new project
- Needing a stable, auditable codebase without heavy runtime
Workflow
1. Install Hare
# Linux/macOS — build from source
git clone https://git.sr.ht/~sircmpwn/hare
cd hare
make check # builds and runs tests
sudo make install
hare version
# Create project (Hare has no project generator — lay out manually)
mkdir -p mytool && cd mytool
cat > hare.mod << 'EOF'
module mytool
EOF
2. Hello world and build
// main.ha
use fmt;
export fn main() void = {
fmt::println("Hello, Hare!")!;
};
hare build -o mytool
./mytool
hare run . # build and run
hare test # run tests
3. Stdlib overview
| Module | Purpose |
|---|---|
fmt |
Formatted I/O (printf, println) |
io |
Reader/writer interfaces |
os |
Files, environment, args |
strings |
String manipulation |
bufio |
Buffered I/O |
encoding |
JSON, hex, etc. |
net |
TCP/UDP networking |
time |
Dates and durations |
mem |
Memory helpers |
types |
Platform integer types |
use os;
use fmt;
use strings;
export fn main() void = {
const args = os::args;
for (let i = 0z; i < len(args); i += 1) {
fmt::println(args[i])!;
};
};
4. Error handling
// Errors are tagged union values — explicit propagation with !
fn read_file(path: str) (str | os::error) = {
const file = os::open(path)?;
defer os::close(file);
let buf: []u8 = [];
io::readall(file, &buf)?;
return strings::fromutf8(buf)!;
};
export fn main() void = {
match (read_file("config.txt")) {
case let s: str =>
fmt::println(s)!;
case let err: os::error =>
fmt::fatalf("error: {}", err)!;
};
};
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.
- 8d ago First seen · 239 lines · 67 tokens per session scan B fa8fa5dc287e
hare-lang is a skill published in the GitHub repository mohitmishra786/low-level-dev-skills (203 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 1,578 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
autohotkey-v2
Write AutoHotkey v2 desktop scripts for window management and Win32 integration; troubleshoot permissions and compile scripts with Ahk2Exe.
flow-launcher
Build Flow Launcher plugins with C# or Python JSON-RPC, configure plugin manifests, and integrate Everything search.
ast-refactoring-scripts
Use AST-aware tools such as libcst, ts-morph, or jscodeshift for repeatable code migrations across many files.
header-only-c-cpp-ingestion
Inspect C and C++ headers for public contracts and data structures before reading implementation files.
inline-lambda-functions
Use concise lambdas or arrow functions for small callbacks when a separate named function adds no clarity.
inline-type-signatures
Use native type annotations and avoid repeating the same type information in documentation comments.