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 hashiiiii/rules-for-ai --skill hashiiiii-ziggit clone --depth 1 https://github.com/hashiiiii/rules-for-aiWrote 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/hashiiiii/rules-for-ai/hashiiiii-zig)<a href="https://agentmods.dev/skills/hashiiiii/rules-for-ai/hashiiiii-zig"><img src="https://agentmods.dev/badge/skills/hashiiiii/rules-for-ai/hashiiiii-zig/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/hashiiiii/rules-for-ai/hashiiiii-zig"><img src="https://agentmods.dev/badge/skills/hashiiiii/rules-for-ai/hashiiiii-zig.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 | $0.00025 | $0.00783 |
| Opus 5.5 | $0.00010 | $0.00313 |
| Sonnet 5.5 | $0.00005 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
hashiiiii-zig 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 19d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zig
Write the smallest implementation that preserves the required behavior. Use the project's Zig version. Read a few matching examples in that version's standard library before choosing syntax or APIs.
Structure
- Keep unit tests in the implementation file: tests for
src/parser.zigbelong insrc/parser.zig. - Put end-to-end tests in
e2e/at the repository root. Exercise real public API flows. - Use
src/root.zigfor library exports andsrc/main.zigfor executables. - Ensure the test root references files containing tests; Zig does not discover every source file automatically.
Implementation
- Prefer concrete types,
const, inferred.{ ... }literals,struct,enum,union(enum), and exhaustiveswitch. - Use ordinary functions and runtime loops when they express the behavior directly.
- Prefer file imports within a module, such as
@import("parser.zig"). Use named imports for separate module dependencies. - Use
comptimeorinlinewhen evaluation must happen at compile time. Useanytypeor reflection for necessary type-dependent code. - Propagate errors with
try; usecatchfor recovery or translation. Reserveunreachablefor proven invariants. - Use
deferfor cleanup anderrdeferfor error returns. A failure returned as a union value does not runerrdefer. - Accept allocators explicitly. Store resource owners by value unless retained pointers or allocator handles require a stable address.
- Make owned and borrowed slices clear. Copy retained input when the result must outlive it.
- Use
undefinedonly for storage initialized before reading. Add casts only when inference or representation requires them.
Tests
- Keep or add tests only when at least 80% confident they are necessary. Remove lower-confidence tests and add missing necessary ones.
- Judge user impact, regression risk, and overlap with other tests. The threshold concerns necessity, not code coverage.
- Use native
testblocks andstd.testingexpectations. Name the concrete behavior being checked. - Assert public behavior, not private layout or dependencies' own guarantees.
- Write each test from setup to assertion. Keep inputs and expected values literal and setup local.
- Avoid shared fixtures, computed expectations, and case-table loops that make readers reconstruct the behavior.
- Explain why the behavior matters in comments. Use real dependencies; never use mocks or stubs.
- For allocations, use
std.testing.allocatorand release owned resources withdefer.
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.
- 19d ago First seen · 59 lines · 25 tokens per session scan A fc43a1a9f7bf
hashiiiii-zig is a skill published in the GitHub repository hashiiiii/rules-for-ai (10 stars, last pushed 7d ago), licensed MIT. It adds 25 tokens to every session and 783 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-27.
Other skills, from other repositories
loom-c
C language expertise (C11/C17/C23) for memory-safe, portable, production-quality systems code.
testing-expert
Ultimate Kotlin testing skill. Use this whenever writing, reviewing, or debugging ANY Kotlin test — unit, integration, property-based, or coroutine. Covers TDD (RED/GREEN/REFACTOR), Kotest + MockK + Kover, anti-pattern detection, and four-pillar quality framework. Triggers on: write a test, add coverage, why is this…
laravel-testing
Test strategy for a layered Laravel application — which test style fits each layer, hand-written fakes over mocks, real-database tests for Query Classes and Repositories, pure tests for Value Objects, and feature tests that assert authorization, payload shape and query counts. Use when writing or reviewing Laravel…
cpp-testing
C++ testing workflow for unit and integration tests: GoogleTest/GoogleMock, CMake/CTest integration, diagnosing flaky tests, and running sanitizers and coverage for correctness signal. Use when writing or fixing C++ tests and test infrastructure.
cpp-testing
Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers.
cpp-testing
Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers.