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 vinnie357/claude-skills --skill ziggit clone --depth 1 https://github.com/vinnie357/claude-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/vinnie357/claude-skills/zig)<a href="https://agentmods.dev/skills/vinnie357/claude-skills/zig"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/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/vinnie357/claude-skills/zig"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/zig.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.01268 |
| Opus 5.5 | $0.00013 | $0.00507 |
| Sonnet 5.5 | $0.00007 | $0.00254 |
| Haiku 4.5 | $0.00003 | $0.00127 |
Grade A, and why
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 1mo 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zig Programming Language
Entry point for Zig development. Provides an overview, version awareness, and routes to focused skills.
Anti-fabrication
This skill follows core:anti-fabrication. Zig is pre-1.0 with every minor release
breaking std and build APIs, so version-migration claims are the highest-risk content
in this plugin. Verified against zig 0.16.0 (locally installed, claude-skills-204) by
compiling the documented snippets: references/migration-0.16.md's claim that
std.c.arc4random_buf is BSD/Darwin-only was refuted by its own citation (lib/std/c.zig
covers Linux/Android too) and corrected to a compile-probed target table, and
references/version-history.md's listing of fmt.bufPrintZ under "Renamed" was
corrected — it is still present, deprecated in favor of bufPrintSentinel. Re-verify
against a locally installed zig version before asserting a std API claim this skill
doesn't cover — see plugins/languages/zig/skills/sources.md for the full per-claim
record.
Available Skills
This plugin provides focused skills for specific Zig topics:
- zig:language - Core language: comptime, error handling, data types, slices, defer
- zig:build - Build system: build.zig, cross-compilation, dependencies, CI
- zig:allocators - Memory management: allocator types, patterns, leak detection
- zig:testing - Built-in test framework, test allocator, build integration
- zig:c-interop - C interoperability: @cImport, type mappings, translate-c, linking
- zig:troubleshooting - Common errors, debugging, runtime panics, memory issues
Version Awareness
Zig is pre-1.0: every minor release carries breaking changes. Run zig version
first and match guidance to the installed toolchain. This plugin documents
0.16.0 (current stable, released 2026-04-13); 0.15.x and 0.14.x notes are
retained for migration. Check https://ziglang.org/download/index.json for the
release list — GitHub tags lag behind (they stop at 0.15.2).
When borrowing an upstream example, compare it with that project's source and
compiler manifest at a pinned commit. Report any disagreement with general or
official documentation and follow the consuming project's existing pin; do not
silently change its toolchain. For example, Ghostty commit
44f2a44
records Zig 0.16.0 even when Ghostty's official build documentation still
describes 0.15.2.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +8 lines 3e636feac3d6
- 2mo ago First seen · 78 lines · 33 tokens per session scan A 11251d67e6ac
zig is a skill published in the GitHub repository vinnie357/claude-skills (27 stars, last pushed 14d ago), licensed MIT. It adds 33 tokens to every session and 1,268 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 2026-09-03.
zig compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| zigvinnie357/claude-skills | Skill | 27 | 14d ago | MIT | A | 33 | Claude Code |
| omh-rustrlaope/oh-my-hermes | Skill | 5.3k | today | MIT | A | 74 | Claude Code, Codex |
| erlang-otp-behaviorsbenchflow-ai/skillsbench | Skill | 1.9k | 6d ago | Apache-2.0 | A | 52 | Claude Code, Codex |
| axiom-concurrencyCharlesWiltgen/Axiom | Skill | 1.3k | yesterday | MIT | A | 49 | Claude Code |
| tddcodewithmukesh/dotnet-claude-kit | Skill | 811 | 5d ago | MIT | A | 81 | Claude Code |
| haskell-prormyndharis/antigravity-skills | Skill | 2.0k | 2d ago | MIT | A | 37 | Claude Code, Codex |
| precisemicroprediction/precise | Skill | 338 | 8d ago | MIT | A | 76 | Claude Code, Codex |