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 skills/kelp/agent-plugins/zig-initnpx skills add kelp/agent-plugins --skill zig-initgit clone --depth 1 https://github.com/kelp/agent-pluginsWhat 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 | $0.00091 | $0.00657 |
| Opus 5 | $0.00046 | $0.00329 |
| Sonnet 5 | $0.00018 | $0.00131 |
| Haiku 4.5 | $0.00009 | $0.00066 |
Grade A, and why
zig-init 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/zig-init
Add Zig training corrections to this project's CLAUDE.md. The plugin supports both 0.15.x and 0.16.x; this skill detects the target version and appends the matching fragment.
Procedure
1. Detect Zig version
Run the detection helper:
${CLAUDE_PLUGIN_ROOT}/scripts/detect-zig-version.sh
It prints 0.15 or 0.16 based on (in order): the project's
build.zig.zon .minimum_zig_version field, then zig version if zig is on PATH, then a default of 0.16.
Capture the output as $VERSION.
2. Read the version-specific fragment
Read the file at:
${CLAUDE_PLUGIN_ROOT}/docs/$VERSION/claude-md-fragment.md
This contains the corrections formatted as a CLAUDE.md section matched to the detected version. If the file is missing, report the error to the user and stop -- do not proceed.
3. Check current CLAUDE.md
Each fragment opens with a version-specific marker heading:
0.15fragment:## Zig 0.15.x Training Corrections0.16fragment:## Zig 0.16.x Training Corrections
Branch on the detected version:
- If no
CLAUDE.mdexists in the project root, create one with just a# CLAUDE.mdheader followed by the fragment content. - If
CLAUDE.mdalready contains the version-specific marker, report "Zig $VERSION.x corrections already present" and stop. - If
CLAUDE.mdcontains the other version's marker (e.g. the project was previously targeting 0.15 and is now 0.16), report "CLAUDE.md has corrections for the other Zig version ($OTHER); manual review needed before swapping" and stop — do not silently overwrite. - Otherwise append the fragment content to the end of the file. Ensure a blank line separates the existing content from the fragment.
4. Report result
Tell the user what you did:
- "Created CLAUDE.md with Zig $VERSION.x corrections"
- "Added Zig $VERSION.x corrections to existing CLAUDE.md"
- "Zig $VERSION.x corrections already present in CLAUDE.md"
- "CLAUDE.md targets the other Zig version; manual review needed before swapping" (with current marker named)
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 · 77 lines · 91 tokens per session scan A 9bdf5a721a2f
zig-init is a skill published in the GitHub repository kelp/agent-plugins (2 stars, last pushed 9d ago), licensed MIT. It adds 91 tokens to every session and 657 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
outcome-roadmap
Transform an output-focused roadmap into an outcome-focused one that communicates strategic intent. Rewrites initiatives as outcome statements reflecting user and business impacts. Use when shifting to outcome roadmaps, making a roadmap more strategic, or rewriting feature lists as outcomes.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
shipping-artifacts
The durable documentation set that makes an AI-built (vibe-coded) app reviewable before shipping. A small core every app needs — architecture, user/permission flows, permissions, variables/secrets, and a test-coverage map — plus conditional docs added only when they apply: emails, scheduled work, SEO, and embedded…
stakeholder-map
Build a stakeholder map using a power/interest grid, identify communication strategies per quadrant, and generate a communication plan. Use when managing stakeholders, preparing for a launch, aligning cross-functional teams, or planning stakeholder engagement.