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 AlteredCraft/claude-code-plugins --skill example-skill-codegit clone --depth 1 https://github.com/AlteredCraft/claude-code-pluginsWrote 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/alteredcraft/claude-code-plugins/example-skill-code)<a href="https://agentmods.dev/skills/alteredcraft/claude-code-plugins/example-skill-code"><img src="https://agentmods.dev/badge/skills/alteredcraft/claude-code-plugins/example-skill-code/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/alteredcraft/claude-code-plugins/example-skill-code"><img src="https://agentmods.dev/badge/skills/alteredcraft/claude-code-plugins/example-skill-code.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 | $0.00107 | $0.02676 |
| Opus 5.5 | $0.00043 | $0.01070 |
| Sonnet 5.5 | $0.00021 | $0.00535 |
| Haiku 4.5 | $0.00011 | $0.00268 |
Grade C, and why
feature-spec-creator scanned grade C 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 2mo 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
- **Don't refuse to call out a contradiction because it might be awkward.** Surfacing them is the job. Frame as a question if uncertain ("am I looking at the right code?"), but don't paper over them. How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feature Spec Generator
Interview the user to produce a focused feature spec for an existing codebase. The output is a single markdown file the user can hand to a developer (or future-Claude) and have enough context to plan the work without re-asking the same questions.
Why this skill exists
A good spec is the cheapest place to surface scope creep, integration headaches, and contradictions between what the user describes and what the code actually does. Catching those at spec time costs minutes; catching them mid-implementation costs hours. The interview is the value — the markdown is just the artifact. The skill's job is to make that surfacing happen before code gets written.
Workflow
The sequence matters. Do not jump ahead.
1. Confirm the feature in one sentence
Before reading any code, ask the user what feature they want to spec, in one sentence. If they already said it clearly in the prompt, just paraphrase it back and ask "is that right?" — don't make them repeat themselves.
If their description is vague (e.g., "I want to improve the dashboard"), ask a single clarifying question to get to a concrete feature before scanning code. Scanning the wrong area is wasted work.
2. Lightweight code scan to seed context
The code scan is steered by the seed, not exhaustive. Read what the seed makes relevant; ignore what it doesn't. The goal is to know enough to ask sharp anchored questions in step 3 and recognize when an answer contradicts the code — not to understand the whole codebase. Deeper reading for implementation happens after the spec narrows the focus, not here.
Aim for a quick scan, not a full architectural review. Specifically:
- Locate the area of the codebase the feature touches (Glob/Grep for likely module names, route handlers, models, components).
- Read 2–4 of the most relevant files end-to-end.
- Skim adjacent files (tests, configs, types) to spot patterns and constraints.
- Note: existing similar features, the data model around the affected area, integration points (APIs, queues, DB tables), and any obvious tech-debt or workarounds in the area.
What ships with it
1 file 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.
- 2mo ago First seen · 146 lines · 107 tokens per session scan C 25645c7b4a11
feature-spec-creator is a skill published in the GitHub repository AlteredCraft/claude-code-plugins (12 stars, last pushed 5mo ago), licensed MIT. It adds 107 tokens to every session and 2,676 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…