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 nweii/agent-stuff --skill nweii-skillsgit clone --depth 1 https://github.com/nweii/agent-stuffWrote 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/nweii/agent-stuff/nweii-skills)<a href="https://agentmods.dev/skills/nweii/agent-stuff/nweii-skills"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/nweii-skills/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/nweii/agent-stuff/nweii-skills"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/nweii-skills.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 | $0.00074 | $0.05415 |
| Opus 5 | $0.00037 | $0.02707 |
| Sonnet 5 | $0.00015 | $0.01083 |
| Haiku 4.5 | $0.00007 | $0.00541 |
Grade B, and why
nweii-skills 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 9d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
`bunx skills add` keeps **one real copy** of each skill in the canonical dir `~/.agents/skills/<name>/`, then **symlinks each agent's skills dir to it**. So Claude Code sees `~/.claude/skills/<name>` as a symlink pointin How it starts
The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nweii-skills
Reference context for Nathan's skills ecosystem. Read this before creating, editing, or migrating any skill in his environment.
The repos
Skills live in two paired repos:
- nweii/agent-stuff — public + internal-but-public skills. Cloned at
~/Developer/LLMs/agent-stuff/. nweii/agent-stuff-private— truly private skills (sensitive materials, personal workflows, confidential content). Pushed to a private GitHub remote.
Both repos share a core layout, with some folders specific to one:
<repo>/
├── skills/ # Skill folders
├── agents/ # Subagent definitions (public: inspiration set; private: backups)
├── zips/ # Auto-built per-skill zips for drag-into-Claude.ai (generated)
├── scripts/ # update-catalog.py + build-zips.py (run by the pre-commit hook)
└── templates/ # SKILL_TEMPLATE.md, RULE_TEMPLATE.md (agent-stuff only)
Both repos have a .githooks/pre-commit that, when a skill changes, regenerates the README.md catalog (update-catalog.py) and rebuilds the zips/ mirror (build-zips.py) into the same commit.
The zips/ mirror
Each skill is also packaged as a <name>.zip (one top-level folder named after the skill, containing its files) for non-CLI user convenience. Key properties:
- Built locally by the pre-commit hook, not a GitHub Action — the zip lands in the same commit as the skill edit, and reverts with it.
- Deterministic —
build-zips.pyuses fixed timestamps, sorted entries, and git-tracked files only (so.DS_Storeand other junk never get in). An unchanged skill produces a byte-identical zip, so editing one skill diffs exactly one zip; no churn. - Self-healing — the hook wipes and fully rebuilds
zips/each run, so a deleted, renamed, or newly-internal skill drops its stale zip automatically. - Per-repo scope —
build-zips.pycarries aZIP_INCLUDE_INTERNALconstant:Falseinagent-stuff(general-purpose skills only — don't encourage dropping internal ones in unmodified),Trueinagent-stuff-private(every skill is personal, so zip all).
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.
- 9d ago First seen · 255 lines · 74 tokens per session scan B 9d1be6d9a5a5
nweii-skills is a skill published in the GitHub repository nweii/agent-stuff (9 stars, last pushed 21d ago), licensed MIT. It adds 74 tokens to every session and 5,415 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…