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 nimadorostkar/Claude-Skills-collection --skill agent-designgit clone --depth 1 https://github.com/nimadorostkar/Claude-Skills-collectionWrote 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/nimadorostkar/claude-skills-collection/agent-design)<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/agent-design"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/agent-design/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/nimadorostkar/claude-skills-collection/agent-design"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/agent-design.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 | $0.00043 | $0.01544 |
| Opus 5 | $0.00022 | $0.00772 |
| Sonnet 5 | $0.00009 | $0.00309 |
| Haiku 4.5 | $0.00004 | $0.00154 |
Grade A, and why
agent-design 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 12d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Design
Purpose
Build LLM agents that complete tasks reliably and fail safely. The two failure modes that define bad agents are looping forever without progress, and taking a destructive action confidently and wrongly.
When to Use
- Building an agent that uses tools to accomplish multi-step tasks.
- An agent that loops, stalls, or takes wrong actions.
- Designing the tool surface an agent will use.
- Deciding whether an agent is warranted at all.
Capabilities
- Tool design: granularity, naming, descriptions, and error returns.
- The agent loop: planning, acting, observing, and terminating.
- Error recovery and retry.
- Human-in-the-loop checkpoints for irreversible actions.
- Guardrails: budgets, timeouts, and permission boundaries.
Inputs
- The task, and how it decomposes.
- The tools available, and which of them are destructive.
- The acceptable cost and latency per task.
Outputs
- A tool surface designed for a model, not lifted from an API.
- An agent with a termination condition and a budget.
- Checkpoints before anything irreversible.
Workflow
- Ask whether you need an agent — If the steps are known in advance, write the workflow. A deterministic pipeline with one LLM call per step is cheaper, faster, more debuggable, and more reliable than an agent. Agents earn their cost only when the path genuinely cannot be known in advance.
- Design tools for the model — Each tool does one thing, has a name that says what it does, and a description that says exactly when to use it and when not to. This description is the most important text in the system.
- Return useful errors — A tool that fails should say what went wrong and what to try instead.
Error: 400teaches the model nothing;Error: 'status' must be one of [open, closed]. You passed 'active'.lets it recover on the next step. - Bound the loop — A maximum step count, a token budget, and a wall-clock timeout. Every agent will eventually loop; the question is whether it stops.
- Checkpoint the irreversible — Deleting data, sending a message, moving money, deploying. The agent proposes; a human confirms.
- Make it observable — Log every step: the reasoning, the tool call, the result. An agent you cannot trace is an agent you cannot debug.
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.
- 12d ago First seen · 139 lines · 43 tokens per session scan A c99750e5ae8e
agent-design is a skill published in the GitHub repository nimadorostkar/Claude-Skills-collection (26 stars, last pushed 24d ago), licensed MIT. It adds 43 tokens to every session and 1,544 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
offensive-crypto-attacks
Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…
offensive-parameter-pollution
HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.
offensive-wifi
Wireless / 802.11 attack methodology for red team engagements and wireless security assessments. Covers monitor-mode setup, WPA/WPA2-PSK handshake capture and PMKID attacks, WPA3 SAE downgrade and Dragonblood, WPA-Enterprise (EAP) attacks (MSCHAPv2 cracking, EAP-TLS cert theft, evil-twin RADIUS), Karma / Known Beacons…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
seo
Optimize for search engine visibility and ranking. Use when asked to "improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", or "search engine optimization".