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 slash-commandsgit 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/slash-commands)<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/slash-commands"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/slash-commands/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/slash-commands"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/slash-commands.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 | $0.00037 | $0.01085 |
| Opus 5 | $0.00018 | $0.00543 |
| Sonnet 5 | $0.00007 | $0.00217 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade A, and why
slash-commands 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slash Commands
Purpose
Turn a workflow you repeat into a command you invoke. A slash command is an explicit, user-triggered prompt — as distinct from a skill, which the model decides to load on its own.
When to Use
- A prompt you find yourself retyping.
- A multi-step workflow with a fixed shape: review, release, triage, summarize.
- A team workflow that everyone should run the same way.
- Anything you want to invoke deliberately, rather than have the model choose.
Capabilities
- Command authoring with arguments.
- Composing tool calls and shell commands into a workflow.
- Scoping: project-level, personal, or bundled in a plugin.
- Distinguishing command from skill.
Inputs
- The workflow, and the variable parts of it.
- What the user will type, and what they will pass as arguments.
Outputs
- A command file that runs the workflow reliably.
- Clear argument handling with a sensible default.
Workflow
- Decide: command or skill? — A skill is loaded when the model judges it relevant. A command is invoked when the user decides. If you want control over when it runs, it is a command.
- Name it for the action —
/review,/release,/triage. A verb the user would think of. - Handle the arguments — What varies between invocations? A PR number, a file, a version. Provide a default where one is sensible.
- Write the workflow as instructions — The command file is a prompt. It should say what to do, in order, with what constraints.
- Front-load the context — A command can run shell commands and include their output before the model reads the instructions. This is what makes a command dramatically more efficient than typing the same request.
Best Practices
- A command that just rephrases a request is not worth the file. The value is in the workflow, the pre-gathered context, and the consistency.
- Gather the context in the command, not in the model's turns. A
/reviewcommand that includes the diff, the CI status, and the linked issue up front saves the model three tool calls. - Give arguments a default.
/reviewwith no argument should review the current branch, not fail. - Keep the command focused on one workflow. A command with a mode flag is two commands.
- Commands are the right place for team conventions: everyone running
/releaseruns the same checks in the same order. - Document what it does at the top. Someone will run it without reading the file.
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 · 113 lines · 37 tokens per session scan A 68344d0cef4e
slash-commands is a skill published in the GitHub repository nimadorostkar/Claude-Skills-collection (26 stars, last pushed 24d ago), licensed MIT. It adds 37 tokens to every session and 1,085 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-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-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-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".