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/rfxlamia/skillkit/skillkit-helpnpx skills add rfxlamia/skillkit --skill skillkit-helpgit clone --depth 1 https://github.com/rfxlamia/skillkitWhat 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 | $0.00066 | $0.00745 |
| Opus 5 | $0.00033 | $0.00373 |
| Sonnet 5 | $0.00013 | $0.00149 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
skillkit-help 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 3d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Routing
Detect which path the user needs and jump directly to it.
| User says | Route |
|---|---|
| "what are skills", "how do skills work", "explain", "understand", "not sure", "should I" | → Path A |
| "validate", "check", "review my skill", "is this good" | → Path B |
| "ready to build", "let's create", "make a skill" | Tell them: "You're ready — invoke /skillkit directly to start building." |
| Ambiguous | Ask: "Do you want to (A) understand how skills work, (B) validate an existing skill, or are you ready to build (invoke /skillkit)?" |
Path A: Understand How Skills Work
Goal: Build a mental model of skills — what they are, when to use them, and whether you actually need one — before starting to build.
Step 1 — Why skills exist
Load and read in full: knowledge/foundation/01-why-skills-exist.md
Summarize for the user: skills are reusable prompt-time instructions that extend your agent's behavior for specific tasks. They live in ~/.claude/skills/ and are invoked via /skill-name.
Step 2 — Skills vs subagents
Load and read: knowledge/foundation/02-skills-vs-subagents-comparison.md
Explain the difference with a concrete example:
- Skill: "When I type
/review-pr, load these code review instructions" - Subagent: "Spin up a separate agent with browser tools to scrape and summarize a URL"
Step 3 — Decision framework
Load and read: knowledge/foundation/03-skills-vs-subagents-decision-tree.md
Walk the user through the decision tree for their specific use case.
Step 4 — Platform constraints
Load and read: knowledge/foundation/06-platform-constraints.md
Cover the key rules: frontmatter requirements, size limits, trigger conditions.
Step 5 — Hand off to the builder
Tell the user: "You now have enough context to start building. Invoke /skillkit — it will guide you through the full creation workflow."
Path B: Validate an Existing Skill
Goal: Check an existing skill for quality issues before sharing or publishing.
What ships with it
8 files 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.
- knowledge/application/09-case-studies.md 11 KB
- knowledge/application/12-testing-and-validation.md 9.9 KB
- knowledge/foundation/01-why-skills-exist.md 9.5 KB
- knowledge/foundation/02-skills-vs-subagents-comparison.md 11 KB
- knowledge/foundation/03-skills-vs-subagents-decision-tree.md 11 KB
- knowledge/foundation/06-platform-constraints.md 9.6 KB
- knowledge/foundation/08-when-not-to-use-skills.md 10 KB
- template/SKILL.md 1.3 KB
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.
- 3d ago First seen · 82 lines · 66 tokens per session scan A 0a3d7874f9fd
skillkit-help is a skill published in the GitHub repository rfxlamia/skillkit (101 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 66 tokens to every session and 745 once invoked, about $0.0003 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-vuln-classes
Exploit development curriculum covering core vulnerability classes with real-world CVE case studies: stack/heap buffer overflows, use-after-free, integer overflows, format strings, type confusion, and race conditions. Use when learning or teaching vuln classes, researching specific CVE patterns, or building exploit…
offensive-tls-attacks
Comprehensive methodology for auditing and exploiting TLS/SSL implementations and misconfigurations across network services and mobile applications. Covers protocol downgrade attacks including POODLE (CVE-2014-3566) against SSLv3 CBC padding, DROWN (CVE-2016-0800) cross-protocol attack leveraging SSLv2 export ciphers…
offensive-advanced-redteam
Comprehensive red team operations methodology covering full engagement lifecycle from planning through reporting. Addresses engagement scoping and rules of engagement negotiation, multi-tier C2 infrastructure design with redirectors and domain fronting, malleable traffic profiles and beacon tradecraft, OPSEC…
offensive-social-engineering
Social engineering attack techniques beyond email phishing for authorized red team and physical penetration testing engagements. Covers pretexting methodology (persona creation, authority and urgency psychological triggers, rapport building), vishing (voice phishing via caller ID spoofing, IVR system exploitation…
offensive-dependency-confusion
Deep-dive offensive methodology for dependency confusion and namespace attacks across all major package ecosystems. Covers npm scope confusion exploiting the gap between public and private scoped packages and .npmrc misconfigurations where registry mappings fail to pin internal scopes exclusively. Addresses PyPI…
offensive-idor
IDOR (Insecure Direct Object Reference) testing checklist: object ID enumeration, horizontal/vertical privilege escalation, GUID predictability, indirect references via hashes, chained IDOR, and API endpoint IDOR. Use for web app pentests and bug bounty IDOR discovery.