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/sshh12/claude-plugins/build-skillnpx skills add sshh12/claude-plugins --skill build-skillgit clone --depth 1 https://github.com/sshh12/claude-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/sshh12/claude-plugins/build-skill)<a href="https://agentmods.dev/skills/sshh12/claude-plugins/build-skill"><img src="https://agentmods.dev/badge/skills/sshh12/claude-plugins/build-skill.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.04344 |
| Opus 5 | $0.00043 | $0.02172 |
| Sonnet 5 | $0.00017 | $0.00869 |
| Haiku 4.5 | $0.00009 | $0.00434 |
Grade A, and why
build-skill 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 5d 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
build-skill
Helps the user build a Claude Code skill end-to-end. A skill is a Markdown file with YAML frontmatter that Claude loads when its trigger description matches the user's intent — it encodes a workflow Claude should follow consistently.
What makes a good skill
- Does one thing well — overly broad skills fail more often than overly narrow ones
- Specific enough to be useful, flexible enough to handle real variation
- Connects to data sources and tools available in the user's environment
- Solves a problem the user has actually felt, not a hypothetical
- Worth running at least weekly — one-off jobs don't justify the authoring cost
The central risk: overfitting
You and the user will iterate on a small handful of test cases because it's fast — they know those cases in and out, and the feedback loop tightens. But the skill will get used hundreds or thousands of times across prompts neither of you have seen. A skill that works only for the test cases is useless. Resist piling on rigid rules to make the current example perfect at the cost of generality. Most edits should make the skill more robust, not more specific. When you're tempted to add a fiddly rule that fixes one case, ask whether it would still help — or hurt — on cases you haven't seen.
Build process
Walk through these stages in order. Skipping the problem-mapping or testing stages is the most common cause of bad skills.
1. Start with the problem, not the solution
What's the painful workflow? What takes too long? What does the user keep re-explaining? Don't open with "I want a skill that..." — open with "Every week I have to..." Surface the real pain before designing anything.
Mine the conversation first. If the user just said "turn this into a skill" or "let's make this reusable", the workflow they want is probably already in the chat. Extract it: the tools used, the sequence of steps, the corrections they made along the way, the input and output formats observed. Confirm the extracted workflow with the user before interviewing further. Don't make them re-explain what they just did.
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.
- 5d ago First seen · 220 lines · 86 tokens per session scan A a041962e1ebe
build-skill is a skill published in the GitHub repository sshh12/claude-plugins (22 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 4,344 once invoked, about $0.0004 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
frontmcp-development
Use when building any FrontMCP server component other than a tool (for tools, use create-tool). Covers @Resource static resources and parameterized URI templates; @Prompt reusable prompts (RAG, multi-turn); @Provider singleton dependency-injection providers (database pools, API clients); @Agent autonomous LLM agents…
pipefy-ai-agents
Use this skill when the user wants to create, read, update, delete, or troubleshoot AI agents (conversational agents with behaviors). Covers 7 MCP tools including pre-flight validation, plus pipe-scoped knowledge bases (list, plain text/document/data lookup CRUD, access probe) attached via dataSourceIds. For…
pipefy-automations
Use this skill when the user wants to create, read, update, or delete traditional automations (if/then rules) or AI automations (prompt-driven). Covers 16 MCP tools. For AI agents (conversational), see skills/ai-agents/.
pipefy-ipaas
Use when the user wants to build, test, publish, or manage iPaaS (Advanced Automations) flows: multi-step integrations with external apps (Slack, Gmail, Google Sheets), incoming webhooks, schedules, routers, code steps, or iPaaS data tables. MCP-only, driven through 4 meta-tools over a per-pipe catalog discovered at…
pipefy-portal-setup
Use this skill when the user wants to list, create, or configure Pipefy portals (main hub, pages, page elements, sub-portals, publish/unpublish). Covers 20 MCP tools on Interfaces + internalapi. Not for pipes/cards.
pipefy-api-fallback
Use this skill when an MCP tool fails AND the introspection skill could not resolve the problem. This is the last-resort fallback (Tier 3): call the Pipefy GraphQL API directly using curl or httpx, authenticating with the Service Account (OAuth2) or a Personal Access Token (PAT) available as env var. Follow the 3-tier…