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 yeaight7/agent-powerups --skill mcp-server-buildergit clone --depth 1 https://github.com/yeaight7/agent-powerupsWrote 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/yeaight7/agent-powerups/mcp-server-builder)<a href="https://agentmods.dev/skills/yeaight7/agent-powerups/mcp-server-builder"><img src="https://agentmods.dev/badge/skills/yeaight7/agent-powerups/mcp-server-builder/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/yeaight7/agent-powerups/mcp-server-builder"><img src="https://agentmods.dev/badge/skills/yeaight7/agent-powerups/mcp-server-builder.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 | $0.00036 | $0.00772 |
| Opus 5.5 | $0.00014 | $0.00309 |
| Sonnet 5.5 | $0.00007 | $0.00154 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade A, and why
mcp-server-builder 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 1mo 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Server Builder
Use this skill when designing or implementing an MCP server.
When to Use
- Building a new MCP server from scratch.
- Refactoring a weak or over-thin MCP tool surface.
- Reviewing whether a server exposes the right workflows.
- Designing evaluation cases for MCP usability.
Core Principles
- Build workflow tools, not thin endpoint wrappers — one tool should complete a meaningful agent task, not expose a single API method.
- Keep input schemas narrow and typed — reject unknown fields; use enums over free strings where possible.
- Return high-signal, size-bounded outputs — default to concise; add
detailorverboseflags when larger payloads are occasionally useful. - Make error messages corrective — tell the agent what to do next, not just what went wrong.
- Prefer human-meaningful identifiers over opaque IDs when both are available.
- Design evaluation cases before declaring the server "done".
Workflow
1. Map the workflow
- Identify the real tasks an agent must complete, not the underlying API surface.
- Merge low-level steps into meaningful operations (e.g., one
create_and_publishtool instead of separatecreate,validate,publish).
2. Design the tool surface
tool name: stable, verb-noun, describes the workflow step
input schema: typed, narrow, required fields only + optional detail flags
output shape: consistent structure across all tools in the server
failure modes: named error codes + correction hint
3. Design for context limits
- Default response fits in ~500 tokens for list operations, ~1500 for detail operations.
- Add
limit,page, orsummaryparameters for large result sets. - Truncate deterministically (e.g., top N by recency) — never truncate randomly.
4. Design corrective errors
Bad error: "Error: 404 Not Found"
Good error: "Resource 'project-123' not found. Use list_projects to see available project IDs."
Every error should tell the agent its next valid action.
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.
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.
- 1mo ago First seen · 94 lines · 36 tokens per session scan A b04c7f943254
mcp-server-builder is a skill published in the GitHub repository yeaight7/agent-powerups (6 stars, last pushed 19d ago), licensed Apache-2.0. It adds 36 tokens to every session and 772 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-14.
Other skills, from other repositories
skill-authoring
Author SKILL.md: frontmatter, structure, writing principles.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
github-code-review
Review PRs: diffs, inline comments via gh or REST.
requesting-code-review
Pre-commit review: security scan, quality gates, auto-fix.
simplify-code
Sequential 3-lens cleanup of recent code changes.
test-driven-development
TDD: enforce RED-GREEN-REFACTOR, tests before code.