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 Heretyc/subagent-mcp --skill mcp-buildergit clone --depth 1 https://github.com/Heretyc/subagent-mcpWrote 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/heretyc/subagent-mcp/mcp-builder)<a href="https://agentmods.dev/skills/heretyc/subagent-mcp/mcp-builder"><img src="https://agentmods.dev/badge/skills/heretyc/subagent-mcp/mcp-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/heretyc/subagent-mcp/mcp-builder"><img src="https://agentmods.dev/badge/skills/heretyc/subagent-mcp/mcp-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 | $0.00245 | $0.01620 |
| Opus 5.5 | $0.00098 | $0.00648 |
| Sonnet 5.5 | $0.00049 | $0.00324 |
| Haiku 4.5 | $0.00024 | $0.00162 |
Grade B, and why
mcp-builder scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Codex CLI** (`~/.codex/config.toml`): How it starts
The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Builder
Build and ship MCP servers for Claude and Codex. Load references/retrieval-map.md first to find the right leaf doc for any task.
This is generic MCP-server-building guidance for arbitrary servers; it does not apply to subagent-mcp's own no-API-key architecture.
Quick Decision Tree
Some "Load" targets below are thin indexes with a same-named sub-directory (config-claude.md, implementation-patterns.md, install-windows.md, packaging-node.md, packaging-python.md, tool-resource-prompt-schemas.md, troubleshooting.md). For these, follow the index's table of contents into references/<topic>/ for full detail : don't stop at the index. See references/retrieval-map.md for specifics.
| Task | Load |
|---|---|
| Understand MCP protocol / primitives | protocol-spec.md |
| Tool / resource / prompt schemas | tool-resource-prompt-schemas.md |
| TypeScript/Node server + npm package | packaging-node.md |
| Python server + pip/uvx package | packaging-python.md |
| Claude Desktop or Claude Code config | config-claude.md |
| Codex CLI config | config-codex.md |
| Windows install / path / registry | install-windows.md |
| macOS install / Gatekeeper / LaunchAgent | install-macos.md |
| Implementation patterns / security | implementation-patterns.md |
| Debug / errors / ENOENT / tool missing | troubleshooting.md |
| Source citations | source-ledger.md |
Core Rules (Always Active)
- stdio: never write to stdout except JSON-RPC. All logs go to stderr.
- Absolute paths in all config files. Never relative.
- Windows MSIX bug: Claude Desktop MSIX reads from
%LOCALAPPDATA%\Packages\Claude_pzs8sxrjxfjjc\LocalCache\Roaming\Claude\not%APPDATA%\Claude\. Edit the correct file. - Protocol version: Current spec is
2025-06-18. Server must echo client's version on init. - inputSchema must be JSON Schema with
type: "object". Missingrequiredarray = all fields optional. - Secrets: use
envkey in config, never hardcode. Never log secrets.
What ships with it
30 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.
- references/config-claude.md 2.1 KB
- references/config-claude/01-locations-and-json-format.md 2.3 KB
- references/config-claude/02-transport-and-windows-paths.md 1.3 KB
- references/config-claude/03-cli-env-scope-and-oauth.md 2.7 KB
- references/config-codex.md 4.3 KB
- references/implementation-patterns.md 2.0 KB
- references/implementation-patterns/01-handlers-async-progress.md 3.0 KB
- references/implementation-patterns/02-security.md 2.6 KB
- references/implementation-patterns/03-perf-lifecycle-testing-transport.md 3.3 KB
- references/install-macos.md 5.0 KB
- references/install-windows.md 1.8 KB
- references/install-windows/01-msix-trap-and-runtimes.md 2.4 KB
- references/install-windows/02-path-escaping-cli-wsl-diagnostics.md 4.1 KB
- references/packaging-node.md 1.4 KB
- references/packaging-node/01-server-and-package-setup.md 3.6 KB
- references/packaging-node/02-transport-extras-publishing.md 2.0 KB
- references/packaging-python.md 1.5 KB
- references/packaging-python/01-server-code.md 2.3 KB
- references/packaging-python/02-packaging-uvx-and-ops.md 2.9 KB
- references/protocol-spec.md 5.5 KB
- references/retrieval-map.md 9.3 KB
- references/source-ledger.md 6.8 KB
- references/tool-resource-prompt-schemas.md 1.9 KB
- references/tool-resource-prompt-schemas/01-tools.md 4.2 KB
- references/tool-resource-prompt-schemas/02-resources.md 1.1 KB
- references/tool-resource-prompt-schemas/03-prompts-and-descriptions.md 1.5 KB
- references/troubleshooting.md 2.1 KB
- references/troubleshooting/01-startup-and-connection.md 3.8 KB
- references/troubleshooting/02-params-schema-timeout-platform.md 2.5 KB
- references/troubleshooting/03-inspector-logs-restart-error-codes.md 2.1 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.
- 1mo ago First seen · 142 lines · 245 tokens per session scan B fa293896d7a5
mcp-builder is a skill published in the GitHub repository Heretyc/subagent-mcp (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 245 tokens to every session and 1,620 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
data-engineering
Builds and operates data pipelines — ingestion, transformation, orchestration, quality testing, and reliability of data delivery. Use this to design or debug a pipeline, decide batch versus streaming, add data quality checks, handle late or duplicate data, or work out why a dashboard's numbers changed without anyone…
api-design
Designs interfaces that survive their consumers — resource modeling, errors, versioning, pagination, and compatibility. Use this to design a new API, review one before it ships, decide how to version or deprecate, fix an interface consumers keep misusing, or work out whether a change is breaking.
architecture-selection
System architecture patterns including monolith, microservices, event-driven, and serverless, with C4 modeling, scalability strategies, and technology selection criteria. Use when designing system architectures, evaluating patterns, or planning scalability.
api-contract-design
REST and GraphQL API design patterns, OpenAPI/Swagger specifications, versioning strategies, and authentication patterns. Use when designing APIs, reviewing API contracts, evaluating API technologies, or implementing API endpoints.
domain-modeling
Unified domain and data modeling for business entities, invariants, schema design, aggregate boundaries, and evolution strategy. Use when designing business models, schema changes, bounded contexts, or consistency rules.
python-patterns
Python backend patterns: layered architecture, async I/O, dependency injection, repository/service separation. TRIGGER when: creating routes, models, schemas, or services in a Python backend. SKIP: REST contract design (use api-design); schema/index tuning (use database-optimization). (Examples: FastAPI + SQLAlchemy +…