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/heretyc/subagent-mcp/mcp-buildernpx 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.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 | $0.00245 | $0.01620 |
| Opus 5 | $0.00122 | $0.00810 |
| Sonnet 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 4d 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.
- 4d 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 6d ago), licensed Apache-2.0. It adds 245 tokens to every session and 1,620 once invoked, about $0.0012 per session on Opus 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
planflow
Draft a plan and get it approved as an editable flowchart in the user's browser before executing. Use when the user asks to plan a task with PlanFlow, or wants to review, edit, or approve a plan before any code changes are made.
seo-strategy
Audits and improves organic search performance — technical health, site architecture, internal linking, structured data, and the content decisions that determine what can rank. Use this to run an SEO audit, diagnose why pages are not ranking or were deindexed, plan a site's URL and navigation structure, add structured…
implement-factory
Factory loop orchestrator for multi-feature or multi-component implementation manifests. Use for high-complexity work with parallel-eligible workstreams and holdout-scenario evaluation.
chief-strategy-officer
Owns where the business plays and how it wins over a multi-year horizon — portfolio choices, corporate development, strategic partnerships, and planning under uncertainty. Use this for a decision about which markets or businesses to be in, whether to build, buy, or partner, how to allocate capital across business…
scenario-planning
Plans under genuine uncertainty — building scenarios, identifying which assumptions are load-bearing, setting early-warning indicators, and stress-testing a plan against futures rather than forecasting one. Use this when a decision depends on something unknowable, when a plan assumes conditions that may not hold…
ai-ml-governance
Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory…