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/fold-run/fold/mcp-specnpx skills add fold-run/fold --skill mcp-specgit clone --depth 1 https://github.com/fold-run/foldWrote 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/fold-run/fold/mcp-spec)<a href="https://agentmods.dev/skills/fold-run/fold/mcp-spec"><img src="https://agentmods.dev/badge/skills/fold-run/fold/mcp-spec.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 5.1 | $0.00065 | $0.01257 |
| Opus 5 | $0.00032 | $0.00629 |
| Sonnet 5 | $0.00013 | $0.00251 |
| Haiku 4.5 | $0.00006 | $0.00126 |
Grade A, and why
mcp-spec 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reading the MCP specification
fold's whole value proposition is that it is invisible: behavior through the gateway matches hitting the upstream directly. That is a claim about a specification, so protocol questions get answered from the specification — not from memory, not from the SDK's Go doc comments, and not from how fold currently behaves.
Fetch the page. Quote the normative sentence. Then write code.
The pin
fold targets 2026-07-28, the revision config.protocol accepts
(config/config.go) and the one the Go SDK negotiates. Every URL below
carries the revision in its path — keep it there. A bare
/specification/ URL redirects to whatever is current and will silently
answer a different question than the one you asked.
Append .md to any page for clean markdown (…/server/tools.md).
https://modelcontextprotocol.io/llms.txt is the full page index.
Where things are
| Question | Page |
|---|---|
Method shapes, _meta, error codes, error-code allocation policy |
/specification/2026-07-28/basic/index |
Lifecycle, statelessness, server/discover |
/specification/2026-07-28/server/discover |
| Streamable HTTP, headers, stream semantics | /specification/2026-07-28/basic/transports/streamable-http |
| stdio framing | /specification/2026-07-28/basic/transports/stdio |
Tools, inputSchema/outputSchema |
/specification/2026-07-28/server/tools |
Resources, URIs, resources/read |
/specification/2026-07-28/server/resources |
| Prompts | /specification/2026-07-28/server/prompts |
ttlMs / cacheScope (CacheableResult) |
/specification/2026-07-28/server/utilities/caching |
| Pagination (cursors) | /specification/2026-07-28/server/utilities/pagination |
subscriptions/listen |
/specification/2026-07-28/basic/patterns/subscriptions |
MRTR — input_required, inputRequests |
/specification/2026-07-28/basic/patterns/mrtr |
| Progress, cancellation | /specification/2026-07-28/basic/patterns/progress, …/cancellation |
| Elicitation, sampling, roots | /specification/2026-07-28/client/… (all three deprecated) |
| Authorization, resource-server discovery, DCR | /specification/2026-07-28/basic/authorization/… |
| Security considerations | /specification/2026-07-28/basic/authorization/security-considerations |
| What changed this revision | /specification/2026-07-28/changelog |
| What is scheduled for removal | /specification/2026-07-28/deprecated |
| Raw types | /specification/2026-07-28/schema |
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 · 89 lines · 65 tokens per session scan A 2aeb8c0d8a59
mcp-spec is a skill published in the GitHub repository fold-run/fold (1 stars, last pushed today), licensed Apache-2.0. It adds 65 tokens to every session and 1,257 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 2026-08-31.
Other skills, from other repositories
memory-index
Index a folder's contents into the MemPalace semantic memory for search and retrieval. Use this skill whenever the user asks to "index a folder", "index a directory", "index memory", "mine a project into memory", "make a folder searchable", "embed a folder", "ingest code into the palace", or "index this directory for…
memory-mine
Mine project files or conversations into the MemPalace memory system. Indexes source code and conversation history as searchable palace drawers with semantic embeddings and room assignment.
memory-status
Show MemPalace memory system status — drawer counts, wings, rooms, knowledge graph stats, and embedding model state.
higress-wasm-go-plugin
Develop Higress WASM plugins using Go 1.24+. Use when creating, modifying, or debugging Higress gateway plugins for HTTP request/response processing, external service calls, Redis integration, or custom gateway logic.
migrate-goldmark-extension-v1-to-v2
Migrate goldmark extension from goldmark v1 to v2.
migrate-goldmark-app-v1-to-v2
Migrate your application from goldmark v1 to v2.