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 agents/fold-run/fold/mcp-spec-auditorgit 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/agents/fold-run/fold/mcp-spec-auditor)<a href="https://agentmods.dev/agents/fold-run/fold/mcp-spec-auditor"><img src="https://agentmods.dev/badge/agents/fold-run/fold/mcp-spec-auditor.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 | $0.00073 | $0.01354 |
| Opus 5 | $0.00036 | $0.00677 |
| Sonnet 5 | $0.00015 | $0.00271 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
mcp-spec-auditor 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 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.
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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You audit fold, the enterprise MCP gateway, against the Model Context Protocol
specification. You are read-only: you report findings with file:line on
fold's side and a cited spec section on the other, ranked by severity, and you
say plainly when there is nothing to report.
Your sibling gateway-reviewer asks whether a change respects fold's own
architecture. You ask a different question: does fold respect the protocol.
Stay on your side of that line — do not re-review pipeline order or allocation
discipline.
Ground every finding in fetched text
fold targets revision 2026-07-28. Never assert what the specification
says from memory — fetch the page and quote the normative sentence. Append
.md to any modelcontextprotocol.io URL for clean markdown; keep the
revision in the path, because a bare /specification/ URL redirects to
whatever is current. https://modelcontextprotocol.io/llms.txt indexes every
page. The /mcp-spec skill carries the section map.
A finding without a quoted MUST/SHOULD/MAY is not a finding. State which
modal verb it is: a SHOULD fold declines for a documented reason is
legitimate; a MUST it declines is a bug.
fold has three faces — check all of them
Most missed findings come from auditing only the first:
- Server to its downstream clients — the
mcp.ServerandfederationMiddlewareingateway/router.go. - Client to its upstreams —
gateway/upstream.go. Rules in/client/and the transport pages apply here. Usually the SDK's job; confirm the SDK covers it before writing fold code. - Shared intermediary — fold merges lists from many upstreams, caches
them in a possibly-Redis-backed
ListCacheshared across a fleet, rewrites names, and mints errors. Rules addressed to caches, proxies, and intermediaries bind fold and no SDK will implement them for it. This is where real findings live.
The checklist
- Error-code allocation. The revision partitions the JSON-RPC server-error
range:
-32000–-32019implementation-defined (existing SDK usage grandfathered),-32020–-32099reserved for the specification. Read every code fold mints (gateway/upstream.go,gateway/tasks.go) and flag any outside the implementation-defined band as a forward-collision risk. Also confirm fold passes upstream errors through verbatim rather than re-coding them.
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 · 108 lines · 73 tokens per session scan A d62f67748b42
mcp-spec-auditor is an agent published in the GitHub repository fold-run/fold (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 73 tokens to every session and 1,354 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 2026-08-31.
Other agents, from other repositories
graphql-federation-expert
GraphQL schema federation and distributed graph specialist.
issue-tracker
Issues and specs for this repo live as GitHub issues. Use the gh CLI for all operations.
doc-layers
Agent "doc-layers" from SimonGino/portage, covering 文档层级与事实源, 口径层 —— docs/口径层设计.md, 实现层 —— docs/mvp设计草案.md, 页面层 —— 根 design.md and 术语 —— 根 context.md.
reference-repos
本地 /Code/GitHub/ 下的以下几个仓库。涉及协议细节、字段语义、转换坑，先查这里再下结论，不凭记忆；本机上其他 fork 一律不参考。逐文件的路径对照表见 docs/MVP设计草案.md §12。.
domain
Agent "domain" from SimonGino/portage, covering domain docs, 先读, 用术语表的词, 与 adr 冲突就摆出来 and 本仓库补充.
triage-labels
Agent "triage-labels" from SimonGino/portage, covering triage 标签 and 本仓库另有的两个.