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 instructions/fold-run/fold/claude-mdgit 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/instructions/fold-run/fold/claude-md)<a href="https://agentmods.dev/instructions/fold-run/fold/claude-md"><img src="https://agentmods.dev/badge/instructions/fold-run/fold/claude-md.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 | $0.02330 | $0.02330 |
| Opus 5 | $0.01165 | $0.01165 |
| Sonnet 5 | $0.00466 | $0.00466 |
| Haiku 4.5 | $0.00233 | $0.00233 |
Grade A, and why
fold CLAUDE.md 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 3d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
This repo is fold, the enterprise MCP gateway — one governed endpoint federating any number of upstream MCP servers into a single virtual server, adding auth, policy, caching, rate limiting, and audit. Single Go module; the Makefile is a thin wrapper over the Go toolchain and is the source of truth for dev/CI commands. The wire protocol (streamable HTTP, request/response and SSE) is the official MCP Go SDK's implementation on both the client-facing and upstream-facing sides — fold never hand-rolls protocol framing.
Commands
make build
make test # unit + integration (real SDK client/server fixtures)
make race # what CI runs
make lint # golangci-lint (config in .golangci.yml)
make check # fmt-check + tidy-check + vet + build + race + lint
go test ./gateway -run TestName -v # one test
make bench # latency gate (FOLD_BENCH=1; skipped without it)
make conformance # official MCP conformance suite through the gateway (needs node/npx)
# Federation cost — the list path, whose work scales with federation size and
# which the latency gate's 1-upstream fixture does not exercise:
go test ./gateway -run '^$' -bench BenchmarkFederatedListTools -benchmem
FOLD_LOAD_UPSTREAMS=20 FOLD_LOAD_TOOLS=50 make loadtest
# Tenant resolution cost, whose work scales with the number of tenant
# declarations rather than with the federation:
go test ./gateway -run '^$' -bench BenchmarkResolveTenant -benchmem
CI (.github/workflows/ci.yml) gates every merge on: gofmt, go mod tidy -diff, vet, build, go test -race, golangci-lint, govulncheck, the added-latency benchmark (added p50 < 5 ms through the proxy path), and the conformance suite (40/40 checks, pinned to a commit in scripts/conformance.sh — bump deliberately).
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.
- 3d ago First seen · 64 lines · 2,330 tokens per session scan A e15a8a548957
fold CLAUDE.md is an instructions file published in the GitHub repository fold-run/fold (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,330 tokens to every session, about $0.0117 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 instructions, from other repositories
zentinel AGENTS.md
Instructions for zentinelproxy/zentinel, covering zentinel, philosophy (north star), architecture, crates and core crates.
hotplex AGENTS.md
Instructions for hrygo/hotplex, covering hotplex 项目知识库, 约定与规范, 必须遵守, 反模式（禁止） and 代码编辑规则.
cortex-gateway AGENTS.md
Instructions for wellknownmcp/cortex-gateway, covering agents.md, what this is, verify the claims yourself, the demo authorization server builds independently and protected-resource metadata (rfc 9728).
genefoundry-router AGENTS.md
Instructions for berntpopp/genefoundry-router, covering agents.md, what this project is, required check before handoff, coding standards and project-specific guidance.
genefoundry-router CLAUDE.md
Instructions for berntpopp/genefoundry-router, a project described as: MCP gateway federating 21 biomedical MCP servers — gnomAD, ClinVar, HPO, UniProt, Ensembl VEP, PanelApp and more — behind one Streamable-HTTP endpoint, with collision-free namespaced tools and BM25 tool search.
portage AGENTS.md
AGENTS.md instructions for SimonGino/portage, covering portage, 构建与测试, 与 po 协作, 事实源：查什么去哪 and 硬约束.