Borrowing it
Nothing to install: this file belongs to manifest-network/manifest-mcp-mono. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/manifest-network/manifest-mcp-mono/main/CLAUDE.mdgit clone --depth 1 https://github.com/manifest-network/manifest-mcp-monoWrote 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/manifest-network/manifest-mcp-mono/claude-md)<a href="https://agentmods.dev/instructions/manifest-network/manifest-mcp-mono/claude-md"><img src="https://agentmods.dev/badge/instructions/manifest-network/manifest-mcp-mono/claude-md/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/instructions/manifest-network/manifest-mcp-mono/claude-md"><img src="https://agentmods.dev/badge/instructions/manifest-network/manifest-mcp-mono/claude-md.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 | $0.09512 | $0.09512 |
| Opus 5 | $0.04756 | $0.04756 |
| Sonnet 5 | $0.01902 | $0.01902 |
| Haiku 4.5 | $0.00951 | $0.00951 |
Grade A, and why
manifest-mcp-mono 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 today.
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 — 162 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.
Commands
npm run build # Build all packages (tsdown, unbundled ESM)
npm run lint # Type-check all workspace packages (tsc --noEmit)
npm run test # Unit tests all packages (vitest)
npm run check # Lint, format, and import sorting check, including e2e TypeScript
npm run check:fix # Auto-fix biome issues
npm run format # Format all packages via biome
npm run lint:e2e # Rebuild dependencies, then type-check e2e; CI runs it as a named gate
npm run test:e2e:annotations # PR-safe live MCP metadata matrix (run after build; no compose devnet)
npm run check:workflows # Immutable action pins + workflow permissions; CI and release run it
npm run check:dependency-hygiene # Validator resolution + E2E gate decision regressions (ENG-768)
npm run audit:dependencies # Full locked dependency graph; high/critical findings fail CI/release
npm run depcruise # Architecture boundary + package-DAG guard (dependency-cruiser); CI runs it
npm run size # Bundle-size budgets for the SDK subpaths (size-limit); CI runs it
npm run check:packages # Dry-run npm packs; reject test/runtime vendoring + undeclared SDK d.ts imports
npm run test:types -w @manifest-network/manifest-sdk # SDK type-tripwire (.test-d.ts); CI runs it
npm run build -w @manifest-network/sdk-acceptance # then the browser-build gate below; CI runs both
npx vitest run examples/sdk-acceptance/scripts/browser-build.test.ts # browser resolution + /reads leak guard
npm run test:e2e # E2E tests against live chain (requires docker-compose up)
# Per-package (run from packages/core, packages/chain, packages/lease, packages/fred, packages/cosmwasm, or packages/node)
npm run build # tsdown
npm run lint # tsc --noEmit
npm run test # vitest run
npm run test:watch # vitest (watch mode)
# Single test file — runtime or .test-d.ts, from the root or via the owning workspace. The root
# vitest.config.mts delegates to each package's config, so both forms type-check a type test
# (before ENG-648 a root run used Vitest's defaults: a bare run found no test files, and
# `--typecheck` pointed tsc at the references-only root tsconfig.json with `files: []`, so
# every assertion passed with zero analysis). Cross-package type tests (sdk, agent-core, fred)
# resolve siblings through dist, so build first.
npx vitest run packages/core/src/cosmos.test.ts
npx vitest run packages/core/src/manifest-types.test-d.ts
npm run test -w @manifest-network/manifest-mcp-core -- src/manifest-types.test-d.ts
npm run check:type-tests # root type-test harness: known-bad probe must fail + coverage guards; CI runs it
# E2E setup (first prepare Linux/XFS project quotas: docs/e2e-setup.md)
npm run check:e2e-env
docker compose -f e2e/docker-compose.yml up -d --wait --wait-timeout 180
npm run test:e2e
docker compose -f e2e/docker-compose.yml down -v --remove-orphans
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.
- today Changed · +179 tokens per session 3665fc5669a4
- yesterday Changed · +1 lines · +149 tokens per session 1063ad0c011a
- 2d ago Changed · +3 lines · +114 tokens per session 3f1f752693ea
- 7d ago Changed · +16 lines · +635 tokens per session 4b00052a0407
- 11d ago First seen · 142 lines · 8,435 tokens per session scan A 3f8c99c6dbb2
manifest-mcp-mono CLAUDE.md is an instructions file published in the GitHub repository manifest-network/manifest-mcp-mono (0 stars, last pushed today), licensed MIT. It adds 9,512 tokens to every session, about $0.0476 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).