Borrowing it
Nothing to install: this file belongs to theshadow27/mcp-cli. 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/theshadow27/mcp-cli/main/CLAUDE.mdgit clone --depth 1 https://github.com/theshadow27/mcp-cliWrote 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/theshadow27/mcp-cli/claude-md)<a href="https://agentmods.dev/instructions/theshadow27/mcp-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/theshadow27/mcp-cli/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/theshadow27/mcp-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/theshadow27/mcp-cli/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 | $0.04225 | $0.04225 |
| Opus 5.5 | $0.01690 | $0.01690 |
| Sonnet 5.5 | $0.00845 | $0.00845 |
| Haiku 4.5 | $0.00422 | $0.00422 |
Grade A, and why
mcp-cli CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 18d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **No shell interpolation**: never pass template literals with `${}` to `execSync` or `execFileSync` — use `spawnSync("cmd", [...args])` instead. How it starts
The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
MCP CLI — Model Context Preservation - call MCP server tools from the command line with zero context overhead, delegate to other Claude Code instances, and monitor operations.
Quick Reference
Validation: bun run am-i-done
bun run am-i-done is the single command for checking whether work is done — run it
before committing. It runs typecheck, lint, the standalone arch checks (args-bounds,
timeouts, teardown, phase-drift), and the full doing-it-wrong rule sweep, then tests and
the coverage ratchet — in the optimal order, silent-first with clear output on failure. It
is the same command the pre-commit hook and CI both run, so a local pass means a green
PR; running a subset is how violations slip through. In a Claude/agent context it captures
step output to build/am-i-done-<ts>.txt and surfaces only the path on failure (protects
context budget).
bun run am-i-done # full check: typecheck → lint → rules → tests → coverage
bun run am-i-done --pre-commit # fast static subset (no tests/coverage) — what the hook runs
Run the individual steps only to diagnose a specific am-i-done failure or iterate on
one concern — not as a substitute for the full check:
bun install # install deps
bun typecheck # bun check --all (Bun's native TS7-compatible checker; don't call tsc directly)
bun lint # biome check + format (may reformat files — re-read after)
bun run doing-it-wrong # architecture rule sweep only (see Rules below)
bun test # run tests
bun build # compile binaries to dist/
# Development
bun dev:daemon # run daemon directly
bun dev:mcx -- ls # run CLI directly
bun dev:mcx -- call atlassian search '{"query":"test"}'
bun <script> is interchangeable with bun run <script> for scripts that don't clash with native bun verbs.
Architecture
packages/
core/ → Shared types, IPC protocol, config types, env expansion
daemon/ → mcpd: background daemon managing MCP server connections
command/ → mcx: fast CLI that talks to daemon via Unix socket
control/ → mcpctl: TUI for daemon status and auth management
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.
- 18d ago Changed · +40 tokens per session 87489c7637d5
- 2mo ago First seen · 243 lines · 4,185 tokens per session scan A 9d4f437a41f4
mcp-cli CLAUDE.md is an instructions file published in the GitHub repository theshadow27/mcp-cli (2 stars, last pushed 3d ago), licensed MIT. It adds 4,225 tokens to every session, about $0.0169 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.