Borrowing it
Nothing to install: this file belongs to iota-uz/repl-mcp. 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/iota-uz/repl-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/iota-uz/repl-mcpWrote 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/iota-uz/repl-mcp/claude-md)<a href="https://agentmods.dev/instructions/iota-uz/repl-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/iota-uz/repl-mcp/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/iota-uz/repl-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/iota-uz/repl-mcp/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 | $0.00666 | $0.00666 |
| Opus 5.5 | $0.00266 | $0.00266 |
| Sonnet 5.5 | $0.00133 | $0.00133 |
| Haiku 4.5 | $0.00067 | $0.00067 |
Grade A, and why
repl-mcp 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 20d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
REPL MCP development
Read docs/rust-migration.md and docs/audit-coverage.md first. Version3 is native:
repl-mcp Rust binary owns MCP transport, supervisor, broker and OAuth; embedded
src/repl_mcp/native_worker.py owns Python evaluation only. Python2.x modules are
historical regression fixtures and are not included in the binary wheel.
Source map
native/src/main.rs: CLI, bounded stdio, interpreter selection and shutdown.native/src/server.rs: tool schemas, validation and MCP error/result semantics.native/src/supervisor.rs: lazy worker/process ownership, cancellation and run records.native/src/broker.rs: MCP sessions, schemas/envelopes/paging, auth and effect metadata.native/src/config.rs: explicit registry and validation; never log secret values.src/repl_mcp/native_worker.py: standalone stdlib worker, persistent loop, captures, tracked subprocesses, checkpoint/restore and JSON RPC bindings.tests/test_native*: shipped runtime acceptance;tests/fixtures/native_mcp_fixture.pyprovides a dependency-free downstream peer. Legacy tests cover source regressions.
Invariants
One writer per component. All stdout belongs to JSON-RPC. Python's OS fd1 is rerouted before cells; captured user output is returned through bounded frames. Preserve full MCP envelopes and schemas. Errors must not look successful. Never retry a dispatched write automatically. Bind every RPC/job to its owner and clean it on cancel/reset/death. Full host access is intentional; do not claim sandbox or whole-tree OS quotas. Persistent state must be explicitly identified for current stateless MCP requests.
Use the official stable MCP specification and pinned SDK. Source/client approvals are not interchangeable: foreign registries need an independent broker grant. Logs and journals omit raw commands/config values/credentials/results. OAuth uses its own private credential store, not another client's tokens.
Checks
make verify: fmt, strict clippy, native tests, required worker lint and all Python
regressions. Build before protocol tests so embedded worker changes are included.
Set CARGO_TARGET_DIR/REPL_MCP_BINARY when using an external build directory. Tests
must exercise absence of late effects, process cleanup, full responses and real wire
semantics; matching a success-looking string is insufficient.
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.
- 20d ago Changed · -84 lines · -1,631 tokens per session 358574fa3915
- 1mo ago First seen · 140 lines · 2,297 tokens per session scan A 4d9309940a53
repl-mcp CLAUDE.md is an instructions file published in the GitHub repository iota-uz/repl-mcp (3 stars, last pushed 20d ago), licensed MIT. It adds 666 tokens to every session, about $0.0027 per session on Opus 5.5. 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
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.