Borrowing it
Nothing to install: this file belongs to Wolfe-Jam/mcp-better. 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/Wolfe-Jam/mcp-better/main/AGENTS.mdgit clone --depth 1 https://github.com/Wolfe-Jam/mcp-betterWrote 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/wolfe-jam/mcp-better/agents-md)<a href="https://agentmods.dev/instructions/wolfe-jam/mcp-better/agents-md"><img src="https://agentmods.dev/badge/instructions/wolfe-jam/mcp-better/agents-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/wolfe-jam/mcp-better/agents-md"><img src="https://agentmods.dev/badge/instructions/wolfe-jam/mcp-better/agents-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 | $0.00794 | $0.00794 |
| Opus 5.5 | $0.00318 | $0.00318 |
| Sonnet 5.5 | $0.00159 | $0.00159 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
mcp-better AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
What this is
mcp-better is a Rust MCP server (crate mcp-better), distributed two ways: directly via cargo/crates.io, and via an npm shim (bin/mcp-better.js) that downloads the native binary from GitHub Releases. Rust is the source of truth — the npm package does not reimplement anything.
Three tools: health, echo, confirm_echo. confirm_echo is the interesting one — it demonstrates SEP-2322 MRTR (input_required → client retry) with a sealed, tamper-checked requestState (see src/server.rs).
Build
export PATH="$HOME/.cargo/bin:$PATH"
cargo build --release
Test — two different questions, two different commands
cargo test --all-targets answers "does the code work" — unit tests, including the four confirm_echo round-trip tests co-located in src/server.rs (confirm_echo_round1_input_required, confirm_echo_round2_complete_after_confirm, confirm_echo_rejects_wrong_confirm_text, confirm_echo_rejects_tampered_state).
It does not answer "does the tool still promise what it promised." cargo test --all-targets compiles the examples/ binaries as part of its build but runs zero test functions in them (each reports 0 passed; 0 failed) — the actual contract check only happens if you separately run the binary. That's a distinct, named layer:
cargo run --example mrtr-client— the realconfirm_echocontract check: MRTR round 1→2, sealedrequestStateintegrity, elicitation response shape.cargo run --example contrast-smoke— cross-checks against the siblingmcp-worsebinary (better passes, worse fails, on purpose).cargo run --example order-restart-smoke— two-process ordering check.cargo run --example http-smoke— Streamable HTTP transport check.
⚠️ tests/conformance_smoke.rs, despite its name, only asserts tool-listing metadata (tool order, names, cache TTL). It does not cover confirm_echo's actual request/response contract. A green cargo test is not proof the contract held — do not treat it as one.
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.
- 1mo ago First seen · 48 lines · 794 tokens per session scan A 324e4bb933c4
mcp-better AGENTS.md is an instructions file published in the GitHub repository Wolfe-Jam/mcp-better (2 stars, last pushed 13d ago), licensed MIT. It adds 794 tokens to every session, about $0.0032 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 2026-09-12.
mcp-better AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-better AGENTS.mdWolfe-Jam/mcp-better | Instructions file | 2 | 13d ago | MIT | A | 794 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |