ml4t-agent-tool-contracts skillA
ml4t-agent-tool-contracts is agent-read markdown (skill) from ml4t/skills: Typed tool contracts for autonomous research agents. Use when exposing files, search, databases, or execution tools to an LLM agent..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Agent Tool Contracts
An agent tool is an API boundary, not a prompt convenience. Every tool needs a typed input schema, a narrow execution policy, and a result object that records provenance.
## The Problem
LLM agents fail badly when tools accept vague strings and return unstructured text. The model cannot distinguish stale search results from fresh ones, allowed paths from forbidden paths, or recoverable tool errors from final evidence. Worse, a prompt-injected page can ask the agent to call another tool unless the execution layer enforces policy outside the model.
## The Pattern
### WRONG
```python
def run_tool(name: str, args: str) -> str:
if name == "read_file":
return open(args).read()
if name == "search":
return web_search(args)
raise ValueError(name)
```
### CORRECT
```python
from dataclasses import dataclass
from pathlib import Path
from typing import Any
@dataclass(frozen=True)
class ToolResult:
ok: bool
value: Any
source: str
observed_at: str
policy: str
def read_file(path: str, root: Path) -> ToolResult:
requested = Path(path).expanduser().resolve()
allowed = root.resolve()
…Read the whole file at its exact version.
How to install
mdr add ml4t/skills/ml4t-agent-tool-contracts@git:20260901.c415df0mdr add ml4t/skills/ml4t-agent-tool-contracts@sha256:31952cae1e6e0acdPin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_ois75sdbcmoxikd4)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260901.c415df0 latest | 2026-09-01 | c415df0 | 3,346 B | A | view · diff |
| git:20260528.303089e | 2026-05-28 | 303089e | 3,359 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3346 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
ml4t/skills · 19 stars · license Apache-2.0 · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ois75sdbcmoxikd4 GET https://markdownregistry.com/api/v1/resolve?ref=ml4t/skills/ml4t-agent-tool-contracts GET https://markdownregistry.com/api/v1/blob/31952cae1e6e0acdcc722ce144b91296622e23fa2a0a8f14a172643ce3fa5c53
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.