ml4t-agent-state-memory skillA
ml4t-agent-state-memory is agent-read markdown (skill) from ml4t/skills: Durable agent state, memory, and replay for autonomous research workflows. Use when an agent must resume, audit, or compare multi-step runs..
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 State and Memory
Agent memory should be an explicit state object that can be serialized, replayed, and inspected. Chat history is not enough because it loses typed evidence, tool provenance, and quality gate status.
## The Problem
Long-running research agents make dozens of tool calls and intermediate judgments. If the only memory is the prompt transcript, the run cannot be resumed safely, audited by a reviewer, or compared against an ablation. The agent may also reuse stale claims because evidence has no timestamp or source boundary.
## The Pattern
### WRONG
```python
messages = []
messages.append({"role": "user", "content": task})
while True:
answer = llm(messages)
messages.append(answer)
if "done" in answer["content"].lower():
break
```
### CORRECT
```python
from dataclasses import asdict, dataclass, field
from pathlib import Path
from typing import Any
import json
@dataclass
class AgentState:
task: str
evidence: list[dict[str, Any]] = field(default_factory=list)
tool_trace: list[dict[str, Any]] = field(default_factory=list)
decisions: list[dict[str, Any]] = field(default_factory=list)
…Read the whole file at its exact version.
How to install
mdr add ml4t/skills/ml4t-agent-state-memory@git:20260901.c415df0mdr add ml4t/skills/ml4t-agent-state-memory@sha256:60bfe217a86a136cPin 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_w5vwpc7u6wgvqo4x)
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 | 3,355 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_w5vwpc7u6wgvqo4x GET https://markdownregistry.com/api/v1/resolve?ref=ml4t/skills/ml4t-agent-state-memory GET https://markdownregistry.com/api/v1/blob/60bfe217a86a136c0229b284a64d3aa1cfa3106922835a831ed156f7ec705fce
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.