durable-state-patterns SKILL.md skillA

durable-state-patterns from latestaiagents/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add latestaiagents/agent-skills/durable-state-patterns@git:20261104.9adbc3a

Pins git:20261104.9adbc3a in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
latestaiagents/agent-skills
Path
plugins/agent-architect/skills/langgraph/durable-state-patterns/SKILL.md
Versions recorded
2
Latest version
git:20261104.9adbc3a, committed Nov 4, 2026
First version recorded
Feb 5, 2026
Size
11,429 bytes
Repository stars
6
License
MIT

Implement persistent agent state that survives failures and restarts. Use this skill when building stateful agents, implementing checkpointing, persisting agent memory across sessions, or recovering from failures. Activate when: durable state, agent persistence, checkpointing, agent recovery, stateful agents, state persistence, cross-session memory, agent restart.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Durable State Patterns

**Build agents that remember state across failures, restarts, and sessions.**

## Why Durable State?

Without durability:
- Long-running agents lose progress on crash
- Users can't resume conversations after timeout
- No audit trail of agent decisions
- Expensive recomputation on every restart

With durability:
- Resume from any checkpoint
- Survive infrastructure failures
- Debug by replaying history
- Share state across instances

## LangGraph Checkpointing

### Basic Setup

```python
from langgraph.graph import StateGraph
from langgraph.checkpoint.memory import MemorySaver
from langgraph.checkpoint.sqlite import SqliteSaver
from langgraph.checkpoint.postgres import PostgresSaver

# In-memory (development only)
memory_checkpointer = MemorySaver()

# SQLite (single instance)
sqlite_checkpointer = SqliteSaver.from_conn_string("checkpoints.db")

# PostgreSQL (production, multi-instance)
postgres_checkpointer = PostgresSaver.from_conn_string(
    "postgresql://user:pass@localhost/db"
)

# Compile with checkpointer
app = workflow.compile(checkpointer=postgres_checkpointer)
```

### Thread-Based State

```python
from uuid import uuid4
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add latestaiagents/agent-skills/durable-state-patterns@sha256:a06b146dee38a318

The line at the top of this page pins the label git:20261104.9adbc3a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_pdapexbqkvdxqmci.svg)](https://markdownregistry.com/a/art_pdapexbqkvdxqmci)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Feb 5, 2026 and Nov 4, 2026, about one every 272 days.

versioncommittedcommitsizeaudit
git:20261104.9adbc3a latest2026-11-04 9adbc3a 11,429 BA view · diff
git:20260205.a0b87802026-02-05 a0b8780 11,424 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (11429 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

GitHub

latestaiagents/agent-skills · 6 stars · license MIT · pushed 2026-11-04 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_pdapexbqkvdxqmci
GET https://markdownregistry.com/api/v1/resolve?ref=latestaiagents/agent-skills/durable-state-patterns
GET https://markdownregistry.com/api/v1/blob/a06b146dee38a31836b60f43bd3d21346b27f87873f42a21d09d32da99cd0f15

Your AI assistant 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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from latestaiagents/agent-skills

CLAUDE.md CLAUDE.md file
latestaiagents/agent-skills · CLAUDE.md
git:20261104.63d994b · audit B · 6 stars
agent-checkpointing SKILL.md skill
latestaiagents/agent-skills · plugins/agent-architect/skills/langgraph/agent-checkpointing/SKILL.md · Implement checkpointing for agent recovery, debugging, and replay. Use this skill when building recoverable agents…
git:20260205.a0b8780 · audit A · 6 stars
langgraph-workflows SKILL.md skill
latestaiagents/agent-skills · plugins/agent-architect/skills/langgraph/langgraph-workflows/SKILL.md · Build agent workflows with LangGraph 1.0 state machines and graph patterns. Use this skill when creating agent graphs…
git:20261104.9adbc3a · audit A · 6 stars
a2a-protocols SKILL.md skill
latestaiagents/agent-skills · plugins/agent-architect/skills/patterns/a2a-protocols/SKILL.md · Implement Agent-to-Agent (A2A) communication for cross-framework interoperability. Use this skill when building…
git:20261104.9adbc3a · audit A · 6 stars
agent-error-recovery SKILL.md skill
latestaiagents/agent-skills · plugins/agent-architect/skills/patterns/agent-error-recovery/SKILL.md · Use this skill when implementing error handling for AI agents. Activate when the user needs agents to handle failures…
git:20260205.a0b8780 · audit A · 6 stars
agent-handoff-protocols SKILL.md skill
latestaiagents/agent-skills · plugins/agent-architect/skills/patterns/agent-handoff-protocols/SKILL.md · Use this skill when designing task handoffs between agents. Activate when the user needs to pass work between agents…
git:20260205.a0b8780 · audit A · 6 stars
agent-memory-systems SKILL.md skill
latestaiagents/agent-skills · plugins/agent-architect/skills/patterns/agent-memory-systems/SKILL.md · Use this skill when implementing memory for AI agents. Activate when the user needs agents to remember past…
git:20260205.a0b8780 · audit A · 6 stars
agent-mesh-architecture SKILL.md skill
latestaiagents/agent-skills · plugins/agent-architect/skills/patterns/agent-mesh-architecture/SKILL.md · Use this skill when designing peer-to-peer multi-agent systems. Activate when the user needs agents that collaborate…
git:20260205.a0b8780 · audit A · 6 stars
agent-supervisor-pattern SKILL.md skill
latestaiagents/agent-skills · plugins/agent-architect/skills/patterns/agent-supervisor-pattern/SKILL.md · Use this skill when designing supervisor-based multi-agent systems. Activate when the user needs to orchestrate…
git:20260205.a0b8780 · audit A · 6 stars
agent-tool-routing SKILL.md skill
latestaiagents/agent-skills · plugins/agent-architect/skills/patterns/agent-tool-routing/SKILL.md · Use this skill when implementing tool selection for AI agents. Activate when the user needs agents to choose the right…
git:20261104.9adbc3a · audit A · 6 stars
human-in-loop-agents SKILL.md skill
latestaiagents/agent-skills · plugins/agent-architect/skills/patterns/human-in-loop-agents/SKILL.md · Build agents that pause for human approval, review, and intervention. Use this skill when implementing approval…
git:20260205.a0b8780 · audit A · 6 stars
agent-testing-harness SKILL.md skill
latestaiagents/agent-skills · plugins/agent-architect/skills/testing/agent-testing-harness/SKILL.md · Use this skill when testing AI agent systems. Activate when the user needs to test agent behavior, write tests for…
git:20260205.a0b8780 · audit A · 6 stars

Every file in latestaiagents/agent-skills

Browse by kind, by grade A, or by owner.