handbag_agent_architecture SKILL.md skillB

handbag_agent_architecture from parisneo/lollms_client is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add parisneo/lollms_client/handbag_agent_architecture@git:20261103.92f9bc1

Pins git:20261103.92f9bc1 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
parisneo/lollms_client
Path
skills/handbag_agent_architecture/SKILL.md
Versions recorded
3
Latest version
git:20261103.92f9bc1, committed Nov 3, 2026
First version recorded
Sep 22, 2026
Size
7,332 bytes
Repository stars
13
License
Apache-2.0

Definitive architectural doctrine for building sovereign agent Handbags, crafting SOUL.md personalities, injecting app-level tools and skills, and inspecting agent state.

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

# Handbag Agent Architecture & Persona Engineering

## 7. Round Checkpointing and Turn Resumption
Agents support state persistence across unexpected interruptions or pauses:
- Each round automatically saves a turn checkpoint (`.lollms_code/turn_checkpoint.json` in workspaces, or `ai_msg.metadata["turn_checkpoint"]` in discussions).
- To resume an interrupted turn, call `agent.resume_turn()` or pass `resume_turn=True` to `agent.chat()`. Virtual history, tool calls, and round numbers will be restored without starting from scratch.

The **Handbag** is the sovereign, self-contained portable directory specification in LOLLMS. It encapsulates an agent's identity, system prompt, specialized tools, persistent cognitive memories, learned skills, and coworker multi-agent teams.

---

## 1. Handbag Directory Layout

```
my_specialist_agent/
├── SOUL.md                  # Primary persona identity (YAML frontmatter + Markdown body)
├── handbag.yaml             # Optional settings manifest (skills mode, memory policy)
├── coworkers/               # Sub-agent teams (Crew Handbag)
│   ├── backend_coder/
│   │   └── SOUL.md
│   └── security_auditor/
│       └── SOUL.md
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add parisneo/lollms_client/handbag_agent_architecture@sha256:3623bee1a0855c9d

The line at the top of this page pins the label git:20261103.92f9bc1, 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_lirwtfcnxwe36x2y.svg)](https://markdownregistry.com/a/art_lirwtfcnxwe36x2y)

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

Versions

The registry has recorded 3 versions of this file, between Sep 22, 2026 and Nov 3, 2026, about one every 21 days.

versioncommittedcommitsizeaudit
git:20261103.92f9bc1 latest2026-11-03 92f9bc1 7,332 BB view · diff
git:20260928.96e9de42026-09-28 96e9de4 6,235 BB view · diff
git:20260922.2bfcb5b2026-09-22 2bfcb5b 5,750 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: Frontmatter declares a name
  • pass: Frontmatter block present
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7332 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

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

parisneo/lollms_client · 13 stars · license Apache-2.0 · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_lirwtfcnxwe36x2y
GET https://markdownregistry.com/api/v1/resolve?ref=parisneo/lollms_client/handbag_agent_architecture
GET https://markdownregistry.com/api/v1/blob/3623bee1a0855c9d5c2d14b05dcd2543a2eb8dde86e048bb85e34679f19cc16d

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 parisneo/lollms_client

Lollms Artifacts and Surgical Patching SKILL.md skill
parisneo/lollms_client · skills/artifacts_and_patching/SKILL.md · Teaches the model how to formulate strategic <coding_plan> blocks, apply indentation-agnostic Aider search/replace…
v1.0.0 · audit A · 13 stars
assumption_fixing_and_rapid_execution SKILL.md skill
parisneo/lollms_client · skills/assumption_fixing_and_rapid_execution/SKILL.md
git:20261013.137c2c2 · audit C · 13 stars
async_multi_agent_coordination SKILL.md skill
parisneo/lollms_client · skills/async_multi_agent_coordination/SKILL.md · Patterns and Python implementations for spawning multiple asynchronous worker instances, coordinating them via atomic…
git:20260920.17e6935 · audit B · 13 stars
bibliography_and_research SKILL.md skill
parisneo/lollms_client · skills/bibliography_and_research/SKILL.md · Methodology for searching academic papers, extracting citations, structuring bibliographies, and synthesizing research…
git:20260928.96e9de4 · audit A · 13 stars
canvas_tts_video_recording SKILL.md skill
parisneo/lollms_client · skills/canvas_tts_video_recording/SKILL.md
git:20260827.208f16d · audit C · 13 stars
client_creation_and_profiles SKILL.md skill
parisneo/lollms_client · skills/client_creation_and_profiles/SKILL.md · Authoritative doctrine for configuring and instantiating LollmsClient across all modalities using the Two-Tier Profile…
git:20260924.391072e · audit B · 13 stars
Lollms Cognitive Persistent Memory SKILL.md skill
parisneo/lollms_client · skills/cognitive_memory/SKILL.md · Teaches the model about the persistent tiered memory system (Level 1 Working, Level 2 Deep, Level 3 Archive), proactive…
v1.0.0 · audit A · 13 stars
LoLLMS Connection Bindings SKILL.md skill
parisneo/lollms_client · skills/connection_bindings/SKILL.md · Teaches how to use LoLLMS connection bindings to send messages to communication services (Discord, Telegram, Slack…
v1.0.0 · audit A · 13 stars
deep_websearch_and_extraction SKILL.md skill
parisneo/lollms_client · skills/deep_websearch_and_extraction/SKILL.md · Protocol for multi-source web searches, page content scraping, evidence corroboration, and factual synthesis.
git:20260928.96e9de4 · audit A · 13 stars
desktop_automation SKILL.md skill
parisneo/lollms_client · skills/desktop_automation/SKILL.md · Vision-driven desktop automation loop for inspecting screens, locating UI elements, typing, and clicking.
git:20260928.96e9de4 · audit A · 13 stars
Lollms Discussion and Chat SKILL.md skill
parisneo/lollms_client · skills/discussion_and_chat/SKILL.md · Teaches the model how to manage stateful discussions, track conversational trees/branches, navigate alternative sibling…
v1.0.0 · audit A · 13 stars
document_analysis_and_extraction SKILL.md skill
parisneo/lollms_client · skills/document_analysis_and_extraction/SKILL.md · In-depth workflow for extracting text, tables, schemas, and applying corrections or comments to PDF, Word, Excel, and…
git:20261103.d81e853 · audit A · 13 stars

Every file in parisneo/lollms_client

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