agentleFS
modeled-information-formatmodeled-information-format/mnemonic/skills/blackboard/SKILL.md

blackboard

Skill23 starsChanged 10 months agoMITView on GitHub

Cross-session handoff, persistent context via blackboard, and agent coordination patterns

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. nivoset/skills★ 4same name
    2. Lutra-Fs/blackboard-skill★ 1same name
    3. pinguy/Skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run /mnemonic:list --namespaces to see available namespaces from loaded ontologies.

    line 19

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- BEGIN MNEMONIC PROTOCOL -->

Memory

Search first: /mnemonic:search {relevant_keywords} Capture after: /mnemonic:capture {namespace} "{title}"

Run /mnemonic:list --namespaces to see available namespaces from loaded ontologies.

<!-- END MNEMONIC PROTOCOL -->

Mnemonic Blackboard Skill

Cross-session handoff, persistent context, and agent coordination.

Trigger Phrases

  • "blackboard", "cross-session", "session handoff", "shared context"

Coordination Overview

ScopeMechanismTools
In-sessionClaude Code native swarmTeamCreate, SendMessage, TaskCreate, TaskUpdate
Cross-sessionMnemonic blackboard handoffhandoff/latest-handoff.md via hooks
Persistent knowledgeMnemonic memories*.memory.md files

Path Resolution

MNEMONIC_ROOT=$(tools/mnemonic-paths root)
BLACKBOARD=$(tools/mnemonic-paths blackboard)
HANDOFF_DIR=${BLACKBOARD}/handoff

Directory Structure

${BLACKBOARD}/
├── _legacy/                      # Pre-migration files (frozen)
├── sessions/
│   └── {session_id}/
│       ├── session-notes.md      # Session activity log
│       └── _meta.json            # Session lifecycle metadata
├── handoff/
│   ├── latest-handoff.md         # Cross-session context (overwritten each session end)
│   └── handoff-{session_id}.md   # Archived per-session handoffs
└── .archive/                     # Archived entries

Cross-Session Handoff

How It Works

  1. Session end (hooks/stop.py): Writes summary to handoff/latest-handoff.md
  2. Session start (hooks/session_start.py): Reads handoff/latest-handoff.md to restore context

This is automatic via hooks.

Handoff Format

# Session Handoff

**Session:** {session_id}
**Ended:** {timestamp}
**Project:** {org}/{project}

## What Was Accomplished
- Completed items

## In Progress
- Ongoing work with current state

## Blocked
- Blocker: reason

## Next Steps
- [ ] Action item 1
- [ ] Action item 2

## Important Context
- Key context for next session

Mnemonic Agents

AgentPurposeInvocation
memory-curatorMaintenance, deduplication, decayStandalone or native swarm
mnemonic-search-subcallIterative memory searchSpawned via Task tool
compression-workerMemory summarizationSpawned via Task tool
ontology-discoveryEntity discovery from codebaseSpawned via Task tool

Session Metadata

Each session creates _meta.json:

{
  "session_id": "abc-123",
  "started": "2026-01-15T10:00:00Z",
  "ended": "2026-01-15T11:30:00Z",
  "project": "zircote/mnemonic",
  "org": "zircote",
  "status": "ended"
}

Best Practices

  • Native swarm for in-session work — don't write coordination state to blackboard
  • Let hooks handle handoff — session lifecycle hooks manage cross-session context automatically
  • Memories for persistence — if something should survive beyond the next session, capture it as a memory
  • Keep handoffs actionable — focus on what the next session needs to continue work

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.