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
- nivoset/skillstheir own version, first seen Oct 18, 2026
- Lutra-Fs/blackboard-skilltheir own version, first seen Oct 11, 2026
- pinguy/Skillstheir own version, first seen Sep 17, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- nivoset/skills★ 4same name
- Lutra-Fs/blackboard-skill★ 1same name
- 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.
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
- Very specific: line 19
Run /mnemonic:list --namespaces to see available namespaces from loaded ontologies.
“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.
Files
<!-- 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
| Scope | Mechanism | Tools |
| In-session | Claude Code native swarm | TeamCreate, SendMessage, TaskCreate, TaskUpdate |
| Cross-session | Mnemonic blackboard handoff | handoff/latest-handoff.md via hooks |
| Persistent knowledge | Mnemonic memories | *.memory.md files |
Path Resolution
MNEMONIC_ROOT=$(tools/mnemonic-paths root)
BLACKBOARD=$(tools/mnemonic-paths blackboard)
HANDOFF_DIR=${BLACKBOARD}/handoffDirectory 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 entriesCross-Session Handoff
How It Works
- Session end (
hooks/stop.py): Writes summary tohandoff/latest-handoff.md - Session start (
hooks/session_start.py): Readshandoff/latest-handoff.mdto 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 sessionMnemonic Agents
| Agent | Purpose | Invocation |
memory-curator | Maintenance, deduplication, decay | Standalone or native swarm |
mnemonic-search-subcall | Iterative memory search | Spawned via Task tool |
compression-worker | Memory summarization | Spawned via Task tool |
ontology-discovery | Entity discovery from codebase | Spawned 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
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
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.

