blackboard

A command for reading or writing a shared key-value store used by Network-AI agents. A blackboard is a shared place where agents record information for one another.

In plain words
What is it for?
Listing stored keys, reading one key, or writing a value and confirming that the update was saved.
Why use it?
It lets agents inspect shared project state or update it while retaining ownership and audit information.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/jovancoding/network-ai/blackboard
Clone the repo
git clone --depth 1 https://github.com/Jovancoding/Network-AI
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 135 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00016 $0.00135
Opus 5 $0.00008 $0.00068
Sonnet 5 $0.00003 $0.00027
Haiku 4.5 $0.00002 $0.00014

Measured 2d ago against content hash d507ab9f1778, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

blackboard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/blackboard.md · 14 lines

What it actually says

Work with the Network-AI shared blackboard using the loaded MCP tools.

Arguments given: $ARGUMENTS

  • If no arguments: call blackboard_list and show all keys with their owners.
  • If one argument (a key): call blackboard_read and show the value plus metadata.
  • If two arguments (key + value): call blackboard_write with agent_id: "claude-code", then confirm the write by reading it back.

Remember every write is identity-verified, namespace-scoped, and audit-logged.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 14 lines · 16 tokens per session scan A d507ab9f1778

Subscribe to this mod's changes

blackboard is a command published in the GitHub repository Jovancoding/Network-AI (72 stars, last pushed 8d ago), licensed MIT. It adds 16 tokens to every session and 135 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.