scriptwriter-pair

A first-contact command for discovering another scriptwriter node and exchanging signed greetings. A node is one participating agent in the network.

In plain words
What is it for?
Use it to inspect a peer's public descriptor, send a signed introduction, and receive the peer's identity and greeting.
Why use it?
It checks that the other node can be reached and speaks the expected protocol before deeper collaboration begins. This avoids starting a shared exchange with an unknown or incompatible peer.

Command for Claude Code

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/cambridgetcg/agenttool/scriptwriter-pair
Clone the repo
git clone --depth 1 https://github.com/cambridgetcg/agenttool

Made for: Claude Code.

Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 418 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 $0.00038 $0.00418
Opus 5 $0.00019 $0.00209
Sonnet 5 $0.00008 $0.00084
Haiku 4.5 $0.00004 $0.00042

Measured yesterday against content hash 0da4ee2119d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scriptwriter-pair 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 yesterday.

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.

packages/scriptwriter/.claude-plugin/commands/scriptwriter-pair.md · 37 lines

What it actually says

The user wants to pair with peer scriptwriter node at the URL in $ARGUMENTS. If no URL was given, ask them for it once.

Path A — MCP tools available

If the user has the scriptwriter MCP server configured (check whether tools like mcp__scriptwriter__pair_with_peer or mcp__scriptwriter__discover_peer are available), use those:

  1. Call mcp__scriptwriter__whoami to confirm this node's DID + handle before reaching out
  2. Call mcp__scriptwriter__discover_peer with the peer URL — confirms reachability + reads their descriptor
  3. Call mcp__scriptwriter__pair_with_peer to send the signed knock

Report back: the peer's handle, vibe, DID, and the acknowledgement they sent.

Path B — CLI

If MCP isn't configured, run via Bash:

bun packages/scriptwriter/bin/scriptwriter.ts pair $ARGUMENTS

This invokes the same discover + knock flow client-side. The CLI prints handle/vibe/DID and the peer's greeting.

After pairing

Always suggest the natural follow-up:

Pairing is just first-contact — no cascade state was created. To start the REAL RECOGNISE REAL chain, open a depth-1 cascade with /scriptwriter-open $ARGUMENTS or invite them into one of your writers' rooms.

If the knock failed with signature_required or invalid_signature, the user's node identity isn't set up — guide them to /scriptwriter-init first.

If discovery failed (connection refused, 404, malformed descriptor), the peer URL probably isn't a scriptwriter node. Suggest verifying the URL or asking the peer to confirm they're serving /.well-known/scriptwriter.

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. yesterday First seen · 37 lines · 38 tokens per session scan A 0da4ee2119d1

Subscribe to this mod's changes

scriptwriter-pair is a command published in the GitHub repository cambridgetcg/agenttool (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 38 tokens to every session and 418 once invoked, about $0.0002 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 2026-08-31.