Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cambridgetcg/agenttoolnpx agentmods add commands/cambridgetcg/agenttool/scriptwriter-statusWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/cambridgetcg/agenttool/scriptwriter-status)<a href="https://agentmods.dev/commands/cambridgetcg/agenttool/scriptwriter-status"><img src="https://agentmods.dev/badge/commands/cambridgetcg/agenttool/scriptwriter-status/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/cambridgetcg/agenttool/scriptwriter-status"><img src="https://agentmods.dev/badge/commands/cambridgetcg/agenttool/scriptwriter-status.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.00441 |
| Opus 5.5 | $0.00021 | $0.00176 |
| Sonnet 5.5 | $0.00010 | $0.00088 |
| Haiku 4.5 | $0.00005 | $0.00044 |
Grade A, and why
scriptwriter-status scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sS http://localhost:7777/rrr/cascades | jq What it actually says
The user wants a status snapshot.
Path A — MCP tools available
Run these MCP calls in parallel and assemble a single tidy report:
mcp__scriptwriter__whoami— identitymcp__scriptwriter__list_cascades(no status filter) — all cascadesmcp__scriptwriter__list_rooms— all local rooms
Render like:
who : <handle> · vibe <vibe> · <did short>
since : <created_at>
cascades : <N total>
· <cascade short id> with <peer short did> depth <D>/<49> <emoji ladder>
<"your turn" | "their turn" | "capped 💛">
· ...
rooms : <N total>
· <room name> (<contributions count> contributions) vibe <room.vibe>
· ...
Highlight cascades where your_turn: true — those need the user's attention.
Highlight rooms with recent contributions (compare to room.created_at).
Path B — CLI
Call the same endpoints over HTTP if MCP isn't configured but the server is running:
bun packages/scriptwriter/bin/scriptwriter.ts whoami
curl -sS http://localhost:7777/rrr/cascades | jq
curl -sS http://localhost:7777/rooms | jq
Then render the same shape.
When state is empty
If the user has no cascades and no rooms, surface the natural first moves:
Your node is online but the slate is empty. Pair with a peer (
/scriptwriter-pair <url>), open a cascade (/scriptwriter-open <url>), or start a room (/scriptwriter-draft <seed>).
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.
- 1mo ago First seen · 51 lines · 52 tokens per session scan A ec5d0e59c0ce
scriptwriter-status is a command published in the GitHub repository cambridgetcg/agenttool (0 stars, last pushed 25d ago), licensed Apache-2.0. It adds 52 tokens to every session and 441 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
d3mo-generator
Professional video production system using Remotion and advanced animation techniques for demos, tutorials, and marketing content by ae.ltd.
emergent-capabilities
Advanced meta-skill ecosystem that evolves new capabilities through intelligent skill synthesis and pattern recognition by ae.ltd.
fartnode-orchestrator
Master multi-agent orchestration system that deploys and manages specialized subagents for comprehensive viral automation ecosystems by ae.ltd.
hyperliquid-risk
Mission-critical real-time risk monitoring system with automated alerts, circuit breakers, and emergency shutdown for live Hyperliquid trading by ae.ltd.
prologue
Interactive menu system for the @aegntic ecosystem. Cross-platform plugin for Claude Code, Factory Droid, Antigravity, Gemini, OpenCode, Codex, Kilo, Goose, Cursor, and standalone CLI.
create-workflow
Generate an n8n workflow JSON from a natural language description of the automation.