callwright copilot-instructions.md

A project guide for Callwright, a self-hosted program that uses an AI model and Retell to place phone calls for one user.

In plain words
What is it for?
Use it when installing, running, testing, or changing Callwright, including its Node.js server, command-line tools, phone-call dispatch, and retry logic.
Why use it?
It gives an AI coding assistant the project's setup, testing, architecture, and file-path rules so changes fit the existing codebase.

Instructions file for GitHub Copilot

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 instructions/topness-msft/callwright/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/topness-msft/callwright

Made for: GitHub Copilot.

Per session 1,472 This file is loaded in full into every session.
When invoked 1,472 The same file — it is already loaded in full.
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 $0.01472 $0.01472
Opus 5 $0.00736 $0.00736
Sonnet 5 $0.00294 $0.00294
Haiku 4.5 $0.00147 $0.00147

Measured yesterday against content hash 507b5f3c0513, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

callwright copilot-instructions.md 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.

.github/copilot-instructions.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Callwright — Copilot instructions

Callwright is a self-hosted, single-user MCP server (Node.js, CommonJS) that places outbound phone calls on the user's behalf via Retell. An LLM shapes each call's direction + grounding; Callwright validates, composes, and dispatches it fire-and-forget, then fetches the outcome on demand.

Build / test / run

  • Runtime: Node >=18, "type": "commonjs". No build step.
  • Install: npm install.
  • Tests use the built-in Node test runner (no framework dependency):
    • Full suite: npm test (runs node --test, which discovers test/*.test.js).
    • Single file: node --test test/retry-core.test.js.
    • Single test by name: node --test --test-name-pattern="classifyDisconnect" test/retry-core.test.js.
  • No linter or formatter is configured — don't add one unless asked.
  • Run locally: node init.js (setup wizard) then node server.js (MCP server on :8787, POST /mcp). Installed globally the binaries are callwright and callwright-init.
  • Place a call from the CLI (bypasses MCP): node dispatch.js <job.json> --go.

Architecture — the core/wrapper split

The central convention: all reusable logic lives in *-core.js modules that are pure of CLI concerns (no process.argv, no stdin/stdout side effects). Thin wrappers adapt them to a surface:

  • dispatch-core.js — the pipeline: validate → profile-match → compose-vars → resolve-agent → dispatch. Both the CLI and the MCP server call this in-process.
  • dispatch.js — CLI over dispatch-core. server.js — the MCP server (Streamable HTTP + bearer auth) over the same cores.
  • Other cores: setup-core.js (provisioning/config/status), lang-core.js (runtime language add/verify/update/remove), learn-core.js (profile enrichment + new-scenario candidate staging), retry-core.js (no-answer re-dial policy), notify-core.js (optional SMS).
  • CLIs learn.js / get-call.js / update-prompt.js are similarly thin wrappers.

When adding behavior, put logic in the relevant *-core.js and keep server.js / the CLI as adapters — don't duplicate logic across the two surfaces.

Read the full file on GitHub · 53 lines

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 · 53 lines · 1,472 tokens per session scan A 507b5f3c0513

Subscribe to this mod's changes

callwright copilot-instructions.md is an instructions file published in the GitHub repository topness-msft/callwright (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,472 tokens to every session, about $0.0074 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.