What is GhostLine AGENTS.md?

A project guide for AI coding agents working on GhostLine, a Python application for authorised security assessments using automated phone calls, speech transcription, generated replies, and synthetic speech.

Use it when developing GhostLine, setting up its Python environment, changing its web or call-processing code, or checking how its speech and language-model components connect.

It explains the project structure, tools, and safety boundaries before code is changed. This helps prevent unsafe use, incorrect setup, and changes that bypass consent or security controls.

How mbhatt1/GhostLine configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to mbhatt1/GhostLine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/mbhatt1/GhostLine/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/mbhatt1/GhostLine

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mbhatt1/ghostline/agents-md/github.svg)](https://agentmods.dev/instructions/mbhatt1/ghostline/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/mbhatt1/ghostline/agents-md"><img src="https://agentmods.dev/badge/instructions/mbhatt1/ghostline/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mbhatt1/ghostline/agents-md"><img src="https://agentmods.dev/badge/instructions/mbhatt1/ghostline/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,736 This file is loaded in full into every session.

When invoked 1,736 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01736	$0.01736
Opus 5.5	$0.00694	$0.00694
Sonnet 5.5	$0.00347	$0.00347
Haiku 4.5	$0.00174	$0.00174

Measured 1mo ago against content hash d2d8b92e523f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

GhostLine AGENTS.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 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.

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.

AGENTS.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Guide for AI coding agents working on GhostLine

Read this before touching the codebase. Mirrors the conventions a human maintainer would expect.

Project summary

GhostLine is a model-agnostic, LLM-fueled vishing operative for authorized security assessments. It places outbound PSTN calls via Twilio Media Streams, transcribes target speech with Deepgram, generates a social-engineered reply through the OpenAI Agents SDK (backed by any LLM via LiteLLM), synthesizes the reply with ElevenLabs (optionally a cloned voice), and streams µ-law audio back to Twilio.

Ethical guardrail: GhostLine must only be used against targets covered by a signed Rules of Engagement. Never weaken the Guardrails in src/ghostline/agent/ or the consent disclosures in README.md.

Tech stack

Project / deps: uv-managed Python 3.12 (pyproject.toml, uv.lock). No requirements.txt, no venv hand-rolling.
Layout: src/ layout. Package is ghostline under src/ghostline/.
LLM runtime: OpenAI Agents SDK (openai-agents) with the LiteLLM adapter so the LLM provider is swappable via LITELLM_MODEL env var.
Web: FastAPI + Uvicorn. One WS endpoint (/twilio) consumes Twilio Media Stream frames.
Async I/O: aiohttp for Deepgram WSS and ElevenLabs HTTP. aiosqlite for persistence. No sync I/O in the call hot path.
DSP: numpy + scipy. audioop is gone (deprecated in 3.13); µ-law encoding is implemented in pure numpy.
Telephony: twilio (REST) + pyngrok (tunnel).
CLI: Typer. Entrypoint: ghostline (see [project.scripts]).

Common commands

uv sync --extra dev                 # install everything
uv run ruff check .                 # lint
uv run ruff format .                # format
uv run ruff check --fix .           # autofix
uv run mypy                         # strict typecheck (config in pyproject)
uv run pytest                       # all tests (unit + integration)
uv run pytest tests/unit            # just unit
uv run pytest -m "not live"         # skip live PSTN/API tests
uv run pytest -k playbook           # by name
uv run ghostline --help             # run the CLI
uv run pre-commit run --all-files   # all hooks

Read the full file on GitHub · 108 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.

1mo ago First seen · 108 lines · 1,736 tokens per session scan A d2d8b92e523f

Subscribe to this mod's changes

GhostLine AGENTS.md is an instructions file published in the GitHub repository mbhatt1/GhostLine (127 stars, last pushed 3mo ago), licensed MIT. It adds 1,736 tokens to every session, about $0.0069 per session on Opus 5.5. 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.

Backend and APIs Security

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

GhostLine: Instructions file for Codex

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md — Guide for AI coding agents working on GhostLine

Project summary

Tech stack

Common commands

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

vscode copilot-instructions.md

deno copilot-instructions.md