phantom-secrets copilot-instructions.md

phantom-secrets copilot-instructions.md is an instructions file for GitHub Copilot from ashlrai/phantom-secrets. It costs 489 tokens per session, scanned A, original, MIT.

Project instructions for Phantom Secrets, a tool that keeps real API keys in an encrypted vault and replaces them in .env files with safe placeholder tokens.

In plain words
What is it for?
Use them when initializing secret protection, listing or changing stored secret names, checking configuration, or running commands that need API credentials.
Why use it?
They prevent real credentials from being hardcoded, requested from users, or exposed in logs. Commands are provided for managing secrets and running programs with credentials injected securely.

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/ashlrai/phantom-secrets/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/ashlrai/phantom-secrets

Made for: GitHub Copilot.

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.

agentmods badge for phantom-secrets copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ashlrai/phantom-secrets/copilot-instructions.svg)](https://agentmods.dev/instructions/ashlrai/phantom-secrets/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/ashlrai/phantom-secrets/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/ashlrai/phantom-secrets/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 489 This file is loaded in full into every session.
When invoked 489 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 $0.00489 $0.00489
Opus 5 $0.00244 $0.00244
Sonnet 5 $0.00098 $0.00098
Haiku 4.5 $0.00049 $0.00049

Measured today against content hash a7fa036566dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

phantom-secrets 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 today.

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 · 36 lines

What it actually says

Copilot Instructions

This project uses Phantom Secrets to protect API keys from AI leaks.

Key Rules

  • The .env file contains phantom tokens (phm_...), NOT real secrets
  • Real secrets are stored in an encrypted vault (OS keychain or encrypted file)
  • NEVER hardcode API keys in source code
  • NEVER ask the user to paste real API key values into code files
  • NEVER attempt to read, log, or display real secret values

Commands

  • phantom list — See available secrets (never shows values)
  • phantom add <name> — Add a new secret transactionally through the hidden trusted-terminal prompt; run phantom init --empty first in a new project, and never put the value in argv or chat
  • phantom remove <name> — Remove a secret from the vault
  • phantom exec -- <command> — Run code with real credentials injected via proxy
  • phantom init — Protect .env secrets (stores real values in vault, rewrites .env with phm_ tokens)
  • phantom status — Show project status, vault backend, secret count
  • phantom doctor — Health check for config, vault, and .env

How It Works

  1. phantom init reads .env, stores real secrets in encrypted vault, rewrites .env with phm_ tokens
  2. phantom exec -- <cmd> starts a local proxy that injects only a matched route's vault value into its fixed authentication header; client headers and bodies never resolve phantom tokens
  3. AI agents see only worthless phm_ tokens — real keys are never in the AI context window

When You See API Keys

If a user pastes a real API key (starts with sk-, ghp_, xoxb-, etc.):

  1. Treat the pasted value as exposed and recommend rotating it at the provider
  2. Suggest phantom add <KEY_NAME> so the replacement value is entered only in the hidden trusted-terminal prompt
  3. Reference the key by name or its phantom token (phm_...) in code, not the real value
  4. Never write the real key value into any file
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. today Changed · +1 lines · +62 tokens per session a7fa036566dd
  2. 5d ago First seen · 35 lines · 427 tokens per session scan A 30e511a9adec

Subscribe to this mod's changes

phantom-secrets copilot-instructions.md is an instructions file published in the GitHub repository ashlrai/phantom-secrets (16 stars, last pushed today), licensed MIT. It adds 489 tokens to every session, about $0.0024 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.