proxy

A command-line interface for managing a local credential proxy that retrieves keys from the operating-system keychain and adds authentication to approved outbound API requests without showing the keys to the agent.

In plain words
What is it for?
Use it to start and inspect the proxy, synchronize credential revocations, and view its local audit logs.
Why use it?
It keeps secret values out of the agent’s view while controlling which domains it may contact and allowing revoked credentials to be blocked.

Command

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/the-17/agentsecrets/proxy
Clone the repo
git clone --depth 1 https://github.com/The-17/agentsecrets
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 350 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 $0.00000 $0.00350
Opus 5 $0.00000 $0.00175
Sonnet 5 $0.00000 $0.00070
Haiku 4.5 $0.00000 $0.00035

Measured yesterday against content hash af3b169ce824, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

proxy 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.

docs/commands/proxy.md · 47 lines

What it actually says

agentsecrets proxy

Manage local zero-knowledge proxy workflows for your AI agents.

Usage

agentsecrets proxy <command> [flags]

Description

The proxy commands manage the runtime connection between an AI agent and your APIs. It securely resolves keys from the OS keychain, intercepts outbound agent requests in real-time, applies zero-trust domain authorizations, and injects authentication headers without exposing values to the agent model.

Available Commands

start

Starts the HTTP credential proxy on your local machine (default port 8765).

agentsecrets proxy start [--port 9000]

status

Displays the running status of your HTTP proxy, its uptime, process ID, the most recent background sync interval, and the volume of active/revoked identities that have been cached.

agentsecrets proxy status

sync

Forces an immediate cryptographic revocation sync. If a teammate compromised or revoked a key globally, this instantly blocks your proxy from making outbound calls with it. Note that the proxy already auto-syncs periodically every 10 seconds.

agentsecrets proxy sync

logs

Streams or views your proxy's local execution audit trail. This log structure definitively details memory-safe API interactions without displaying any raw secret content.

agentsecrets proxy logs                 # view entire log history
agentsecrets proxy logs --watch         # stream log outputs in real time
agentsecrets proxy logs --last N        # show last N entries
agentsecrets proxy logs --secret <key>  # filter logs associated to a local key
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 · 47 lines · 0 tokens per session scan A af3b169ce824

Subscribe to this mod's changes

proxy is a command published in the GitHub repository The-17/agentsecrets (172 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 350 tokens. 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.