What is agentkeychain AGENTS.md?

Repository instructions for AgentKeychain, an AI-focused vault for storing and using credentials. They define how an agent should install, configure, verify, and safely handle the vault.

Use them when installing or configuring AgentKeychain, preserving an existing vault, creating a new vault, or checking its command-line, skill, and MCP integrations.

They prevent incomplete setup, accidental vault changes, and secret values appearing in logs or transcripts.

How linsipeng/agentkeychain configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to linsipeng/agentkeychain. 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/linsipeng/agentkeychain/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/linsipeng/agentkeychain

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/linsipeng/agentkeychain/agents-md/github.svg)](https://agentmods.dev/instructions/linsipeng/agentkeychain/agents-md)

Your own site

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

Per session 1,150 This file is loaded in full into every session.

When invoked 1,150 The same file — it is already loaded in full.

Security scan C 2 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	$0.01150	$0.01150
Opus 5	$0.00575	$0.00575
Sonnet 5	$0.00230	$0.00230
Haiku 4.5	$0.00115	$0.00115

Measured today against content hash e4e147997683, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-14, from the pricing page.

Security

Grade C, and why

agentkeychain AGENTS.md scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -fsSL https://raw.githubusercontent.com/linsipeng/agentkeychain/v0.5.0/install.sh | sh -s -- --version v0.5.0

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://raw.githubusercontent.com/linsipeng/agentkeychain/v0.5.0/install.sh | sh -s -- --version v0.5.0

AGENTS.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent instructions for AgentKeychain

AgentKeychain is an AI-first credential vault. A user should be able to send an AI agent only this repository URL and ask it to install and configure AgentKeychain as the default credential manager.

When the user asks you to install or configure this repository

Own the full outcome. Do not hand the user a checklist of shell commands.

Required outcome

The correct AgentKeychain binary is installed and on PATH.
The public AgentKeychain skill is installed in Hermes when Hermes is available.
The AgentKeychain MCP server is registered in Hermes when Hermes supports MCP.
An existing vault is preserved exactly as-is. Do not overwrite, import into, migrate, or reset it.
A new vault is initialized only after the user enters a master password at a local, private input boundary.
CLI, skill, MCP, and metadata-only vault access are verified.
Installation and verification never retrieve, print, or persist secret values. Normal akc_get use returns plaintext to the configured MCP client, so register only trusted local clients and prevent their transcripts/logs from retaining tool results.

Installation protocol

Discover before installing:

command -v agentkeychain || true
agentkeychain --version 2>/dev/null || true
command -v hermes || true

If a working CLI with status --json is already present, preserve it. Do not overwrite or upgrade an existing binary unless the user explicitly asked for an upgrade. If the CLI is absent, install the pinned release:
```
curl -fsSL https://raw.githubusercontent.com/linsipeng/agentkeychain/v0.5.0/install.sh | sh -s -- --version v0.5.0
```
Resolve the installed binary by absolute path. Do not modify global PATH without need.
If Hermes is present, inspect hermes skills list. Preserve any existing agentkeychain skill; do not force-overwrite it. Only when absent, install the pinned release skill non-interactively:

Read the full file on GitHub · 102 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.

today First seen · 102 lines · 1,150 tokens per session scan C e4e147997683

Subscribe to this mod's changes

agentkeychain AGENTS.md is an instructions file published in the GitHub repository linsipeng/agentkeychain (0 stars, last pushed today), licensed MIT. It adds 1,150 tokens to every session, about $0.0057 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-14.

Building agents Security

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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 · 6,785 tokens

agentkeychain: Instructions file for Codex