io.github.jmshinhwa/hardcoded-credential-audit

@readystack/hardcoded-credential-audit

Open any config file and see every hardcoded credential — and every setting that quietly undoes your

alive probed 2026-10-16

3tools

362tokens in Claude Opus 5.5

0.2 %of Claude's 200k window

0.2×the median server

81 msto initialize

2 msto list tools

Run it: npx -y @readystack/hardcoded-credential-audit@0.1.1 (stdio, probed in a container with the network off)
Host: npmjs.com
Reports itself as: @readystack/hardcoded-credential-audit 1.0.0
Capabilities: tools
Instructions: none
Of a 1M window: <0.1 % of a 1M context window
Count: 362 tokens in Claude Opus 5.5, exact, measured 2026-10-16. With the Claude Code prefix mcp__…__ on each tool name: 410. The o200k_base estimate is 202. Counted again when the tool definitions change. Method.
Repository: https://github.com/jmshinhwa/readystack-themes
Registry: active, updated 2026-09-18 · registry entry
Reachable: 1 of the last 1 probe

Most expensive tools

The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 1.79×.

Tool	≈ Claude tokens	o200k estimate	Share of this server
check_dir	143	80	40 %
check_text	127	71	35 %
check_file	91	51	25 %

These registry entries have the same tool names and the same schema sizes.

The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.

Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.