BazaarLink
BazaarLink is an OpenAI-compatible AI API gateway: one key for 140+ AI models, pay as you go, with budget limits.
bazaarlink.aiVisit sponsor ↗Claude Code mods, plugins, skills, hooks, status lines and MCP servers. Browse community builds with original sources and L0–L3 permission levels.
14 projectsBazaarLink is an OpenAI-compatible AI API gateway: one key for 140+ AI models, pay as you go, with budget limits.
bazaarlink.aiVisit sponsor ↗Example Claude Code mod that rewrites Bash output before the model reads it, preventing tokens and secrets from entering context.
Secrets found by betterleaks reach the model as ‹secret:…› tokens; Write/Edit restore them, other tools refuse them
A Claude Code plugin that blocks destructive shell commands and edits to secrets before they run, using function hooks on Bash, Edit, Write and NotebookEdit tool calls.
BazaarLink is an OpenAI-compatible AI API gateway: one key for 140+ AI models, pay as you go, with budget limits.
bazaarlink.aiVisit sponsor ↗Agent runtimes for ruflo — one mental model, two backends (a third planned):
Keeps secrets out of transcripts: blocks shell reads of secret files, hides token values in tool output, and checks git add and push.
Before `git push` and publishing via `gh` (in Bash and PowerShell), it checks the commits that are going to be pushed for keys, tokens, and passwords. It blocks the push if any are found. One-off bypass with `VARREDURA_OK=1`.
Keeps secrets, email addresses and IP addresses out of the session transcript: swaps each one for a stable placeholder on the way in, and puts the real value back on the way into a tool call
Masks secrets (API keys, tokens, passwords, private keys) in the Claude Code transcript; hover a masked value to reveal it.
Track what your AI coding tools cost
syrtis.nyanako.comVisit sponsor ↗keeps secrets out of every transcript: api keys, tokens and private keys read as a stable placeholder in every kept row, and come back only inside the tool call that names them
A Claude Code guard mod that denies Edit, Write and NotebookEdit on secret locations (dotenv files, private keys, ~/.ssh, ~/.aws, ~/.gnupg, pass store) and on content carrying a credential shape, including passwords inside URLs. It also denies Bash writes to those paths and Bash reads that would print them. Ships with its own tests.
Put API keys and other secrets into any config file without them appearing in chat, shell history or tool output.
A Claude Code plugin with a tool.call hook that blocks Write, Edit, MultiEdit, NotebookEdit and Bash redirections from putting real-looking credentials (AWS, Anthropic, OpenAI, GitHub, Slack, Stripe, Google keys, private keys, DB URLs with passwords) into files, while allowing placeholders, dev defaults and .env files.