A mod that redacts secret-shaped strings (GitHub, Anthropic, OpenAI, Google, AWS, Slack and Stripe keys, PEM private keys) to [redacted:<kind>] before they are kept in the conversation: your prompt before it is sent, with a toast that suggests rotating the key, and the model's response before it is stored.
1 on GitHubby Seiya Kawamurav0.1.0MITupdated 1 month ago
/
Plugin secret-guard from marketplace claude-ship in insession-space/claude-ship. Commands read from the repo's manifest — 1 month ago.
What it installs
No skills, commands, agents, hooks or MCP servers were found in the standard plugin folders.
A workflow that turns a request into a GitHub Issue and implements it in the same session until every acceptance criterion is met, verification is green, and the review has zero findings. It decides the goal (Issue / implementation / PR / merge) once before starting and stops there.
An add-on to ship-session that lets Jev (TypeSafe AI's System One model) decide the goal from the request and skip the Phase 0 question when its confidence is high. Optional and fail-open: without TYPESAFE_API_KEY, or when the API fails, it behaves exactly like ship-session. Requires ship-session.
Design templates for Artifacts, picked by purpose: a plan becomes a landing page, a review a technical report, an investigation a report or a dashboard, shipped work an implementation report. One dark-first base and a no-slop list keep pages consistent.
Breaks a task into a graph of nodes and edges and runs it deterministically in parallel with the Workflow tool. It shows the graph design for approval first and resumes midway on failure.
A mod that shows the progress of the issue you are working on: when the agent reads or edits a GitHub issue with gh, it reads the issue's checklists back from GitHub and shows above the prompt how many acceptance criteria are done and which remain.
A mod that shows each running subagent and teammate as a character: one row per agent in a band above the prompt (face, type, task, current tool, elapsed time), and their faces at the head of the spinner line. Each agent type has its own face.
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
Duende development skills and agents for Claude Code — covering OAuth/OIDC protocols, IdentityServer, token management, ASP.NET Core authentication/authorization, BFF patterns, and secure identity architecture
24 skills · 2 agents
anthropics/claude-plugins-official 47,076
Maintain secret-guard?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.