New in the bucket
Tools by when we first saw them, newest first.
186 tools
- 01
#1
macOS notch app that lets agents request single Bitwarden credentials, approved per request with Touch ID.
GH#macos#any-agent#menu-bar1 post · 3 days ago★ 25
Stars:25
- 02
#2
Sub-2ms CPU pre-flight guard and tool router for AI coding agents, blocking destructive commands, syntax bugs, and secret leaks before execu
GH#claude-code#codex#any-agent1 post · 4 days ago★ 19
Stars:19
- 03
#3
Agent skill, CLI scanner, and PostToolUse hook that stops coding agents from generating legacy Java 8 / Spring Boot 2.x code.
GH#claude-code#plugin#cli1 post · 4 days ago★ 26
Stars:26
- 04#4
Runs coding agents in per-agent microVMs with scoped short-lived credentials, IAM, model gateway and audit trail.
HN#any-agent#self-hosted#web-app1 post · 4 days ago
no public repo
- 05
#5
SSH agent proxy that lets remote coding agents run commands on your laptop with policy rules, Touch ID approval, and secret injection.
HN#claude-code#codex#macos1 post · 4 days ago★ 28
Stars:28
- 06#6
Security incident alerts for your stack, delivered in Claude Code, Slack, email and pull requests, with local read-only checks.
HN#claude-code#github-action#plugin1 post · 8 days ago
no public repo
- 07
#7
Spec-as-annotation library for Java that generates docs, enforces scope at compile time, and gates AI agent edits via hooks and MCP.
GH#claude-code#mcp-server#cli1 post · 9 days ago★ 12
Stars:12
- 08
#8
Local CLI that audits what coding agents can reach on your machine (secrets, risky modes, permissions) and applies one-command fixes.
GH#claude-code#codex#cursor1 post · 9 days ago★ 14
Stars:14
- 09
#9
Finds API keys leaked by AI agents via planted canary keys; includes a Claude Code status line and redaction hook.
HN#claude-code#cli#github-action1 post · 10 days ago★ 19
Stars:19
- 10#10
MCP server giving coding agents a sandboxed, readable scripting runtime with security policy, secrets, taint tracking, audit logs and undo.
HN#mcp-server#any-agent#macos1 post · 10 days ago
no public repo
- 11
#11
Masks API keys, passwords and PII on your machine before coding agents see them, and restores real values in agent writes and commands.
HN#claude-code#codex#gemini-cli1 post · 11 days ago★ 13
Stars:13
- 12
#12
Desktop app that finds and revokes permissions, MCP servers, trusted folders and secrets granted to AI coding agents, with live alerts and h
HN#claude-code#codex#gemini-cli1 post · 7 days ago★ 15 +3/wk
Stars:15
+3 this week
- 13#13
Guardrail that checks agent commands before they run, blocking destructive actions with local rules and an AI check, with a tamper-evident l
HN#claude-code#cursor#codex1 post · 11 days ago
no public repo
- 14
#14
Local-first guardrails and context optimizer for coding agents: AST-based file slicing, secret-leak blocking, and token savings dashboards.
GH#claude-code#cursor#codex1 post · 13 days ago★ 47 +7/wk
Stars:47
+7 this week
- 15
#15
Static security scanner with 91 rules, an MCP server and agent skill that audits AI-written code for security flaws.
GHHN#claude-code#codex#cursor2 posts · 13 days ago★ 75 +42/wk
Stars:75
+42 this week
- 16
#16
Agent skill for WordPress security operations: audit, hardening, incident response, forensics and recovery, with or without BotBlocker.
GH#claude-code#opencode#codex1 post · 14 days ago★ 17
Stars:17
- 17
#17
Open-source AI agent security platform: inventories coding agents, detects risky actions, and enforces guardrails at agent hooks.
GH#claude-code#codex#cursor1 post · 15 days ago★ 12 +1/wk
Stars:12
+1 this week
- 18
#18
Claude Code hook that blocks unquoted rm -rf and repo-root deletes in all permission modes, including bypassPermissions.
GH#claude-code#macos#linux1 post · 17 days ago★ 16
Stars:16
- 19
#19
Linux sandbox that enforces per-agent contracts on files, programs and network, and keeps a hash-chained audit record of each agent run.
GH#claude-code#codex#linux1 post · 19 days ago★ 27 +3/wk
Stars:27
+3 this week
- 20
#20
Stop hook for Claude Code and Codex that blocks turn end when code changed and no test passed after the last change.
GH#claude-code#codex#plugin1 post · 21 days ago★ 2
Stars:2
- 21
#21
Security tools for coding agents: dependency audits, source and workflow scans, and secrets checks delivered via CLI, MCP and HTTP.
HN#claude-code#codex#any-agent1 post · 22 days ago★ 71
Stars:71
- 22
#22
CLI that intercepts risky shell commands with configurable checks, audit logs, and hooks/MCP integration for AI coding agents.
HN#claude-code#cursor#cli1 post · 23 days ago★ 954
Stars:954
- 23
#23
Prompt/skill library that lets coding agents generate evidence-traced threat models of a codebase, with 36 architectures and 29 methods.
GH#claude-code#codex#any-agent1 post · 24 days ago★ 618 +171/wk
Stars:618
+171 this week
- 24#24
In-flight security for AI agents: redacts secrets, blocks prompt injections in 30+ languages, and holds risky actions for human approval.
HN#any-agent#cursor#claude-code1 post · 25 days ago
no public repo
- 25
#25
Agent skill that runs 20 security checks and 10 launch-readiness checks on an app and produces a report with fixes for the agent to apply.
GH#claude-code#codex#cursor1 post · 25 days ago★ 17
Stars:17