agent safety plugins

27 tagged agent safety, measured the same way as everything else here.

Browse within: ai-governance 18claude-plugins 18

sponsio-claude-code

01

SponsioLabs/Sponsio

Plugin Claude Code

Runtime contract guardrails for every tool call in your Claude Code session — backed by per-plugin contract libraries under /.sponsio/plugins/.

438 3d ago A tokens not measured original Apache-2.0

bridgeward

02

bridge-mind/BridgeWard

Plugin Claude Code

Skeptical-reading and prompt-injection defense for AI coding agents. Trust nothing. Ship safely.

38 4mo ago A tokens not measured original MIT

msapps-plugins

03

MSApps-Mobile/claude-plugins

Plugin Claude Code

Plugin marketplace listing 30 plugins: google-drive-upload, toggl-time-tracker, session-backup, youtube-transcriber, notion-memory.

9 5d ago A tokens not measured original MIT

apollo

04

MSApps-Mobile/claude-plugins

Plugin Claude Code

3 pre-built skills that chain multiple Apollo APIs into complete sales workflows — no manual steps, no tab switching. Enrich any contact from a name, email, or LinkedIn URL. Prospect by describing your ICP in plain English and get ranked leads. Find, enrich, and load contacts into a sequence in one shot.

9 5d ago A tokens not measured original MIT

notion-memory

05

MSApps-Mobile/claude-plugins

Plugin Claude Code

Long-term memory for Claude across sessions via Notion — plus the 4 official Anthropic Notion skills (knowledge-capture, meeting-intelligence, research-documentation, spec-to-implementation) bundled in.

9 5d ago A tokens not measured original MIT

groundwork

06

choiyounggi/groundwork

Plugin Claude Code

A safe-by-default, batteries-included Claude Code harness starter pack — guardrails, a wiki-grounded quality loop, and a memory lifecycle.

3 2d ago C tokens not measured original MIT

guardrails

07

choiyounggi/groundwork

Plugin Claude Code

Safe-by-default guardrails for Claude Code: a PreToolUse Bash guard that blocks supply-chain / disk-destroying / fork-bomb commands and asks before rm -rf, force-push, DROP/TRUNCATE, kubectl delete, secret/credential access, and cloud-resource deletion — every rule configurable (off / ask / block) — plus a redacted…

3 2d ago C tokens not measured original MIT

memory-loop

08

choiyounggi/groundwork

Plugin Claude Code

A memory lifecycle for Claude Code's native file-based memory: a save gate against hallucinated memories, tiered expiry (short-tier memories archived — never deleted — when they lapse), a propose-then-confirm consolidation pass (merge/dedupe long-tier memory), a periodic learning-review nudge, a two-file habit frame…

3 2d ago A tokens not measured original MIT

auto-cc

09

SSHdotCodes/auto-cc

Plugin Claude Code

Automatic tool-call review for Claude Code.

1 23d ago A tokens not measured original Apache-2.0

auto-cc

10

SSHdotCodes/auto-cc

Plugin Claude Code

Automatic tool-call review for Claude Code. A local encoder scores every proposed tool call before it runs, approving safe work and blocking dangerous calls with an explanation the agent can act on.

1 23d ago A tokens not measured original Apache-2.0

constitution-lint

12

joeyycli/constitution-lint-action

Plugin Claude Code

Lint a CLAUDE.md-style agent constitution for missing operational guardrails — 10 heuristic checks (spend limits, injection defense, escalation path, secrets handling, ledger discipline, session ritual, referenced state files). Adds a /lint-constitution command.

0 1mo ago A tokens not measured original MIT