CERBERUS — the two-headed guard at the gate for a PUBLIC skills marketplace. A PostToolUse hook fires on every skill / reference / script / eval / manifest edit and reminds you to run BOTH heads before committing: cerberus:leak-check (outward — no real work identifier or secret escapes into the public marketplace) and cerberus:security-scan (inward — the eight-point consumer-safety checklist: prompt injection, exfiltration, secrets, dangerous commands, obfuscation, external fetches, credential access, privilege escalation, so nothing unsafe reaches whoever installs the skill). Before a push it also guards the commits themselves — their messages, authors and branch name, which no file check reads: a classic PreToolUse hook has a nested claude judge the outgoing commits and blocks a push that leaks or that it cannot judge, and on Claude Code 2.1.292 or newer a push-guard mod judges them in-process first; an older Claude Code gets a red notice at session start to update. The verdict cache is guarded best-effort, so the hook stops a forgotten check, not a deliberate forgery. Both are agent judgment passes, no denylist by design — a list of the real names to catch would itself be the leak; the intelligence lives in the agent, not a regex.
Plugin cerberus from marketplace bladeforge in aquivalabs/BladeForge. Commands read from the repo's manifest — 2 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
leak-checkUse before committing OR PUSHING a NEW or EDITED skill, its references, its bundled scripts, or its eval fixtures to this PUBLIC marketplace — review the change, and before a push also the outgoing commits themselves (messages, author, committer, branch name), for anything that points to a real work
security-scanUse before committing a NEW or EDITED skill, its references, its bundled scripts, or its eval fixtures to this marketplace — review the change for anything UNSAFE to the person who installs and runs it: prompt-injection text, data exfiltration, an embedded secret, a dangerous/destructive command, ob
bash "${CLAUDE_PLUGIN_ROOT}/hooks/on-git-push.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/on-skill-edit.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/on-git-push.sh"
bash "${CLAUDE_PLUGIN_ROOT}/hooks/check-version.sh"
Stack-agnostic pre-push review framework — eight reviewer agents (five on by default, plus skill, leak and security-scan for repos that publish skills), the /review orchestrator, and the secret-scan + attestation gate, all driven by a per-project .claude/review.config.json.
2 skills · 2 commands · 8 agents
Meta skills — authoring new skills, the OCKHAM minimal-entities discipline, and the WITTGENSTEIN clarity gate for specs & plans.
10 skills
Frontend Vue 3 skills — single-file components with Composition API and TypeScript, component architecture, BEM in scoped styles, Pinia stores, VueUse-first composables, Nuxt conventions, motion, testing.
9 skills
Frontend React skills — component structure, hooks registry, skeleton components, Storybook stories.
8 skills
Personal Salesforce skills — Apex test authoring standard and salesforce-dx MCP usage.
5 skills
Whose Turn, the Claude Code side of a local monitor of your Jira, GitHub, Linear and other sources: whose turn it is, what changed, your own to-dos, a summary at the start of each session, a hand-off from the monitor window into the session, a /whose-turn command that opens the window, and an MCP server for any agent. The monitor itself is the published whose-turn npm package; the plugin installs its latest version into the monitor's data directory on first start and runs it from there; each newer version is then announced in its window and at session start and installs only when the user says yes or clicks Update. Employer-specific values live in a workspace config on the machine, not in the plugin.
1 skill · 1 command · 1 MCP server · hooks
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
SAST analysis, dependency vulnerability scanning, OWASP Top 10 compliance, container security scanning, and automated security hardening
5 skills · 3 commands · 2 agents
Long-term semantic memory for Claude Code, powered by OpenViking
5 skills · 1 command · 1 MCP server · hooks
Connect Claude to Prowler Cloud through the Prowler MCP server. Reads providers, scans, findings, compliance results and resources for AWS, Azure, GCP, Kubernetes, Microsoft 365, GitHub and the other providers listed at https://registry.prowler.com, and returns remediation guidance for failed checks. Writes are limited to Prowler Cloud itself: triggering scans, finding triage, mute rules and the mutelist, providers and integrations. Your cloud resources are not changed by the connector.
1 skill · 1 MCP server
Triage, budget, constraints, and verifier skills. Pair with npx @cobusgreyling/loop init . --tool claude
14 skills
Point it at a codebase and it figures out what's worth doing — bugs, perf, tech debt, what to build next — then writes plans any agent can execute. It can hand the work to a cheaper model and review the result. It never edits your code.
1 skill
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.