Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
/plugin marketplace add dominiek/promptcellar-for-claude-codenpx agentmods add plugins/dominiek/promptcellar-for-claude-code/discovery-plugingit clone --depth 1 https://github.com/dominiek/promptcellar-for-claude-codeGrade A, and why
promptcellar-discovery scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "promptcellar-discovery",
"description": "M0 forensic-dump plugin for Promptcellar — captures every hook payload + transcript snapshot to ~/.promptcellar-discovery/. Intended for design research only.",
"version": "0.0.1",
"author": {
"name": "Promptcellar"
}
}
What it installs
The manifest is a name and a version. 1 command, 7 hooks travel with it, and installing the plugin installs all of them — 29 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 9 lines scan A 5919d9498500
promptcellar-discovery is a plugin published in the GitHub repository dominiek/promptcellar-for-claude-code (7 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
mimirs marketplace
Plugin marketplace listing 1 plugin: mimirs.
aiprise-webhooks
Receive and verify AiPrise webhooks (callbacks). Use when setting up AiPrise identity/KYC/KYB callback handlers, debugging X-HMAC-SIGNATURE verification, or handling verification results like APPROVED, DECLINED, REVIEW, and UNKNOWN.
aircall-webhooks
Receive and verify Aircall webhooks. Use when setting up Aircall webhook handlers, debugging Aircall webhook token verification, or handling Aircall cloud phone events like call.created, call.answered, call.ended, message.received, contact.updated, or user.connected.v2. Aircall does NOT use an HMAC signature …
ascend-webhooks
Receive and verify Ascend webhooks. Use when setting up Ascend webhook handlers, debugging Ascend signature verification (X-Ascend-Signature, HMAC-SHA256), or handling insurance payment events like invoice.paid, payout.paid, and refund.paid.
azure-event-grid-webhooks
Receive and validate Azure Event Grid webhook deliveries. Use when setting up an Event Grid WebHook event handler, implementing the Microsoft.EventGrid.SubscriptionValidationEvent handshake (echo data.validationCode as validationResponse with HTTP 200), implementing the CloudEvents v1.0 HTTP OPTIONS abuse-protection…
baselinker-webhooks
Receive BaseLinker (Base.com) webhooks. Use when building a BaseLinker order or warehouse callback receiver, because BaseLinker is not a normal webhook source: deliveries arrive as HTTP HEAD requests with NO body, the entire payload is in the query string (observed params: orderid, state), there is NO signature verifi.