promptcellar-discovery

promptcellar-discovery is a plugin for Claude Code from dominiek/promptcellar-for-claude-code. Its manifest loads nothing; the 1 command, 7 hooks it bundles cost 29 tokens per session together, scanned A, original, MIT.

A research plugin for Promptcellar, a system that records Claude Code activity, which saves hook data and transcript snapshots for analysis.

In plain words
What is it for?
Use it for design research involving hook payloads and session transcript snapshots.
Why use it?
It collects the information needed to investigate how Claude Code events and transcripts are represented.

Plugin for Claude Code

Install

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.

Claude Code
/plugin marketplace add dominiek/promptcellar-for-claude-code
agentmods
npx agentmods add plugins/dominiek/promptcellar-for-claude-code/discovery-plugin
Clone the repo
git clone --depth 1 https://github.com/dominiek/promptcellar-for-claude-code

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 command, 7 hooks cost 29 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade 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.

discovery-plugin/.claude-plugin/plugin.json · 9 lines

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"
  }
}
Contents

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.

Changes

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.

  1. 3d ago First seen · 9 lines scan A 5919d9498500

Subscribe to this mod's changes

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.

Related

Other plugins, from other repositories

mimirs marketplace

Plugin marketplace listing 1 plugin: mimirs.

TheWinci/mimirs · not measured

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.

hookdeck/webhook-skills · not measured

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 …

hookdeck/webhook-skills · not measured

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.

hookdeck/webhook-skills · not measured

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…

hookdeck/webhook-skills · not measured

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.

hookdeck/webhook-skills · not measured