pseudospam-filter

Plugin pseudospam-filter in danielrosehill/Claude-Pseudospam-Filter-Plugin. Commands read from the repo's manifest — 19 days ago.

Skills (18)

• adguard-configure

  One-time setup for AdGuard Home integration. Captures the AdGuard Home base URL, credentials, and target blocklist filename, validates connectivity, and persists to corpus/config.json. Use before adguard-push.

• adguard-push

  Push the user's accumulated tracking-pixel + ad-tracker domains from the Pseudospam Filter corpus into a self-hosted AdGuard Home instance, using the credentials configured by adguard-configure. Network-layer block — every device on the LAN benefits, not just one mailbox. Use when the user wants to

• analyse-email

  Run the full Pseudospam Filter analysis pipeline on a single email — semantic spam reasoning, tracking-pixel detection, sender block, processed-emails log, markdown report. Use when the user wants a deep dive on one email rather than the lighter capture-example flow.

• block-sender

  Create a server-side Gmail filter that auto-trashes (or labels + archives) future mail from a sender, via an available email MCP. Falls back to recording the block in the local sender-blocklist.json if no MCP is wired up. Use when the user says "block this sender" or "make sure I never see another e

• bulk-analyse

  Process every unanalysed .eml file in the user's corpus inputs/emails/ directory through the full analyse-email pipeline. Skips files that already have a corresponding analysis report. Use when the user has dropped many .eml files into the corpus at once.

• capture-example

  Capture one email as a Pseudospam Filter example. Labels it as a pseudospam (or genuine) example in Gmail so the judge learns from it, saves a copy to the corpus, asks what pattern it represents, suggests a filter pattern, and optionally pushes a server-side block or drafts an unsubscribe reply. Use

• contribute-blocklist

  Strip per-recipient identifiers from the user's tracking inventories and prepare a redacted contribution suitable for opening a PR against collaborative public anti-tracking lists (EasyPrivacy, hagezi, oisd, Pi-hole community, AdGuard's tracker filter). Outputs a sanitised diff plus a draft PR descr

• draft-unsubscribe-reply

  Draft (and optionally send) a manual unsubscribe-request reply to a spam sender — used when the email has no working List-Unsubscribe header or the user wants to make the request human-to-human. Threads on the original message via the available email MCP. Use when the user says "tell them to take me

• export-dns-blocklist

  Aggregate the user's accumulated tracking-domains.json + ad-trackers.json into a portable DNS blocklist (Pi-hole / AdGuard / hosts / dnsmasq formats). Writes to corpus/exports/. Use when the user wants to push their pixel inventory to a network-level blocker.

• learn-from-labels

  Teach Pseudospam Filter your own boundary from the emails you've labelled as examples. Reads the example labels, writes examples.jsonl (few-shot cases the judge sees) and profile.md (your rules, in your words, where they differ from the standard). Use when the user says "learn from my labels", "I've

• manage-labels

  Create, explain, rename or remap the Gmail labels Pseudospam Filter works with. Example labels teach Claude what you consider pseudospam; result labels mark what a sweep processed. Use when the user says "set up the pseudospam labels", "what do the labels mean", "use my existing labels for examples"

• prioritise-genuine

  Turn the genuine mail a sweep found into a reply queue ordered by what deserves attention, by the user's own priority order (paid work, peers in their niches, real corrections, reasonable asks), with a one-line summary and suggested action each. Use when the user says "what should I reply to", "prio

• review-caught

  Review what Pseudospam Filter caught, rescue mistakes and turn them into teaching examples. Lists the Caught (and Unsure) labels with the judge's one-line reasons; for anything the user says was wrongly caught, moves it back to the inbox and labels it as a genuine example (and vice versa), then rele

• scan-recent-pixels

  Bulk scan of recent inbox messages (default last 30) for tracking pixels and ad-tracker beacons. For every detection logs which email it came from, sender, time, recipient, the raw pixel URL, and a suggested block pattern. Appends to the user's tracking inventories. Requires an email MCP (e.g. gws-p

• scan-tracking-pixels

  Scan a single email (raw .eml or live message via email MCP) for tracking pixels and ad-tracker beacons, then append every detected pixel host to the user's tracking inventories (tracking-domains.json + ad-trackers.json). Use when the user wants to surgically extract pixels from one email without ru

• setup

  First-run setup for Pseudospam Filter. Resolves the data directory, writes config.json (account, label names, thresholds, a short recipient profile), creates the Gmail label tree, and scaffolds the sample/tracking corpus. Use when the plugin is first used, or to change the account, labels or corpus

• sweep

  Run Pseudospam Filter over the inbox. Finds unsolicited one-to-one-looking mail, has parallel Haiku judges classify it against the standard plus the user's own examples, then labels pseudospam as Caught and archives it, marks genuine mail as Passed, and leaves unsure mail in place. Works like a seco

• tracking-report

  Summarise the user's accumulated tracking-pixel and ad-tracker inventory — totals by type, top domains, top senders, recent additions. Read-only — does not modify any inventory. Use when the user wants visibility into what their corpus has captured.

Subagents (2)

• email-analyst
• pseudospam-judge

  Classifies a batch of candidate emails as genuine, pseudo_personalised (pseudospam) or out_of_scope using the plugin's standard plus the user's own profile and examples, and assigns a priority. Reads a JSONL file of messages, writes one verdict per line. Spawned by the sweep skill, several in parall

Similar plugins