Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →cowork-os/unbroker
Find and remove authorized personal information exposures from data brokers and people-search sites with a consent-gated local workflow.
Passed 14 of 18 test cases with the skill, and 7 of 18 without it.
and 6 more in the full report
9 fixed8 passed either way5 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
The run is wrapping up and Google Sheets tracker integration is enabled in configuration. What command should be executed to update the tracking sheet?
| Checked | Without skill | With skill |
|---|---|---|
| Invokes $PDD report with the --sheets option | Missed | Passed |
The instructions your model reads when the skill loads.
This CoWork OS bundled port is based on the upstream Hermes Agent unbroker skill:
https://github.com/NousResearch/hermes-agent/tree/main/optional-skills/security/unbroker
CoWork runtime mapping:
terminal as CoWork's shell/run_command capability.web_extract as CoWork web search, fetch, or extraction tools.browser_* as the available CoWork browser automation tools.delegate_task as CoWork multi-agent orchestration when available.cronjob as CoWork scheduling/automation.$PDD_DATA_DIR when set. Otherwise it prefers
$COWORK_HOME/unbroker, then $COWORK_USER_DATA_DIR/unbroker, then the upstream legacy
$HERMES_HOME/unbroker / ~/.hermes/unbroker path.Code is MIT licensed. Broker data includes BADBOOL-derived data under CC BY-NC-SA 4.0; keep the
license and attribution notes in LICENSE.txt and the README intact when redistributing.
Find where a person's personal information (name, addresses, phone, email, relatives) is exposed on data brokers and people-search sites, then remove it - automatically where possible, with guided human steps only where a site demands a CAPTCHA, government ID, phone call, or fax. Manages multiple people independently. It does not defeat anti-bot systems, does not act on anyone without recorded consent, and does not remove public records (voter/property/court) or accounts the person controls.
The Python CLI (scripts/pdd.py) owns the deterministic state - config, dossiers + consent, the
broker database, tier planning, the ledger, drafts, reports, email sending (SMTP), verification-link
polling (IMAP), and the autonomous action queue (next). You (the agent) do the scanning,
form-driving, parallel work, and scheduling with the matching CoWork tools.
This skill is designed to run hands-off. After intake (+ recorded consent) there are exactly TWO
legitimate human touchpoints: (1) the intake conversation itself, and (2) ONE consolidated human-task
digest at the end of the run ($PDD tasks). Between those:
$PDD setup --auto detects capabilities and
picks the most autonomous valid config itself.autonomy=full (the default): the consenttest cases passed, vs 7 / 18 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.