publisher profilecommunity

gostlightai

gostlightai publishes 3 tracked skills in DriftBot.

Catalog decision: Review-first publisher: this catalog currently carries failed runtime rows or high-risk labels, so inspect individual skills before trusting the brand halo.

indexed skills

average score

manual reviews

high-risk labels

catalog evidence snapshotbaseline-v3 coverage 1/3functionality-v2 coverage 1no manual reviews yet1 high-risk label

Read this row as a catalog snapshot: runtime coverage, deeper follow-on coverage, human review presence, and high-risk concentration before you compare individual skills.

📊 Runtime quality summary

Runtime read: stronger publisher evidence means more than broad coverage — look for low current failure pressure, some functionality depth, and stale-runtime counts that stay under control.

eligible runtime skills: 3latest touch: 9h agono current regressions

Baseline coverage

133% of eligible skills have baseline-v3 receipts

Baseline pass rate

100%1 passed · 0 currently failing

Functionality coverage

1100% of baseline-cleared skills have functionality-v2

Fixture-backed rate

0%0 functionality-v2 rows have richer fixture/example proof

Stale baseline rows

0baseline receipts older than 7 days

Functionality failures

1current failed functionality-v2 rows in the latest publisher state

This is the quality surface for the publisher, not just a directory listing. It shows how much of the catalog has real receipts, how often those receipts are passing, whether richer fixture-backed proof exists, and whether the publisher currently carries regressions, reproduced failures, or stale runtime evidence.

Latest runtime touch: 2026-03-15 18:15 UTC. Publisher-level summaries do not replace skill-level review, but they do make reputation more earned: a publisher with broader coverage, stronger pass rates, and fixture-backed proof looks different from one living on thin smoke tests.

If you want the system-wide view, open the runtime dashboard. If you want the scoring logic, read the methodology.

Fresh runtime slice Stale runtime slice

failedfunctionality-v2first failed run seen for this lane9h ago

casual-cron

4/6 passed

runtime_failed

passedbaseline-v39h ago

casual-cron

8/8 passed

passed

Skills from this publisher

Showing 3 of 3 skills

Label mix on this page

Trusted: 1Use Caution: 1Insufficient Evidence: 0High Risk: 1

This distribution is a quick provenance cue, not a verdict. A publisher can have a mix of safer and riskier skills, so the useful move is to compare patterns here and then open the individual scorecards.

Publisher profiles are best for spotting catalog patterns: repeated shell access, common external services, whether manual review exists, and whether higher-risk labels are isolated or widespread.

On this page: 3 source-scanned, 0 catalog-only, and 0 manually reviewed entries in the current slice.

If you want the scoring logic, read the methodology. If you want the broader landscape, go back to the full index.

agent-step-sequencer

gostlightai · vsource-scanned

overall

Multi-step scheduler for in-depth agent requests. Detects when user needs multiple steps, suggests plan and waits for confirmation, persists state, and runs heartbeat-aware flow. Use when requests have 3+ actions, sequential dependencies, output dependencies, or high scope/risk.

Trustedconfidence: source evidencesource-scanned

+ 1 more

Take: Source-aware scan found higher-privilege capability areas (token, email), but that alone is not evidence of malicious behavior.

Decision cue: Decent evidence base — source-level signals are available, so inspect the receipts.

casual-cron

gostlightai · vsource-scanned

overall

Create Clawdbot cron jobs from natural language with strict run-guard rules. Use when: users ask to schedule reminders or messages (recurring or one-shot), especially via Telegram, or when they use /at or /every. Examples: 'Create a daily reminder at 8am', 'Remind me in 20 minutes', 'Send me a Telegram message at 3pm', '/every 2h'.

High Riskfollow-on functionality checks failed · 4/6confidence: source evidence

+ 2 more

Runtime receipts + what failed2026-03-15 18:15 UTC

functionality-v2evidence depth: follow-on functionality checkstested recently: within 24 hoursfirst failed run seen for this lanepassed, runtime_failedoutput 3.0 KBartifacts 0worker oc-sandboxsource stage: cache hitsuite 2086 msbaseline-v3 8/8

🕵️ expected proof signal was missing🚫 skill exited with an error

RatioDaemon muttered: The runtime lane gave casual-cron a chance to act normal. It declined and made it to runtime and then fell apart on contact.4/6 functionality-v2 checks passed before the stumble. The meta json shape is the part that made this interesting.

Observed: skill-structure-ok

Take: Potentially suspicious implementation signals detected: rm -rf.

Decision cue: Review first — functionality-v2 already found trouble.

cdp-browser

gostlightai · vsource-scanned

overall

CDP browser control at localhost:9222. Use when you need to inspect tabs, take screenshots, navigate, scroll, post to X, or run JS in a persistent browser session (e.g. logged into X, Gmail).

Use Cautionconfidence: source evidencesource-scanned

+ 1 more

Take: Potentially suspicious implementation signals detected: curl |.

Decision cue: Proceed carefully — suspicious signals matter more than capability surface alone.

Page 1 / 1

Trust reading guide

Publisher-level summaries help with provenance context, but trust still lives at the skill level. Use this page to compare patterns across the publisher’s catalog, then inspect the raw findings on individual skill pages.

Back to the full index