ownex-atlas
Skill1 starsChanged 3 months agoMITView on GitHub
Goal: Expand bug bounty coverage — discover new targets, update intelligence profiles, and identify coverage gaps in existing programs. App: atlas · Cadence: 1d · Risk: low discover → triage → classify → report
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- graftSkill
- loop-triageSkill
- ownex-forgeSkill
- ownex-odysseySkill
- ownex-pulseSkill
- ownex-securitySkill
- ownex-vaultSkill
The file
Files
OWNEX Atlas Cycle — Target Intelligence
Goal: Expand bug bounty coverage — discover new targets, update intelligence profiles, and identify coverage gaps in existing programs.
App: atlas · Cadence: 1d · Risk: low
Default Phases
discover → triage → classify → report
Human Gates
- New target approval (requires program manager sign-off)
- Program policy changes
- Scope expansion decisions
Required Skills
target-discover— Discover new potential targets (domains, subdomains, APIs)intel-update— Refresh target intelligence profilescoverage-scan— Identify gaps in current coverage
Data Sources
- Censys / Shodan API
- Certificate transparency logs
- DNS enumeration results
- Program scope definitions from HackerOne / Bugcrowd
- Existing target database
State File
# Atlas Cycle State
Last run: <timestamp>
New Discoveries:
- api.staging.example.com — not in scope (flag for review)
- admin-dashboard.example.com — new subdomain, unknown service
Intelligence Updates:
- example.com: updated tech stack (Vue 3 → React 18)
- api.partner.com: added new endpoint /v3/graphql
Coverage Gaps:
- Mobile API (iOS) — no coverage
- WebSocket endpoints — partially covered
Pending Approval:
- Target: api.staging.example.com (proposed addition)Success Metrics
- New targets discovered per week
- Intelligence profiles updated on schedule
- Coverage gap closure rate
- % of discovered targets that are in-scope
Budget
- Daily cap: 60k tokens
- Max runs: 1/day
- L1: report only
- L2: auto-submit target addition proposals
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.