Claude-OSINT is a library of structured skills that guide Claude through external reconnaissance, including methodology, attack-surface analysis, security checks, risk assessment, and related investigative techniques. It is intended for authorized red-team and bug-bounty engagements. The catalogue entries are the project's own Claude skills for these reconnaissance workflows.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/elementalsouls/Claude-OSINTnpx agentmods add skills/elementalsouls/claude-osint/continuous-exposure-monitoringWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/elementalsouls/claude-osint/continuous-exposure-monitoring)<a href="https://agentmods.dev/skills/elementalsouls/claude-osint/continuous-exposure-monitoring"><img src="https://agentmods.dev/badge/skills/elementalsouls/claude-osint/continuous-exposure-monitoring/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/elementalsouls/claude-osint/continuous-exposure-monitoring"><img src="https://agentmods.dev/badge/skills/elementalsouls/claude-osint/continuous-exposure-monitoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 322 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 325 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Rogue Agent · line 707 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00408 | $0.12572 |
| Opus 5.5 | $0.00163 | $0.05029 |
| Sonnet 5.5 | $0.00082 | $0.02514 |
| Haiku 4.5 | $0.00041 | $0.01257 |
Grade A, and why
continuous-exposure-monitoring 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 818 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Continuous Exposure Monitoring — Loop, Diff, Chatter, Lifecycle
Companion skills:
osint-methodology(the 5-stage pipeline this skill loops — see its §7.2 "ongoing weekly diff" profile, which this skill fills in with concrete mechanics),offensive-osint(§29 Threat Intel & IOCs — this skill deepens that section's advisory/IOC-feed directory with the continuous adversary-chatter watch loop and CTI-feed cadence it explicitly lacks; use §29 for indicator enrichment and vulnerability-prioritization data sources, this skill for the standing collection loop),org-attack-surface(the org-first discovery this skill's re-scans re-run on a schedule),exposure-risk-quantification(reads this skill's finding-lifecycle suppression state to computerisk_trendand the FAIR score — see its risk-score model). This skill answers a different question than all four: not "what does the target expose right now," but "is what the target exposes changing, and should anyone be told."
0. When to Use / When NOT
Use this skill when:
- Standing up ongoing monitoring for a retainer, MSSP, or bug-bounty program instead of a one-shot engagement — the client wants to know about new exposure, not to re-read yesterday's report.
- Deciding how often to re-run which recon stage (daily vs. weekly vs. monthly) without either wasting API quota / detection budget on cheap-to-skip stages or missing real drift.
- Building or tuning adversary-chatter monitoring (ransomware leak sites, forum/paste mentions, Telegram brand mentions) for a target's brand/domain.
- Deciding whether a finding that keeps showing up in every re-scan should keep alerting, or has already been triaged/accepted and should go quiet.
- Debugging "the webhook never fired" or "the webhook fired twice" — alert delivery reliability, dedup, and backoff behavior.
- Writing a "what changed on the perimeter since last week" deliverable.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 818 lines · 408 tokens per session scan A fbf370d7c5fc
continuous-exposure-monitoring is a skill published in the GitHub repository elementalsouls/Claude-OSINT (2,972 stars, last pushed 17d ago), licensed MIT. It adds 408 tokens to every session and 12,572 once invoked, about $0.0016 per session on Opus 5.5. 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 2026-08-30.
continuous-exposure-monitoring compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| continuous-exposure-monitoringelementalsouls/Claude-OSINT | Skill | 3.0k | 17d ago | MIT | A | 408 | Claude Code, Codex |
| reproduce-and-fix-issuesbacknotprop/pstack | Skill | 3.7k | yesterday | MIT | A | 48 | Claude Code, Cursor |
| triage-issue-reportsbacknotprop/pstack | Skill | 3.7k | yesterday | MIT | A | 46 | Claude Code, Cursor |
| setup-pstackbacknotprop/pstack | Skill | 3.7k | yesterday | MIT | A | 62 | Cursor |
| poteto-helpbacknotprop/pstack | Skill | 3.7k | yesterday | MIT | A | 40 | Claude Code, Cursor |
| arenabacknotprop/pstack | Skill | 3.7k | yesterday | MIT | A | 58 | Claude Code, Cursor |
| no-commentsbacknotprop/pstack | Skill | 3.7k | yesterday | MIT | A | 20 | Claude Code, Cursor |