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/identity-provider-reconWrote 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/identity-provider-recon)<a href="https://agentmods.dev/skills/elementalsouls/claude-osint/identity-provider-recon"><img src="https://agentmods.dev/badge/skills/elementalsouls/claude-osint/identity-provider-recon/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/identity-provider-recon"><img src="https://agentmods.dev/badge/skills/elementalsouls/claude-osint/identity-provider-recon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 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 Excessive Agency · line 216 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 904 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Data Exfiltration · line 534 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 647 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 755 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.
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 | $0.00418 | $0.14293 |
| Opus 5.5 | $0.00167 | $0.05717 |
| Sonnet 5.5 | $0.00084 | $0.02859 |
| Haiku 4.5 | $0.00042 | $0.01429 |
Grade A, and why
identity-provider-recon scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sk -m 15 "https://login.microsoftonline.com/getuserrealm.srf?login=${U}@${D}&xml=1" How it starts
The opening of the file, as written. The whole thing — 1,004 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity-Provider Recon — Tenant, Federation & User-Enumeration Oracle Mapping
Companion skills:
osint-methodology(§6.2 detectability tagging, §11 identity-fabric pointer — the "how to think" skill this plugs into) andoffensive-osint(§22 Identity Fabric — the concrete endpoint/payload reference this skill builds a workflow on top of, rather than re-listing). This skill answers the question those two don't: how do the tenant, its federation partners, its IdP, and its user-enumeration oracle fit together as one map — and where exactly enumeration stops and credential submission begins.
0. When to Use / When NOT
Use this skill when:
- You need to resolve a domain to its identity tenant (Entra/Okta/ADFS/Google Workspace) and determine whether auth is Managed or Federated.
- You need to map an org's federation boundary — every sibling domain that shares the same M365/Azure AD tenant trust, not just the seed.
- You need to distinguish Entra vs. Okta vs. ADFS vs. Google Workspace vs. a generic OIDC IdP from passive/low-detectability signals.
- You need to detect Seamless SSO or Microsoft Defender for Identity (MDI) presence — both change the risk calculus of anything downstream.
- You have authorization for a Medium-detectability, log-generating pass and need to run a
pre-auth user-enumeration oracle (GetCredentialType / Okta
/api/v1/authn) to build a valid-account list — without ever submitting a password. - You have harvested employee names and a confirmed org email-format pattern and need to synthesize ranked login candidates to feed that oracle.
Do NOT use this skill when:
- You need to submit credentials, replay breach creds, forge/replay a token, or confirm an auth-bypass — that is a different, higher-authorization tier. See §14.
- The target's authorization for active, logged probing isn't established — the passive half of this skill (§7–§10) needs the same soft-scope posture as every companion skill; the active half (§11) needs it explicitly, because it generates tenant-side audit-log events (§1, §11.4).
- You already have concrete endpoints and just need the reference table — go straight to
offensive-osint§22.
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 · 1,004 lines · 418 tokens per session scan A 82c16353ecdb
identity-provider-recon is a skill published in the GitHub repository elementalsouls/Claude-OSINT (2,955 stars, last pushed 13d ago), licensed MIT. It adds 418 tokens to every session and 14,293 once invoked, about $0.0017 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
reproduce-and-fix-issues
Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after proof. Use only from the configured Benny repro automation.
triage-issue-reports
Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation. Use only from the configured Benny triage automation.
setup-pstack
Configure which models pstack uses per role and at what reasoning budget. Detects your available models and writes an always-applied rule that overrides the skill defaults. Use for /setup-pstack, "configure pstack models", "pstack budget", or changing pstack's model choices.
poteto-help
Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.
arena
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
no-comments
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.