Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/HermeticOrmus/LibreSecOps-Claude-CodeWrote 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/commands/hermeticormus/libresecops-claude-code/iam-audit)<a href="https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/iam-audit"><img src="https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/iam-audit/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/commands/hermeticormus/libresecops-claude-code/iam-audit"><img src="https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/iam-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00036 | $0.01020 |
| Opus 5.5 | $0.00014 | $0.00408 |
| Sonnet 5.5 | $0.00007 | $0.00204 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
iam-audit 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 12d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/iam-audit
Audit access controls across applications and infrastructure.
Trigger
Use when you need to:
- Review who has access to what in a system
- Identify over-privileged accounts and privilege creep
- Prepare for a SOC 2, PCI DSS, or ISO 27001 audit (access control section)
- Evaluate access controls after organizational changes
- Investigate whether former employees still have access
Input
One or more of:
- Access control configuration: RBAC role definitions, IAM policies, ACLs, group memberships
- User/identity list: Current identities with their assigned roles and permissions
- Access logs: Authentication logs, authorization decision logs, API access logs
- Organizational data: Org chart, team structure, role definitions (for comparison to actual access)
- Specific scope: System, application, or identity subset to audit
Process
Phase 1: Identity Inventory
-
Identity enumeration
- Count and categorize identities: human users, service accounts, API keys, external/guest users
- Identify identity sources: internal directory, SSO, local accounts, federated
- Last activity timestamp for each identity
- Dormant accounts (no activity in 90+ days)
- Orphaned accounts (no owner, former employees)
-
Authentication assessment
- MFA enrollment status for all human users
- MFA enforcement (required vs optional)
- Password policy compliance
- Service account authentication method (keys, certificates, managed identity)
Phase 2: Permission Analysis
-
Role/permission inventory
- All defined roles and their permissions
- Number of users per role
- Roles with no users (dormant roles)
- Roles with excessive permissions (admin-equivalent)
- Custom vs predefined roles
-
Permission usage analysis (if access logs available)
- Granted permissions vs actually used permissions per identity
- Identities using less than 20% of granted permissions (over-privileged)
- Permissions never used by any identity (candidate for removal)
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.
- 12d ago Changed · +5 lines · +36 tokens per session d215bad436bc
- 1mo ago First seen · 126 lines · 0 tokens per session scan A 422ba8d9fc26
iam-audit is a command published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 9d ago), licensed MIT. It adds 36 tokens to every session and 1,020 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
verify
An independent recheck of a security assessment report that derives conclusions from its own evidence instead of accepting the original findings.
corporate-launcher
Build a secure, branded, organization-specific launcher around an AI coding CLI (Claude Code, Codex CLI, Gemini CLI, Cursor, or Cline) so the user can.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.