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/secrets-audit)<a href="https://agentmods.dev/commands/hermeticormus/libresecops-claude-code/secrets-audit"><img src="https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/secrets-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/secrets-audit"><img src="https://agentmods.dev/badge/commands/hermeticormus/libresecops-claude-code/secrets-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 | $0.00035 | $0.01029 |
| Opus 5.5 | $0.00014 | $0.00412 |
| Sonnet 5.5 | $0.00007 | $0.00206 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade A, and why
secrets-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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/secrets-audit
Scan a project for hardcoded secrets, exposed credentials, and secret management anti-patterns.
Trigger
Use when you need to find leaked secrets in a codebase. Appropriate for:
- Security review of a new or acquired codebase
- Pre-deployment security check
- After a suspected credential leak
- Periodic hygiene scan
- Onboarding to a project to understand its secret handling
Input
The command operates on the current project directory. It examines:
- Source code: All tracked and untracked files in the repository
- Git history: Full commit history for secrets that were added then removed
- Configuration files: .env, .env.*, config files, YAML, JSON, TOML, properties files
- CI/CD configurations: .github/workflows/*, .gitlab-ci.yml, Jenkinsfile, docker-compose.yml
- Container files: Dockerfile, docker-compose.yml (secrets in build args or environment)
- Documentation: README, docs (sometimes contain example credentials that are real)
Optional flags:
--history-- include full git history scan (slower, more thorough)--verify-- attempt to verify if detected secrets are still valid (requires network access)--fix-- generate .gitignore updates and pre-commit hook configuration
Process
-
Repository Analysis: Identify the tech stack, frameworks, and cloud providers in use. This determines which secret patterns to prioritize (AWS keys for AWS projects, database strings for backend services, etc.).
-
Current Tree Scan: Scan all files in the current working tree for secret patterns:
- Known credential formats (AWS keys, GCP service accounts, GitHub tokens, etc.)
- Generic high-entropy strings in security-sensitive contexts (variable names containing
secret,password,token,key,credential) - Hardcoded connection strings with embedded credentials
- Private keys (RSA, EC, Ed25519) in source code or configuration
-
Git History Scan (with
--history): Scan the full git history for:- Secrets that were committed and then removed (still in history)
- Secrets in deleted branches (if reachable)
- Large binary blobs that might contain credential stores
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 · +35 tokens per session f436e6ef7432
- 1mo ago First seen · 104 lines · 0 tokens per session scan A e8f40b5e87d6
secrets-audit is a command published in the GitHub repository HermeticOrmus/LibreSecOps-Claude-Code (4 stars, last pushed 9d ago), licensed MIT. It adds 35 tokens to every session and 1,029 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
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
squash
Squash the current jj change into its parent.
aigon-research-spec-revise
You are the author-side agent. Review all pending spec-review: commits on the research spec, decide what to keep, and land one acknowledgement commit.
cl-merge
Shortcut for /quorum:merge — squash-merge worktree branch.
checkpoint
Save a git checkpoint commit of the current working state.