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/mertjane/awesome-claude-commandsWrote 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/mertjane/awesome-claude-commands/security-scan)<a href="https://agentmods.dev/commands/mertjane/awesome-claude-commands/security-scan"><img src="https://agentmods.dev/badge/commands/mertjane/awesome-claude-commands/security-scan/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/mertjane/awesome-claude-commands/security-scan"><img src="https://agentmods.dev/badge/commands/mertjane/awesome-claude-commands/security-scan.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 | $0.00030 | $0.01446 |
| Opus 5 | $0.00015 | $0.00723 |
| Sonnet 5 | $0.00006 | $0.00289 |
| Haiku 4.5 | $0.00003 | $0.00145 |
Grade A, and why
security-scan 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 9d 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Vulnerability Scan
Scan the project's source code for security vulnerabilities and produce a prioritized report.
If $ARGUMENTS is provided, limit the scan to that path. Otherwise scan the entire project.
Step 1 — Discover Source Files
Glob for files to scan (exclude node_modules, .git, dist, .next, build, coverage):
**/*.{ts,tsx,js,jsx,mjs,cjs}
**/*.{py,go,rb,php,java}
**/*.{sql,env,yaml,yml,json,toml}
If $ARGUMENTS is provided, scope the glob to that directory.
Step 2 — Hardcoded Secrets
For every file, search for patterns that suggest embedded credentials:
API keys and tokens:
- Patterns:
sk-[a-zA-Z0-9]{20,},ghp_[a-zA-Z0-9]{36},AIza[0-9A-Za-z-_]{35},AKIA[0-9A-Z]{16} - Variable assignments where key contains
SECRET,API_KEY,TOKEN,PASSWORD,PRIVATE_KEYand value is a non-empty string literal (notprocess.env.*, not${...})
Connection strings with passwords:
- Patterns:
(mongodb|postgresql|mysql|redis):\/\/[^:]+:[^@]+@ password\s*[:=]\s*["'][^"']{3,}["'](inline password assignment)
Private keys:
-----BEGIN (RSA|EC|OPENSSH|PGP) PRIVATE KEY-----
Severity: CRITICAL — these must be rotated and moved to environment variables.
Step 3 — SQL Injection
Search for raw SQL string concatenation patterns in .ts, .js, .py, .php, .java files:
Dangerous patterns:
`SELECT * FROM ${`or"SELECT * FROM " +(template literal or concat with variable)query("... WHERE id = " + req.params)execute(f"SELECT ... {user_input}")(Python f-string in SQL).raw(calls without parameterization
Safe patterns to ignore:
$1,?,:paramplaceholders- ORM query builders (
.where({ id: userId }),.findOne(id))
Severity: HIGH for any raw concatenation with request/user data.
Step 4 — Cross-Site Scripting (XSS)
In .tsx, .jsx, .html, .ejs, .hbs files:
Dangerous patterns:
dangerouslySetInnerHTML={{ __html:with a variable (not a static string)innerHTML =assigned from user input or request datadocument.write(with variable contenteval(ornew Function(with non-literal argumentv-html="in Vue templates with variable
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.
- 9d ago First seen · 176 lines · 30 tokens per session scan A 9686b4a31977
security-scan is a command published in the GitHub repository mertjane/awesome-claude-commands (2 stars, last pushed 6mo ago), licensed MIT. It adds 30 tokens to every session and 1,446 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other commands, from other repositories
session-start
Thin wrapper (GETSITREP-10) — orientation logic (reading MANIFEST.md/STATUSREPORT.md/PROJECTPLAN.md/.sitrep-data.json, building the summary) lives entirely in getsitrep session-start. This file's only job is to invoke it and show the result — it does not re-read those files or re-derive the summary itself.
handoff
Thin wrapper (GETSITREP-10) — generating sitrep/HANDOFF.md (archiving the previous one first), tailoring to a human or AI audience, and committing all live in getsitrep handoff.
decompose
Feature/story breakdown — consume a ready-for-decompose scope doc and produce a task graph in the issue tracker. Re-entrant; tracker-as-canonical with vault breadcrumb.
which-effort
Effort recommendation only for this task. Shows a narrow ladder of just the effort level, from a lower setting to a higher one, for a model named in the task or else the one you are on.
budget
Marks the cheapest Claude model and effort that still clears this task with high confidence. Still shows the full Budget, Optimal, and Splurge spread.
dossier
Force load of Dossier vault profile (and inbox check) before processing the rest of the user's request.