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.
npx agentmods add skills/joaovicdev/claude-owasp-10/api-secure-reportnpx skills add joaovicdev/claude-owasp-10 --skill api-secure-reportgit clone --depth 1 https://github.com/joaovicdev/claude-owasp-10Wrote 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/joaovicdev/claude-owasp-10/api-secure-report)<a href="https://agentmods.dev/skills/joaovicdev/claude-owasp-10/api-secure-report"><img src="https://agentmods.dev/badge/skills/joaovicdev/claude-owasp-10/api-secure-report.svg" alt="Measured on agentmods" 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 | $0.00071 | $0.02002 |
| Opus 5 | $0.00036 | $0.01001 |
| Sonnet 5 | $0.00014 | $0.00400 |
| Haiku 4.5 | $0.00007 | $0.00200 |
Grade A, and why
api-secure-report 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 4d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
API security report
Produces one artifact: an inventory of every route in the project under review, each marked clean or carrying findings, plus a findings section stating what is wrong, how an attacker reaches it, and what fixes it.
This skill is a consumer of the secure-coding skill. It never restates
security material — it reads that skill's files and cites their stable ids
(A01.Q2, NEST.3). If a rule seems missing, the fix is to add a review
question there, not to invent one here.
Nothing in this skill modifies the project under review. It has no Edit, and
the only file it writes is the report itself.
Arguments
/api-secure-report [language] [path] — both positional, both optional.
| Argument | Default | Meaning |
|---|---|---|
language |
pt-BR |
Output language: pt-BR, en, es, … Anything that is not a recognized language tag is treated as path. |
path |
repository root | Restrict the scan to a subdirectory. Stated in the report header when set. |
Step 1 — Resolve the two roots, then load the rules
Everything downstream is addressed by absolute path, so establish both roots before anything else and reuse them verbatim.
-
RULES_ROOT— thesecure-codingskill directory. It is the sibling of this skill: resolve../secure-coding/against the directory thisSKILL.mdwas loaded from, and make it absolute. That holds in every installation — plugin cache, a project's.claude/skills/, or the user's global skills directory — because the two skills always ship side by side.If
RULES_ROOT/SKILL.mddoes not exist, stop and say so, naming the path you tried. Never continue with a partial rule set: a scan missing its rules produces a clean-looking report, which is worse than no report. -
SCAN_ROOT— the root of the project under review, absolute; thepathargument if given, otherwise the repository root. -
Read
RULES_ROOT/SKILL.mdand use its manifest and stack-detection table. Do not duplicate that table here.
What ships with it
2 files 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.
- 4d ago First seen · 158 lines · 71 tokens per session scan A f7ddcdac8928
api-secure-report is a skill published in the GitHub repository joaovicdev/claude-owasp-10 (2 stars, last pushed 9d ago), licensed MIT. It adds 71 tokens to every session and 2,002 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
Test Scaffold (Laravel/PHPUnit)
Generate PHP/Laravel (PHPUnit) test skeletons from specifications.
Laravel Eloquent N+1 and Query Efficiency Review
Detects N+1 query patterns (relation access inside loops without eager loading), full-table get()/all() loads, and unsafe chunk()/cursor() usage in Laravel Eloquent code.
Laravel Mass Assignment and Authorization Review
Detects mass assignment via create/update($request->all()), unguarded models, and missing authorization on mutating controller actions in Laravel.
Laravel Migration Safety Review
Reviews Laravel migrations for destructive operations, change() dropping modifiers, locking index creation on large tables (PostgreSQL), and asymmetric down().
security-sweep
Scan codebase for security vulnerabilities, hardcoded secrets, injection flaws, misconfigurations, and attack surfaces. Use when user wants a security audit, vulnerability scan, or to find security issues.
security-scan
This skill should be used when the user asks to "run a security scan", "check for vulnerabilities", "security audit", "ship secure", "vibecheck scan", or "pre-deploy security check". Runs 156 automated security checks across 15 categories and produces a categorized vulnerability report.