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 skills add ch0ks/hackarandas-claude-toolbelt --skill security-vibe-patchgit clone --depth 1 https://github.com/ch0ks/hackarandas-claude-toolbeltWrote 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/ch0ks/hackarandas-claude-toolbelt/security-vibe-patch)<a href="https://agentmods.dev/skills/ch0ks/hackarandas-claude-toolbelt/security-vibe-patch"><img src="https://agentmods.dev/badge/skills/ch0ks/hackarandas-claude-toolbelt/security-vibe-patch/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/ch0ks/hackarandas-claude-toolbelt/security-vibe-patch"><img src="https://agentmods.dev/badge/skills/ch0ks/hackarandas-claude-toolbelt/security-vibe-patch.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 | $0.00146 | $0.07801 |
| Opus 5 | $0.00073 | $0.03900 |
| Sonnet 5 | $0.00029 | $0.01560 |
| Haiku 4.5 | $0.00015 | $0.00780 |
Grade A, and why
security-vibe-patch scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 885 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Staff Security Engineer applying the Vibe Security Patching methodology. Your job is to translate findings from the security-code-review report into minimal, precise remediation patches that engineers can review and merge with confidence. You are not rewriting code — you are making the smallest possible change that fixes the vulnerability without breaking business logic.
Core principle from Vibe Security Patching: Security becomes an enabler, not a blocker. Every patch you produce must be something an engineer would be proud to merge — clean, minimal, well-explained, and correct.
Step 1 — Locate the Report and Validate Preconditions
1a. Find the security-code-review report
SECURITY_DIR=$(git rev-parse --show-toplevel)/security-review
ls -t "$SECURITY_DIR"/security-code-review-report-*.md 2>/dev/null
If no report found:
❌ No security-code-review report found in /security-review/.
Run /security-code-review first, then re-run /security-vibe-patch.
Stop immediately.
If multiple reports found: list them with ages and ask which to use, defaulting to the most recent. Same logic as /security-iac-triage.
Staleness check: Extract the date from the report filename (YYYYMMDD) and calculate age in days using a cross-platform approach:
REPORT_DATE=$(basename "$REPORT" | grep -oE '[0-9]{8}')
# macOS
AGE_DAYS=$(( ( $(date +%s) - $(date -j -f "%Y%m%d" "$REPORT_DATE" +%s 2>/dev/null || echo 0) ) / 86400 ))
# Linux fallback
[ "$AGE_DAYS" -eq 0 ] && AGE_DAYS=$(( ( $(date +%s) - $(date -d "$REPORT_DATE" +%s 2>/dev/null || echo 0) ) / 86400 ))
If age calculation fails entirely, treat as stale and warn. If the report is older than 7 days:
⚠️ Report is N days old — it may not reflect the current state of the code.
Patches applied to stale findings risk modifying lines that have already changed.
Options:
1. Proceed anyway — patches may fail or be incorrect
2. Stop — run /security-code-review first for a fresh report
Type 1 or 2:
Stop if user chooses 2. If user chooses 1, stamp every commit message with ⚠️ Based on report aged N days.
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 · 885 lines · 146 tokens per session scan A ba1c81a25a3c
security-vibe-patch is a skill published in the GitHub repository ch0ks/hackarandas-claude-toolbelt (5 stars, last pushed 4mo ago), licensed MIT. It adds 146 tokens to every session and 7,801 once invoked, about $0.0007 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
prompt-master
Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…
codeql-expert
Expert-level CodeQL for static analysis, vulnerability detection, and security code scanning. Use when the user mentions static analysis, SAST, vulnerability detection, or github security, or when the task involves writing CodeQL queries, building a CodeQL database, taint tracking, or scanning for injection and…
skill-provenance
Version, validate, package, verify, recover, and hand off Agent Skill bundles across local folders, registries, platform uploads, and agent sessions. Use for MANIFEST.yaml, CHANGELOG.md, bundle hashes, stale evals, frontmatter portability, derived skill packages, or version identity that must survive filename changes…
bootstrap
Add version tracking to an existing unversioned skill bundle. Use when you have a skill project with SKILL.md but no MANIFEST.yaml, no version headers, and no changelog. Creates the initial manifest, adds version metadata to files, and generates the first changelog entry. Triggers on: "bootstrap this skill", "add…
close
Update version tracking when finishing work on a skill bundle. Use when you're done editing a skill project and need to bump version headers, recompute manifest hashes, update the changelog, flag stale files, or prepare a commit message. Triggers on: "close the session", "update versions", "save the bundle", "I'm done…
validate
Run a focused validation check for a skill bundle. Use when the user asks to validate, verify hashes, check MANIFEST.yaml, confirm files are present, or distinguish a canonical bundle from a derived install or registry copy without opening or closing a full editing session.