nifra: Skill for Claude Code

.claude/skills/security-checkup/SKILL.md

security-checkup is a skill for Claude Code from nifrajs/nifra. It costs 87 tokens per session (987 once invoked), scanned A, original, MIT.

A deterministic security scanner for a code repository. It checks dependencies, committed secrets, unsafe code patterns, and the project's verification checks without using AI.

In plain words
What is it for?
Use it before commits or in CI to find vulnerable dependencies, leaked secrets, and risky code patterns. It writes JSON and Markdown reports that can also be used for dashboards.
Why use it?
It brings different security checks into one consistent report and gives CI a clear pass-or-fail result. This reduces the need to run and interpret several tools separately.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

This is nifrajs/nifra's own configuration. It tells Claude Code how to work on nifra itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything nifra configures →

Reuse

Borrowing it

Nothing to install: this file belongs to nifrajs/nifra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/nifrajs/nifra/main/.claude/skills/security-checkup/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/nifrajs/nifra

Made for: Claude Code.

Wrote 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.

agentmods badge for security-checkup

README.md
[![agentmods](https://agentmods.dev/badge/skills/nifrajs/nifra/security-checkup.svg)](https://agentmods.dev/skills/nifrajs/nifra/security-checkup)
Your own site
<a href="https://agentmods.dev/skills/nifrajs/nifra/security-checkup"><img src="https://agentmods.dev/badge/skills/nifrajs/nifra/security-checkup.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 987 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00087 $0.00987
Opus 5 $0.00044 $0.00494
Sonnet 5 $0.00017 $0.00197
Haiku 4.5 $0.00009 $0.00099

Measured 8d ago against content hash 67ed9765cfc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

security-checkup 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 8d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/probes.ts, scripts/report.ts, scripts/run.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/security-checkup/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

security-checkup

A deterministic security scanner. It shells out to pinned tools, normalizes their output into one Finding schema, writes two artifacts, and exits with a contract CI can gate on. No model calls.

It complements, and does not replace, nifra's own securityBaseline() route-assurance preset: security-checkup scans the whole repo (deps, secrets, patterns); securityBaseline() proves per-route invariants at nifra check. Ship both.

Run it

bun .claude/skills/security-checkup/scripts/run.ts
flag behavior exit
(default) all probes; artifacts written 1 if any un-suppressed finding >= high
--fast deps + secrets only (pre-commit) 1 on any un-suppressed >= high
--report-only scan + write artifacts always 0 (dashboards, never blocks)
--strict-tools pinned-tool version drift is fatal 2 on drift
--severity <sev> override gate threshold (critical..info) 1 at/above threshold
--out <dir> artifact dir (default .security) -

Exit codes: 0 clean / report-only, 1 findings at-or-above threshold, 2 operational failure (unreadable repo, --strict-tools drift, malformed probe output). A crashed probe is a 2, never a silent 0; a missing scanner prints DEGRADED: <probe> and still gates on the rest.

Probes (pinned)

probe tool pin detects
deps osv-scanner 2.4.0 vulnerable dependencies
secrets gitleaks 8.30.1 committed secrets (value never written to the artifact)
patterns semgrep 1.99.0 taint / unsafe-API rules in rules/semgrep.yml
verify bun run verify repo the project gate, incl. nifra route assurance
outdated bun outdated repo stale deps (advisory, info)

Update pins in scripts/probes.ts (TOOL_PINS). Drift is reported as a high finding, or fatal under --strict-tools.

Artifacts

Written to .security/ (git-ignore it or commit it, your call):

Read the full file on GitHub · 94 lines

Files

What ships with it

7 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.

Changes

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.

  1. 8d ago First seen · 94 lines · 87 tokens per session scan A 67ed9765cfc4

Subscribe to this mod's changes

security-checkup is a skill published in the GitHub repository nifrajs/nifra (2 stars, last pushed 5d ago), licensed MIT. It adds 87 tokens to every session and 987 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.