nexus-gateway: Skill for Claude Code

.claude/skills/oss-secret-scan/SKILL.md

oss-secret-scan is a skill for Claude Code from AlphaBitCore/nexus-gateway. It costs 159 tokens per session (1,496 once invoked), scanned A, original, Apache-2.0.

A two-stage repository scanner for finding leaked secrets, personal information, and production infrastructure details before an open-source release. A deterministic script finds candidates, while an agent reviews whether they are real leaks.

In plain words
What is it for?
Use it before a public release, after importing production data or rewriting history, and as a recurring CI check; it can scan for candidates and apply severity thresholds.
Why use it?
It reduces the risk of publishing passwords, API keys, private keys, internal addresses, or identifying machine data. The automated scan provides consistent coverage instead of relying only on a person or model to notice problems.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is AlphaBitCore/nexus-gateway's own configuration. It tells Claude Code how to work on nexus-gateway 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 nexus-gateway configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AlphaBitCore/nexus-gateway. 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/AlphaBitCore/nexus-gateway/main/.claude/skills/oss-secret-scan/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/AlphaBitCore/nexus-gateway

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 oss-secret-scan

README.md
[![agentmods](https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/oss-secret-scan/github.svg)](https://agentmods.dev/skills/alphabitcore/nexus-gateway/oss-secret-scan)
Your own site
<a href="https://agentmods.dev/skills/alphabitcore/nexus-gateway/oss-secret-scan"><img src="https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/oss-secret-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.

agentmods 80×15 button for oss-secret-scan

Your own site · 80×15
<a href="https://agentmods.dev/skills/alphabitcore/nexus-gateway/oss-secret-scan"><img src="https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/oss-secret-scan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 159 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,496 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00159 $0.01496
Opus 5 $0.00079 $0.00748
Sonnet 5 $0.00032 $0.00299
Haiku 4.5 $0.00016 $0.00150

Measured 11d ago against content hash ee72110cc83f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

oss-secret-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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scan.py), 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/oss-secret-scan/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OSS secret / PII scan

A two-layer scanner. Layer 1 is deterministic (scan.py: regex + Shannon entropy + allowlist) and does 100% of the detection — an LLM is never trusted to "look for secrets" because it drifts and silently misses things. Layer 2 is the LLM (you), which only triages the deterministic candidate list and applies fixes. This split is the whole point: comprehensiveness comes from the script, judgment comes from the model.

When to use

  • Before an OSS release / first public push of the repo.
  • After rewriting git history or importing prod data into seeds/fixtures.
  • After any change that copies prod debugging output into committed files.
  • As a recurring gate (wire scan.py --severity medium into CI).

How to run

# 1. Deterministic scan (machine-readable, every category):
python3 .claude/skills/oss-secret-scan/scan.py --json > /tmp/leak-candidates.json

# 2. Human summary, real-leak severities only (CI gate level):
python3 .claude/skills/oss-secret-scan/scan.py --severity medium

# Options:
#   --severity {critical|high|medium|low}  floor (default low = everything)
#   --include-archive                       also scan docs/_archive (default: skip)
#   --allow FILE                            extra allowlist (default .secret-scan-allow)
#   --paths a b ...                         scan only these paths
# Exit code is 1 when any finding at/above the severity floor remains.

The script scopes to git-tracked text files, skips binaries / lockfiles / node_modules / dist, and tags any hit inside a test fixture (testdata/, *_test.*, /fixtures/, …) as likely_intentional so triage can sort real leaks to the top.

Detectors and severity

Severity Categories
CRITICAL private keys (PEM), AWS secret keys, GCP private_key, DB connection strings with an embedded password (non-localhost)
HIGH AWS access keys, OpenAI/GitHub/Slack/Google/Stripe tokens, JWTs, password=/secret=/token= assignments
MEDIUM public IPv4 (RFC1918 / loopback / TEST-NET excluded), Mac serials, machine IDs / device fingerprints, non-allowlisted emails, EC2 internal hostnames
LOW non-allowlisted domains, generic high-entropy strings (report-only signal)

Read the full file on GitHub · 114 lines

Files

What ships with it

1 file 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. 11d ago First seen · 114 lines · 159 tokens per session scan A ee72110cc83f

Subscribe to this mod's changes

oss-secret-scan is a skill published in the GitHub repository AlphaBitCore/nexus-gateway (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 159 tokens to every session and 1,496 once invoked, about $0.0008 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 2026-08-30.

Related

Other skills, from other repositories