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/ByamB4/find-cve-agentWrote 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/byamb4/find-cve-agent/check-nvd)<a href="https://agentmods.dev/commands/byamb4/find-cve-agent/check-nvd"><img src="https://agentmods.dev/badge/commands/byamb4/find-cve-agent/check-nvd/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/byamb4/find-cve-agent/check-nvd"><img src="https://agentmods.dev/badge/commands/byamb4/find-cve-agent/check-nvd.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 | $0.00038 | $0.00766 |
| Opus 5 | $0.00019 | $0.00383 |
| Sonnet 5 | $0.00008 | $0.00153 |
| Haiku 4.5 | $0.00004 | $0.00077 |
Grade B, and why
check-nvd scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s "https://api.osv.dev/v1/query" -d "{\"package\":{\"name\":\"$ARGUMENTS\",\"ecosystem\":\"PyPI\"}}" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s "https://api.osv.dev/v1/query" \ How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/check-nvd
Check if a package has existing CVEs in NVD, OSV.dev, and GitHub Security Advisories.
Process
Step 1: Query OSV.dev
# Query OSV.dev for known vulnerabilities
curl -s "https://api.osv.dev/v1/query" \
-H "Content-Type: application/json" \
-d "{\"package\":{\"name\":\"$ARGUMENTS\",\"ecosystem\":\"npm\"}}" \
| python3 -m json.tool
If the package is not on npm, try other ecosystems:
# PyPI
curl -s "https://api.osv.dev/v1/query" -d "{\"package\":{\"name\":\"$ARGUMENTS\",\"ecosystem\":\"PyPI\"}}"
# Go
curl -s "https://api.osv.dev/v1/query" -d "{\"package\":{\"name\":\"$ARGUMENTS\",\"ecosystem\":\"Go\"}}"
# RubyGems
curl -s "https://api.osv.dev/v1/query" -d "{\"package\":{\"name\":\"$ARGUMENTS\",\"ecosystem\":\"RubyGems\"}}"
Step 2: Query GitHub Security Advisories
# Search GitHub Advisory Database
gh api graphql -f query='
{
securityAdvisories(first: 20, orderBy: {field: PUBLISHED_AT, direction: DESC}, identifier: {type: CVE, value: ""}) {
nodes {
ghsaId
summary
severity
publishedAt
identifiers { type value }
}
}
}'
# Or search by package name
gh api "/advisories?ecosystem=npm&package=$ARGUMENTS" 2>/dev/null
Step 3: Check the Repo Directly
# Find the GitHub repo
npm view "$ARGUMENTS" repository.url 2>/dev/null
# Check repo security advisories
gh api "repos/<owner>/<repo>/security-advisories" 2>/dev/null
Step 4: Summarize Results
Present a summary:
CVE CHECK: <package-name>
Total CVEs found: <count>
Severity breakdown:
CRITICAL: <count>
HIGH: <count>
MEDIUM: <count>
LOW: <count>
Recent CVEs (last 12 months):
<CVE-ID> | <severity> | <summary> | <date>
<CVE-ID> | <severity> | <summary> | <date>
Recent security fixes (from git log):
<commit hash> | <date> | <message>
Assessment:
<0-3 CVEs>: Under-audited. Good target.
<4-10 CVEs>: Moderately audited. Proceed with caution -- look for incomplete fixes.
<>10 CVEs>: Over-audited. Skip unless looking for fix bypasses.
Incomplete fix opportunities:
<List any CVEs where the fix might be incomplete based on the patch>
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 · 105 lines · 38 tokens per session scan B df610ed93a08
check-nvd is a command published in the GitHub repository ByamB4/find-cve-agent (48 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 38 tokens to every session and 766 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.
adr-supersede
Create a new ADR that supersedes an existing one.