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/hunt)<a href="https://agentmods.dev/commands/byamb4/find-cve-agent/hunt"><img src="https://agentmods.dev/badge/commands/byamb4/find-cve-agent/hunt.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 5.1 | $0.00040 | $0.01012 |
| Opus 5 | $0.00020 | $0.00506 |
| Sonnet 5 | $0.00008 | $0.00202 |
| Haiku 4.5 | $0.00004 | $0.00101 |
Grade B, and why
hunt scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s "https://api.osv.dev/v1/query" -d '{"package":{"name":"$ARGUMENTS","ecosystem":"npm"}}' 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" -d '{"package":{"name":"$ARGUMENTS","ecosystem":"npm"}}' How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hunt
Run the full CVE hunting pipeline on a target package.
Pipeline Steps
Execute these steps in order. Stop if any step fails.
Step 1: Registry Check
Check if this package has already been investigated:
- Read REGISTRY.md and search for the package name
- Query NVD/OSV for existing CVEs:
curl -s "https://api.osv.dev/v1/query" -d '{"package":{"name":"$ARGUMENTS","ecosystem":"npm"}}' - If found in registry as SUBMITTED/SKIP/DUPLICATE -> report status and STOP
- If found as FALSE_POSITIVE -> show reason and ask Director if they want to re-investigate
- If CLEAN -> proceed
Step 2: Target Reconnaissance
Gather target information:
- Get repo metadata:
gh search repos "$ARGUMENTS" --json fullName,stargazerCount,updatedAt,description --limit 5 - Check npm download counts:
curl -s "https://api.npmjs.org/downloads/point/last-week/$ARGUMENTS" - Check for SECURITY.md, bug bounty info
- List existing security advisories:
gh api "repos/<owner>/<repo>/security-advisories" 2>/dev/null - Create
targets/<package>/brief.mdwith findings
Step 3: Clone and Setup
# Clone the repo
git clone --depth 1 <repo-url> targets/<package>/repo
# Check the version
cat targets/<package>/repo/package.json | python3 -c "import sys,json; print(json.load(sys.stdin)['version'])"
Step 4: Hunter Code Review
Perform systematic code review as the Hunter agent:
- Map attack surface based on package type
- Search for vulnerability patterns (Tier 1 first, then Tier 2, then Tier 3)
- For each potential finding, trace the full data flow: source -> transforms -> sink
- Document findings in
targets/<package>/findings.md
If no findings after thorough review:
- Record in REGISTRY.md as SKIP with vectors checked
- Report to Director: "No vulnerabilities found in . Checked: ."
- STOP
Step 5: PoC Development
For each finding:
- Present the PoC plan to the Director:
Finding: <description> Root cause: <file:line> Plan: <approach> Chaining: <opportunities> CVSS: <estimated score> Approve? - Wait for Director approval
- Write PoC script at
targets/<package>/poc_<vuln_type>.py - Test that the PoC runs and produces expected output
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.
- 7d ago First seen · 129 lines · 40 tokens per session scan B 08559f278a79
hunt is a command published in the GitHub repository ByamB4/find-cve-agent (48 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,012 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.
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.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
check-dev
Type-check a Z specification with fuzz.