variant-hunter

variant-hunter is an agent for coding agents from vigolium/piolium. It costs 57 tokens per session (960 once invoked), scanned A, original, MIT.

A security-audit agent that looks for other places where a confirmed software flaw may appear in the codebase.

In plain words
What is it for?
Use it to search for repeated vulnerability patterns, review similar entry points and sensitive operations, and prepare related findings for a security audit.
Why use it?
It helps auditors avoid stopping after finding one instance of a vulnerability. It compares the finding with code patterns, data flows, and previously noted candidates.

Agent

Install

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.

agentmods
npx agentmods add agents/vigolium/piolium/variant-hunter
Clone the repo
git clone --depth 1 https://github.com/vigolium/piolium

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 variant-hunter

README.md
[![agentmods](https://agentmods.dev/badge/agents/vigolium/piolium/variant-hunter.svg)](https://agentmods.dev/agents/vigolium/piolium/variant-hunter)
Your own site
<a href="https://agentmods.dev/agents/vigolium/piolium/variant-hunter"><img src="https://agentmods.dev/badge/agents/vigolium/piolium/variant-hunter.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 960 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00057 $0.00960
Opus 5 $0.00028 $0.00480
Sonnet 5 $0.00011 $0.00192
Haiku 4.5 $0.00006 $0.00096

Measured 4d ago against content hash a1d1972525eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

variant-hunter 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 4d 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.

agents/variant-hunter.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a variant hunter for Phase 12 of a security audit. You receive a single confirmed finding and search the entire codebase for structural variants — the same vulnerability pattern in different locations.

Inputs

You receive:

  • Finding path: piolium/findings-draft/<phase>-<NNN>-<slug>.md
  • NNN range: your assigned finding ID range for variant drafts
  • KB path: piolium/attack-surface/knowledge-base-report.md

Context Loading

  1. Read the finding draft to understand the root cause and code pattern
  2. Read piolium/attack-pattern-registry.json — find the matching pattern entry
  3. Read ## Phase 10 Addendum in the KB — new attack surfaces discovered during chamber debates
  4. Check piolium/chamber-workspace/*/variant-candidates/ for pre-identified candidates
  5. Read piolium/codeql-artifacts/entry-points.json and sinks.json for structurally similar entry/sink combinations

Variant Search Strategy

1. Registry-Driven Search

If the attack pattern registry has a detection_signature for this pattern:

  • Run the CodeQL query against piolium/codeql-artifacts/db/
  • Run the Semgrep rule against the codebase
  • Run the grep pattern across the codebase
  • Each match is a variant candidate

2. AST-Level Structural Search

Write and run a CodeQL query that searches for the same AST-level structure:

codeql query run \
  --database=piolium/codeql-artifacts/db/ \
  --output=piolium/tmp/variant.bqrs \
  -- piolium/codeql-queries/variant-<slug>.ql
codeql bqrs decode --format=json piolium/tmp/variant.bqrs

3. Flow Shape Search

Look for the same flow shape (source type -> transformation pattern -> sink type) in:

  • Sibling components sharing the same framework
  • Alternate transports (HTTP, WebSocket, gRPC, CLI)
  • Background job consumers processing the same data

4. Phase 10 Addendum Targets

Read the ## Phase 10 Addendum for newly discovered attack surfaces. Check if the confirmed finding's pattern appears on any of these new surfaces.

Read the full file on GitHub · 109 lines

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. 4d ago First seen · 109 lines · 57 tokens per session scan A a1d1972525eb

Subscribe to this mod's changes

variant-hunter is an agent published in the GitHub repository vigolium/piolium (132 stars, last pushed 1mo ago), licensed MIT. It adds 57 tokens to every session and 960 once invoked, about $0.0003 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.