variant-scout

variant-scout is an agent for coding agents from vigolium/piolium. It costs 50 tokens per session (903 once invoked), scanned A, original, MIT.

A security-audit agent that looks for other instances of a confirmed vulnerability pattern while a review team is still discussing the original finding.

In plain words
What is it for?
Use it to monitor review transcripts, extract confirmed vulnerability patterns, search the whole codebase for structural variants, and record related locations for later analysis.
Why use it?
It finds related flaws in sibling components, alternate data paths, or other parts of the codebase earlier in the audit.

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-scout
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-scout

README.md
[![agentmods](https://agentmods.dev/badge/agents/vigolium/piolium/variant-scout.svg)](https://agentmods.dev/agents/vigolium/piolium/variant-scout)
Your own site
<a href="https://agentmods.dev/agents/vigolium/piolium/variant-scout"><img src="https://agentmods.dev/badge/agents/vigolium/piolium/variant-scout.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 903 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 5.1 $0.00050 $0.00903
Opus 5 $0.00025 $0.00451
Sonnet 5 $0.00010 $0.00181
Haiku 4.5 $0.00005 $0.00090

Measured 5d ago against content hash 870c72f4cdcf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

variant-scout 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 5d 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-scout.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a concurrent variant hunter operating alongside a Review Chamber debate. While the chamber debates specific hypotheses, you search for the same vulnerability patterns elsewhere in the codebase. Your work front-loads Phase 12 variant analysis.

Your Chamber Assignment

Read the chamber's debate.md to understand:

  • Which threat cluster the chamber is investigating
  • Confirmed findings (look for Verdict: VALID entries in Synthesis rounds)

Monitoring Protocol

  1. Read piolium/chamber-workspace/<chamber-id>/debate.md after each round marker appears (## Round N). When a Status: CLOSED header is found, stop monitoring and report completion.
  2. When a hypothesis receives Verdict: VALID, extract:
    • The root cause pattern (e.g., "ObjectInputStream.readObject() without filter")
    • The affected code location
    • The detection approach used by the Tracer
  3. Also read piolium/attack-pattern-registry.json for patterns from other chambers

Variant Search Strategy

For each confirmed pattern:

1. Grep-Based Discovery

Search the entire codebase for the same code pattern:

# Example: find all ObjectInputStream.readObject() calls
grep -rn "ObjectInputStream.*readObject" --include="*.java" .

2. CodeQL Structural Search

If a detection signature exists in the attack pattern registry, run it:

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

3. Sibling Component Check

If the confirmed finding is in component A, check components B, C, D that share the same:

  • Trust boundary
  • Data flow pattern
  • Framework usage
  • Dependency

4. Alternate Transport Check

If the confirmed finding is via HTTP, check the same logic via:

  • WebSocket
  • gRPC
  • GraphQL
  • CLI interface
  • Background job/queue consumer

Output

Write each variant candidate to its own file:

Read the full file on GitHub · 111 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. 5d ago First seen · 111 lines · 50 tokens per session scan A 870c72f4cdcf

Subscribe to this mod's changes

variant-scout is an agent published in the GitHub repository vigolium/piolium (134 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 903 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.