crossval-harness

crossval-harness is a skill for Claude Code, Codex from William2333ZZ/trustshell. It costs 75 tokens per session (693 once invoked), scanned A, original, MIT.

A workflow that combines static code scanning with live attack tests against an AI agent you are authorized to test. It treats an issue as confirmed only when an exploit works, then connects the result back to the responsible code path.

In plain words
What is it for?
Use it to scan an agent's source, test candidate prompt-injection, memory-poisoning, sandbox-escape, or action-gating paths, and correlate successful exploits with their code causes.
Why use it?
It reduces false alarms from code scanning and avoids reporting an attack without evidence. The process also explains the root cause and potential impact of confirmed findings.

Skill for Claude CodeCodex

Part of the trustshell plugin — 12 skills, 2 commands, 1 agent shipped together

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 skills/william2333zz/trustshell/crossval-harness
Any agent
npx skills add William2333ZZ/trustshell --skill crossval-harness
Clone the repo
git clone --depth 1 https://github.com/William2333ZZ/trustshell

Made for: Claude Code, Codex.

Or install trustshell, the plugin that ships this one along with the rest of its 12 skills, 2 commands, 1 agent.

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 crossval-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/william2333zz/trustshell/crossval-harness.svg)](https://agentmods.dev/skills/william2333zz/trustshell/crossval-harness)
Your own site
<a href="https://agentmods.dev/skills/william2333zz/trustshell/crossval-harness"><img src="https://agentmods.dev/badge/skills/william2333zz/trustshell/crossval-harness.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 693 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 $0.00075 $0.00693
Opus 5 $0.00037 $0.00347
Sonnet 5 $0.00015 $0.00139
Haiku 4.5 $0.00007 $0.00069

Measured 5d ago against content hash 754cfed5edb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

crossval-harness 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.

skills/crossval-harness/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cross-validation harness · static + dynamic

What this is

The orchestration skill. It runs the two halves and correlates them so you get proven findings and root cause — not a wall of static maybes, and not a break with no explanation.

Authorization & safety — read first

Follow every rule in ../README.md. Authorized target, disposable environment, no real credentials, harmless markers, no destruction, responsible disclosure. Otherwise stop.

Procedure

  1. Static triage — where to look. Read the agent's source and flag candidate paths: untrusted content reaching a dangerous sink, a signature-only guard, a missing check, an un-sandboxed exec. Map each candidate to a class (RT-1…RT-9). Tooling: python3 scanner/static_scan.py --source /path/to/agent. A candidate is not a finding.
  2. Dynamic confirmation — what's real. For each candidate, run the matching skill (rt1-prompt-injection, rt6-memory-poisoning, rt3-sandbox-escape, rt4-action-gating) against the running agent. A finding is confirmed only when the exploit actually works.
  3. Correlate.
    • Confirmed: trace the working exploit back to the exact code path → root cause, blast radius, and where to fix.
    • Refuted: a static candidate the dynamic pass couldn't exploit — kill it out loud. A false positive dies to a real attack, not a model vote.
  4. Grade & report. Each finding carries both the code path and a working exploit, with reproduction. Be fair: note the defenses that held. Disclose to help defenders — the finding and fix, not a weaponized payload.

Why both

A pure code verifier can only guess whether a flaw is real, so it leans on model voting to suppress false positives. A pure red-team knows something broke but not why. Cross-validation gives you the precise, proven root cause — and an empirical arbiter a verifier can't provide.

Output shape (suggested JSON)

{
  "target": "<agent + version>",
  "environment": "disposable-sandbox",
  "confirmed": [{ "class": "RT-6", "path": "file:line", "repro": "...", "severity": "crit" }],
  "refuted":   [{ "class": "RT-3", "candidate": "file:line", "why_not": "fails closed" }],
  "defenses_that_held": ["..."],
  "disclosure": "private-to-vendor"
}

Read the full file on GitHub · 51 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 · 51 lines · 75 tokens per session scan A 754cfed5edb6

Subscribe to this mod's changes

crossval-harness is a skill published in the GitHub repository William2333ZZ/trustshell (1 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 693 once invoked, about $0.0004 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 2026-08-31.