audit-verifier-reliability

audit-verifier-reliability is a skill for Claude Code, Codex from understudylabs/understudy-agent-tools. It costs 19 tokens per session (305 once invoked), scanned A, original, MIT.

A procedure for checking whether a verifier—a system that scores results—is reliable enough to support optimization decisions.

In plain words
What is it for?
Running offline adversarial tests and replay tests, checking cryptographic links to the source and test fixtures, and producing a hash-bound trust receipt.
Why use it?
It prevents a score from being trusted when required tests or evidence are missing, while keeping customer data and unreleased test data out of the audit.

Skill for Claude CodeCodex

Part of the understudy plugin — 43 skills, 1 command 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/understudylabs/understudy-agent-tools/audit-verifier-reliability
Any agent
npx skills add understudylabs/understudy-agent-tools --skill audit-verifier-reliability
Clone the repo
git clone --depth 1 https://github.com/understudylabs/understudy-agent-tools

Made for: Claude Code, Codex.

Or install understudy, the plugin that ships this one along with the rest of its 43 skills, 1 command.

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 audit-verifier-reliability

README.md
[![agentmods](https://agentmods.dev/badge/skills/understudylabs/understudy-agent-tools/audit-verifier-reliability.svg)](https://agentmods.dev/skills/understudylabs/understudy-agent-tools/audit-verifier-reliability)
Your own site
<a href="https://agentmods.dev/skills/understudylabs/understudy-agent-tools/audit-verifier-reliability"><img src="https://agentmods.dev/badge/skills/understudylabs/understudy-agent-tools/audit-verifier-reliability.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 305 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 $0.00019 $0.00305
Opus 5 $0.00010 $0.00152
Sonnet 5 $0.00004 $0.00061
Haiku 4.5 $0.00002 $0.00030

Measured 4d ago against content hash 7df3d16b7395, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-verifier-reliability 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.

skills/audit-verifier-reliability/SKILL.md · 33 lines

What it actually says

Audit verifier reliability

Trust requires two independent, offline arms: deterministic adversarial probes and replayed natural trajectories. The receipt is trusted only when both meet the predeclared gate and carries source, verifier, and fixture SHA-256 bindings.

Never read holdout data, call providers, upload traces, include customer data, or spend money in this audit. Natural evidence cannot override an adversarial failure; missing natural coverage is insufficient-evidence.

Use evaluateTrustGate from src/verifier-trust/. Keep raw trajectories out of receipts and retain the resulting hash-bound receipt with the calibration artifact (understudy.verifier_calibration.v1).

Safety Gates

  • Operate only on already-approved local calibration summaries; never read a holdout, call a provider, upload trajectories, or include customer content.
  • Require valid source-binding, verifier, and fixture SHA-256 values plus both natural and adversarial arms. Missing evidence is never trusted.
  • Treat the receipt as verifier-calibration evidence, not model-quality or promotion evidence.

Resolve CLI

No CLI command is required. Build the package and call evaluateTrustGate from dist/verifier-trust/index.js in an offline script or test. Preserve only the hash-bound receipt; keep raw probes in their approved local evidence store.

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 · 33 lines · 19 tokens per session scan A 7df3d16b7395

Subscribe to this mod's changes

audit-verifier-reliability is a skill published in the GitHub repository understudylabs/understudy-agent-tools (16 stars, last pushed 4d ago), licensed MIT. It adds 19 tokens to every session and 305 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens