audit-verifier-reliability SKILL.md skillA

audit-verifier-reliability from understudylabs/orchestra-agent-tools is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add understudylabs/orchestra-agent-tools/audit-verifier-reliability@git:20261020.17ad730

Pins git:20261020.17ad730 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
understudylabs/orchestra-agent-tools
Path
skills/audit-verifier-reliability/SKILL.md
Versions recorded
2
Latest version
git:20261020.17ad730, committed Oct 20, 2026
First version recorded
Aug 3, 2026
Size
1,586 bytes
Repository stars
19
License
MIT

Use when deciding whether a verifier reward is trustworthy for optimization.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file 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
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add understudylabs/orchestra-agent-tools/audit-verifier-reliability@sha256:a2d0bedfd9b362fa

The line at the top of this page pins the label git:20261020.17ad730, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_y5sh5min4i2oyv2y.svg)](https://markdownregistry.com/a/art_y5sh5min4i2oyv2y)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Aug 3, 2026 and Oct 20, 2026, about one every 77 days.

versioncommittedcommitsizeaudit
git:20261020.17ad730 latest2026-10-20 17ad730 1,586 BA view · diff
git:20260803.1d981332026-08-03 1d98133 1,492 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1586 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

understudylabs/orchestra-agent-tools · 19 stars · license MIT · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_y5sh5min4i2oyv2y
GET https://markdownregistry.com/api/v1/resolve?ref=understudylabs/orchestra-agent-tools/audit-verifier-reliability
GET https://markdownregistry.com/api/v1/blob/a2d0bedfd9b362fa2ea66831cf9cc88f8175050252d6d7fd3491712730e9f088

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from understudylabs/orchestra-agent-tools

AGENTS.md AGENTS.md file
understudylabs/orchestra-agent-tools · AGENTS.md
git:20261028.6ac516b · audit A · 19 stars
CLAUDE.md CLAUDE.md file
understudylabs/orchestra-agent-tools · CLAUDE.md
git:20261028.6771875 · audit A · 19 stars
AGENTS.md@apps/moraine-viewer AGENTS.md file
understudylabs/orchestra-agent-tools · apps/moraine-viewer/AGENTS.md
git:20260720.0c3a327 · audit A · 19 stars
CLAUDE.md@apps/moraine-viewer CLAUDE.md file
understudylabs/orchestra-agent-tools · apps/moraine-viewer/CLAUDE.md
git:20260720.0c3a327 · audit B · 19 stars
calibrate-difficulty SKILL.md skill
understudylabs/orchestra-agent-tools · skills/calibrate-difficulty/SKILL.md · Measure per-band model headroom from a local, source-bound run artifact before investing in training.
git:20261020.17ad730 · audit A · 19 stars
capture-evidence SKILL.md skill
understudylabs/orchestra-agent-tools · skills/capture-evidence/SKILL.md · Use when a developer wants to build an eval from their real LLM app before changing anything — "measure how my app is…
git:20261027.533318e · audit A · 19 stars
check-routing-health SKILL.md skill
understudylabs/orchestra-agent-tools · skills/check-routing-health/SKILL.md · Use when a developer asks "is Orchestra causing my errors", "which workloads are routed", "is my routing config…
git:20261027.533318e · audit A · 19 stars
compare-model-sweep SKILL.md skill
understudylabs/orchestra-agent-tools · skills/compare-model-sweep/SKILL.md · Use when a developer wants to compare candidate models — any mix of local, gateway, or frontier — on the same eval and…
git:20261027.533318e · audit A · 19 stars
compare-trajectories SKILL.md skill
understudylabs/orchestra-agent-tools · skills/compare-trajectories/SKILL.md · Use when you need to know HOW two model runs differ behaviorally on the same tasks, not just THAT one scores higher —…
git:20260719.1185398 · audit A · 19 stars
curate-trajectories SKILL.md skill
understudylabs/orchestra-agent-tools · skills/curate-trajectories/SKILL.md · Use to turn loose per-task trajectory JSONs (a Lilac export or local rollout corpus) into a queryable…
git:20260609.050d8ac · audit A · 19 stars
design-simulated-environment SKILL.md skill
understudylabs/orchestra-agent-tools · skills/design-simulated-environment/SKILL.md · Use to build a simulated, seeded environment (AutomationBench / verifiers style) so any model can run a captured…
git:20261027.533318e · audit A · 19 stars
deslop SKILL.md skill
understudylabs/orchestra-agent-tools · skills/deslop/SKILL.md · Use when a user asks to "deslop", "de-AI", "make it sound human", remove AI patterns or tropes, clean up AI writing…
git:20260812.510c636 · audit A · 19 stars

Every file in understudylabs/orchestra-agent-tools

Browse by kind, by grade A, or by owner.