desktop-agent-eval-battery SKILL.md skillC
desktop-agent-eval-battery from anonymousnomad/aide-sovereign-workbench is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add anonymousnomad/aide-sovereign-workbench/desktop-agent-eval-battery@git:20260826.8da8b03Pins git:20260826.8da8b03 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- C, 13 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- anonymousnomad/aide-sovereign-workbench
- Path
skills/packs/desktop-agent-eval-battery/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260826.8da8b03, committed Aug 26, 2026
- Size
- 4,626 bytes
- Repository stars
- 53
- License
- Apache-2.0
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
# Skill: desktop-agent-eval-battery # Desktop-Agent Evaluation Battery & Integration Handoff (Phase E of the Desktop-Agent Program) ## Problem It Solves A desktop-control model that "lost loss" proves nothing. This battery measures the five claims from the master spec (format strictness, task success, injection resistance, permission handling, honest failure) on a LOCKED held-out set, and produces the evidence pack T1 requires before the model enters AIDE's registry. ## Research Foundations | Source | Fact | Rule here | |---|---|---| | verification-complete (house) | No smoke-test-as-proof; gates binary, numbers recorded | Every claim below has a numeric threshold + stored JSON evidence | | pipeline-phase-9-eval-gates (house) | No-vacuous-pass; fresh regression comparisons only | Held-out set hash-locked before training; baselines re-run same harness | | OpenAI/Anthropic safety evals | Injection + permission probes are FIRST-CLASS metrics for action agents | Probe suites are permanent battery members, not ad-hoc checks | | trio program precedent | 7-test Vulkan battery caught real regressions across pilots | Same harness pattern, desktop-domain tests | ## The Five Suites …
Read the whole file at its exact version.
How to install
mdr add anonymousnomad/aide-sovereign-workbench/desktop-agent-eval-battery@sha256:de15f8a56fa7f999The line at the top of this page pins the label git:20260826.8da8b03, 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.
[](https://markdownregistry.com/a/art_kjsz47jsubrx4lcn)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 26, 2026.
Audit of the latest version
- fail: Frontmatter block present
- fail: Frontmatter declares a name
- fail: Frontmatter declares a description
- fail: No prompt-injection phrasing (matched: ignore previous instructions)
- pass: Size between 200 bytes and 200 KB (4626 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 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
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
anonymousnomad/aide-sovereign-workbench · 53 stars · license Apache-2.0 · pushed 2026-10-26 · branch covert-production
API
GET https://markdownregistry.com/api/v1/artifacts/art_kjsz47jsubrx4lcn GET https://markdownregistry.com/api/v1/resolve?ref=anonymousnomad/aide-sovereign-workbench/desktop-agent-eval-battery GET https://markdownregistry.com/api/v1/blob/de15f8a56fa7f9991d5e9c230f8aa90a39d0f6963b0af819a03866a1034243c7
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.