aid-capability-battery-thinking-models SKILL.md skillC
aid-capability-battery-thinking-models 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/aid-capability-battery-thinking-models@git:20260908.e9ac98dPins git:20260908.e9ac98d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- C, 14 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- anonymousnomad/aide-sovereign-workbench
- Path
skills/packs/aid-capability-battery-thinking-models/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260908.e9ac98d, committed Sep 8, 2026
- Size
- 5,924 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
# Capability Battery Adaptation: MoE Models with Interleaved Thinking ## Scope Adapting the AIDE capability audit (originally for Qwen2.5-Coder-4B Instruct at 0.683 composite) for new in-house models. Critical for the North-Mini-Code-1.0 path because the model has **interleaved thinking** which completely changes the response shape. ## Why the original battery breaks on North The original battery (per `docs/evidence/capability-audit-cipher-4b.md`) checks for `must` substrings in the response text. For North-Mini-Code-1.0: - Every response includes `reasoning_content` BEFORE `content` (or AS the entire response on short prompts) - The `content` field can be empty for `finish_reason="length"` truncations (the 33-token "OK" probe had empty `content` because all 16 tokens went to reasoning) - The original battery's "D_tool 0% pass" was caused by an audit format mismatch (model uses AIDE's native grammar, not `ACTION:` prefix). The same problem will hit North unless we test the actual JSON the daemon expects. ## Battery adaptation rules | Battery check | Old (cipher-4b) | New (North + any thinking model) | |---|---|---| …
Read the whole file at its exact version.
How to install
mdr add anonymousnomad/aide-sovereign-workbench/aid-capability-battery-thinking-models@sha256:5303ce110682f392The line at the top of this page pins the label git:20260908.e9ac98d, 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_qdez7b2lkaeglibj)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 8, 2026.
Audit of the latest version
- fail: Frontmatter block present
- fail: Frontmatter declares a name
- fail: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5924 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
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_qdez7b2lkaeglibj GET https://markdownregistry.com/api/v1/resolve?ref=anonymousnomad/aide-sovereign-workbench/aid-capability-battery-thinking-models GET https://markdownregistry.com/api/v1/blob/5303ce110682f392f14f1ad927e7dae30967a98619ff7fdda101b8765611cc5f
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.