cipher-sizing SKILL.md skillA
cipher-sizing 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/cipher-sizing@git:20260908.e9ac98dPins git:20260908.e9ac98d in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- anonymousnomad/aide-sovereign-workbench
- Path
skills/packs/cipher-sizing/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260908.e9ac98d, committed Sep 8, 2026
- Size
- 5,453 bytes
- Repository stars
- 53
- License
- Apache-2.0
Architecture sizing for FSI Felon Cipher cloud training. Use when deciding model size, layer count, expert count, and training hyperparameters for a given GPU time budget. Phase 0 of cipher-cloud-training.
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
# Phase 0: Architecture Sizing ## Purpose Determine the optimal Cipher model configuration for a 7-8 hour cloud GPU training run. ## Sizing Methodology ### Step 1: Determine Token Budget ``` tokens_available = gpu_hours × 3600 × estimated_tok_per_sec × moe_derate_factor A100 80GB: 8 × 3600 × 2000 × 0.75 = ~43M tokens H100 80GB: 8 × 3600 × 5000 × 0.75 = ~108M tokens ``` ### Step 2: Chinchilla-Optimal Dense Size ``` N_optimal_dense = tokens_available / 20 A100: 43M / 20 = ~2.1M params (too small) H100: 108M / 20 = ~5.4M params (still small) ``` ### Step 3: MoE Translation MoE lets us store MORE params than Chinchilla suggests because: - Only active params drive per-token compute - Total stored params = capacity for knowledge - Activation rate ra = N_active / N_total ``` N_active_target = tokens_available / (6 × 20) # 6 = forward+backward FLOPs/param N_total = N_active / ra # ra = 0.10 to 0.30 A100: N_active = 43M / 120 = ~0.36M → N_total at ra=0.20 = ~1.8M (still small) H100: N_active = 108M / 120 = ~0.9M → N_total at ra=0.20 = ~4.5M ``` ### Step 4: Practical Floor …
Read the whole file at its exact version.
How to install
mdr add anonymousnomad/aide-sovereign-workbench/cipher-sizing@sha256:c6549541c5546f6aThe 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_jnahxfh7pg37ojf4)
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
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5453 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
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_jnahxfh7pg37ojf4 GET https://markdownregistry.com/api/v1/resolve?ref=anonymousnomad/aide-sovereign-workbench/cipher-sizing GET https://markdownregistry.com/api/v1/blob/c6549541c5546f6a07d201af8d6f65dd1bb24b07da7f1116b84c5390a85d2f87
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.