cipher-eval SKILL.md skillA
cipher-eval 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-eval@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-eval/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260908.e9ac98d, committed Sep 8, 2026
- Size
- 7,121 bytes
- Repository stars
- 53
- License
- Apache-2.0
Evaluate the trained FSI Felon Cipher model. Use when running the eval battery, checking model quality, or integrating into local serving. Phase 6 of cipher-cloud-training. Final phase.
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 6: Evaluation & Integration
## Purpose
Verify the trained model is actually good. Perplexity, generation quality, routing health, and export to GGUF for local serving.
## Step 1: Perplexity Eval
```python
import torch
from tokenizers import Tokenizer
def eval_perplexity(model, data_path, tokenizer_path, seq_len=2048):
tok = Tokenizer.from_file(tokenizer_path)
data = torch.load(data_path)["sequences"]
model.eval()
total_loss = 0
count = 0
with torch.no_grad():
for i in range(0, min(len(data), 100)): # sample 100 sequences
x = data[i:i+1].cuda()
loss = model(x, labels=x).loss
total_loss += loss.item()
count += 1
avg_loss = total_loss / count
ppl = 2 ** avg_loss # base-2 perplexity
print(f"Perplexity: {ppl:.2f} (loss: {avg_loss:.4f})")
return ppl
```
## Step 2: Generation Quality
```python
def eval_generation(model, tokenizer_path, prompts):
"""Test on representative prompts across all domains."""
tok = Tokenizer.from_file(tokenizer_path)
model.eval()
results = {}
for category, prompt in prompts.items():
enc = tok.encode(prompt)
…Read the whole file at its exact version.
How to install
mdr add anonymousnomad/aide-sovereign-workbench/cipher-eval@sha256:4363a8ea5a0a2677The 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_nnwtyx43slatpgkr)
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 (7121 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_nnwtyx43slatpgkr GET https://markdownregistry.com/api/v1/resolve?ref=anonymousnomad/aide-sovereign-workbench/cipher-eval GET https://markdownregistry.com/api/v1/blob/4363a8ea5a0a26777fdf8254760aed8624a34614a8c9320fb47d4f82ebb82d10
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.