cipher-tokenizer SKILL.md skillA
cipher-tokenizer 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-tokenizer@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-tokenizer/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260908.e9ac98d, committed Sep 8, 2026
- Size
- 3,225 bytes
- Repository stars
- 53
- License
- Apache-2.0
Complete the FSI Felon Cipher tokenizer from 500 to 32K vocabulary. Use when building, training, or verifying the cipher tokenizer. Phase 1 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 1: Tokenizer Completion
## Purpose
Complete the cipher tokenizer from 500 vocab entries to 32768. The tokenizer is the model's interface to language.
## Current State
- Location: `E:\FSI-FELON\models\fsi_felon_cipher\code_tokenizer.py`
- Current vocab: 500 (incomplete)
- Target: 32768
## Why 32K Vocab
- NeurIPS 2024: Nv ~ C^0.42 (vocab scales sublinearly with compute)
- NeurIPS 2025: common-word single-token saturation ~24K
- Practical: 32K sweet spot for code+text at 200M-1B scale
## Step 1: Train BPE Tokenizer
```python
from tokenizers import Tokenizer, models, trainers, pre_tokenizers, decoders
import glob
tokenizer = Tokenizer(models.BPE())
tokenizer.pre_tokenizer = pre_tokenizers.ByteLevel(add_prefix_space=False)
tokenizer.decoder = decoders.ByteLevel()
special_tokens = [
"<unk>", "<s>", "</s>", "<pad>", "<mask>",
"<task>", "<guidelines>", "<check>",
"<mind_spock>", "<mind_sheldon>",
"<code>", "<execute>", "<observe>", "<deliver>",
"<fim_prefix>", "<fim_suffix>", "<fim_middle>",
"<sep>", "<persona>"
]
trainer = trainers.BpeTrainer(
vocab_size=32768,
min_frequency=2,
special_tokens=special_tokens,
show_progress=True,
)
…Read the whole file at its exact version.
How to install
mdr add anonymousnomad/aide-sovereign-workbench/cipher-tokenizer@sha256:7e7b7fd9104e4e2dThe 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_6zhimofjmv52fw42)
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 (3225 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_6zhimofjmv52fw42 GET https://markdownregistry.com/api/v1/resolve?ref=anonymousnomad/aide-sovereign-workbench/cipher-tokenizer GET https://markdownregistry.com/api/v1/blob/7e7b7fd9104e4e2d01dda2649a8b761e1ec06b151090c2804cfc42ffb92f4147
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.