bio-genome-engineering-base-editing-design

bio-genome-engineering-base-editing-design is a skill for Claude Code, Codex from thesecondfox/skill. It costs 61 tokens per session (2,360 once invoked), scanned A, original, MIT.

A guide to designing base-editing guides for changing one DNA letter into another without cutting both DNA strands. It covers cytosine editors for C-to-T changes and adenine editors for A-to-G changes, including possible nearby unintended edits.

In plain words
What is it for?
Use it to design guides for precise nucleotide changes, optimize target positions, predict bystander edits, and evaluate base-editing experiments.
Why use it?
It helps place the desired DNA change inside the editor’s active window and compare likely editing outcomes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to design guides for precise nucleotide changes, optimize target positions, predict bystander edits, and evaluate base-editing experiments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/thesecondfox/skill/bio-genome-engineering-base-editing-design
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add thesecondfox/skill --skill bio-genome-engineering-base-editing-design
Clone the repo
git clone --depth 1 https://github.com/thesecondfox/skill

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for bio-genome-engineering-base-editing-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/thesecondfox/skill/bio-genome-engineering-base-editing-design.svg)](https://agentmods.dev/skills/thesecondfox/skill/bio-genome-engineering-base-editing-design)
Your own site
<a href="https://agentmods.dev/skills/thesecondfox/skill/bio-genome-engineering-base-editing-design"><img src="https://agentmods.dev/badge/skills/thesecondfox/skill/bio-genome-engineering-base-editing-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,360 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.02360
Opus 5 $0.00030 $0.01180
Sonnet 5 $0.00012 $0.00472
Haiku 4.5 $0.00006 $0.00236

Measured 4d ago against content hash 71fd5739070e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

bio-genome-engineering-base-editing-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Common_Skills/bio-genome-engineering-base-editing-design/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Version Compatibility

Reference examples tested with: BioPython 1.83+

Before using code patterns, verify installed versions match. If versions differ:

  • Python: pip show <package> then help(module.function) to check signatures

If code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying.

Base Editing Design

"Design a base editor guide for my C-to-T conversion" → Identify guide sequences that position the target nucleotide within the editing window of cytosine (CBE) or adenine (ABE) base editors, predicting editing outcomes and bystander effects.

  • Python: editing window analysis with Bio.Seq, BE-Hive outcome prediction

Base Editor Types

Cytosine Base Editors (CBE):
- Convert C to T (or G to A on opposite strand)
- Examples: BE3, BE4, BE4max, AncBE4max
- Editing window: Positions 4-8 (PAM-distal numbering)

Adenine Base Editors (ABE):
- Convert A to G (or T to C on opposite strand)
- Examples: ABE7.10, ABE8e, ABE8.20
- Editing window: Positions 4-7 (narrower than CBE)

Position numbering:
Position 1 = PAM-proximal (next to NGG)
Position 20 = PAM-distal (5' end of spacer)
Editing window is typically positions 4-8 from PAM-distal end

Find Editable Positions

Goal: Identify guide sequences that place a target nucleotide within the base editor's editing window while minimizing bystander edits.

Approach: Scan for PAM sites in both orientations, calculate where the target base falls within the spacer, filter guides where the target lands in the CBE (positions 4-8) or ABE (positions 4-7) editing window, and rank by fewest bystander bases in the window.

from Bio.Seq import Seq
import re

# Editing window positions (1-indexed from PAM-distal end)
# Position 1 is first nt of spacer, position 20 is adjacent to PAM
CBE_WINDOW = (4, 8)   # BE4max optimal window
ABE_WINDOW = (4, 7)   # ABE8e optimal window

def find_cbe_targets(sequence, target_c_position):
    '''Find guides that place a C in the CBE editing window

    Args:
        sequence: DNA sequence containing the target C
        target_c_position: 0-indexed position of C to edit

    Returns:
        List of guide options with editing predictions
    '''
    sequence = sequence.upper()
    guides = []

    # Search for PAMs that would place target C in window
    for pam_match in re.finditer(r'(?=(.GG))', sequence):
        pam_pos = pam_match.start()

        # Calculate where target C falls in the spacer
        spacer_start = pam_pos - 20
        if spacer_start < 0:
            continue

        c_position_in_spacer = target_c_position - spacer_start + 1  # 1-indexed

        # Check if C is in editing window
        if CBE_WINDOW[0] <= c_position_in_spacer <= CBE_WINDOW[1]:
            spacer = sequence[spacer_start:pam_pos]

            # Find bystander Cs in window (may also be edited)
            bystanders = []
            for i in range(CBE_WINDOW[0] - 1, CBE_WINDOW[1]):
                if i < len(spacer) and spacer[i] == 'C' and (spacer_start + i) != target_c_position:
                    bystanders.append(i + 1)

            guides.append({
                'spacer': spacer,
                'pam_position': pam_pos,
                'target_position_in_spacer': c_position_in_spacer,
                'bystander_cs': bystanders,
                'bystander_count': len(bystanders),
                'strand': '+'
            })

    # Sort by fewest bystanders
    return sorted(guides, key=lambda x: x['bystander_count'])


def find_abe_targets(sequence, target_a_position):
    '''Find guides that place an A in the ABE editing window'''
    sequence = sequence.upper()
    guides = []

    for pam_match in re.finditer(r'(?=(.GG))', sequence):
        pam_pos = pam_match.start()
        spacer_start = pam_pos - 20
        if spacer_start < 0:
            continue

        a_position_in_spacer = target_a_position - spacer_start + 1

        if ABE_WINDOW[0] <= a_position_in_spacer <= ABE_WINDOW[1]:
            spacer = sequence[spacer_start:pam_pos]

            bystanders = []
            for i in range(ABE_WINDOW[0] - 1, ABE_WINDOW[1]):
                if i < len(spacer) and spacer[i] == 'A' and (spacer_start + i) != target_a_position:
                    bystanders.append(i + 1)

            guides.append({
                'spacer': spacer,
                'pam_position': pam_pos,
                'target_position_in_spacer': a_position_in_spacer,
                'bystander_as': bystanders,
                'bystander_count': len(bystanders),
                'strand': '+'
            })

    return sorted(guides, key=lambda x: x['bystander_count'])

Read the full file on GitHub · 278 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 278 lines · 61 tokens per session scan A 71fd5739070e

Subscribe to this mod's changes

bio-genome-engineering-base-editing-design is a skill published in the GitHub repository thesecondfox/skill (3 stars, last pushed 5mo ago), licensed MIT. It adds 61 tokens to every session and 2,360 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

exploratory-data-analysis

Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…

K-Dense-AI/scientific-agent-skills · 83 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

phylogenetics

Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.

K-Dense-AI/scientific-agent-skills · 68 tokens

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens