SpliceCraft: Instructions file for Claude Code

CLAUDE.md

SpliceCraft CLAUDE.md is an instructions file for Claude Code from Binomica-Labs/SpliceCraft. It costs 9,016 tokens per session, scanned A, original, MIT.

A set of instructions for coding agents working on SpliceCraft, an application that stores plasmid, DNA-part, primer, and collection data. It explains how to protect that data and run the project safely.

In plain words
What is it for?
Use it before changing SpliceCraft code, especially when importing the application, saving records, syncing between laptops, or running it locally.
Why use it?
It helps prevent accidental writes to the user's real data directory, including damage caused by ad-hoc scripts or unsafe tests.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is Binomica-Labs/SpliceCraft's own configuration. It tells Claude Code how to work on SpliceCraft itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything SpliceCraft configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Binomica-Labs/SpliceCraft. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Binomica-Labs/SpliceCraft/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Binomica-Labs/SpliceCraft

Made for: Claude Code.

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 SpliceCraft CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/binomica-labs/splicecraft/claude-md/github.svg)](https://agentmods.dev/instructions/binomica-labs/splicecraft/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/binomica-labs/splicecraft/claude-md"><img src="https://agentmods.dev/badge/instructions/binomica-labs/splicecraft/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for SpliceCraft CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/binomica-labs/splicecraft/claude-md"><img src="https://agentmods.dev/badge/instructions/binomica-labs/splicecraft/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9,016 This file is loaded in full into every session.
When invoked 9,016 The same file — it is already loaded in full.
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 $0.09016 $0.09016
Opus 5 $0.04508 $0.04508
Sonnet 5 $0.01803 $0.01803
Haiku 4.5 $0.00902 $0.00902

Measured 3d ago against content hash 3f21afce67c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

SpliceCraft CLAUDE.md 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 3d 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.

CLAUDE.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — AI Agent Context for SpliceCraft

Agent handoff. Read before touching the codebase.

⚠ SACRED: data-dir safety (READ FIRST)

The user's plasmid library + collections + primers + parts live in ~/.local/share/splicecraft/ (or $XDG_DATA_HOME/splicecraft/). The data is the product. A wrong write here destroys hours-to-years of user work. Three hard rules:

  1. Never import splicecraft from an ad-hoc script (/tmp/*.py, REPL, probe) without first sandboxing XDG_DATA_HOME. _DATA_DIR is computed at import time and won't budge afterwards. Sandbox by:
    import os, tempfile; os.environ["XDG_DATA_HOME"] = tempfile.mkdtemp(prefix="sc-")
    os.environ.setdefault("SPLICECRAFT_SKIP_LOCK", "1")
    import splicecraft as sc
    # NB: _DATA_DIR (+ the _*_FILE paths, _DNA_ORIGINALS_DIR, …) migrated to _state
    # during the modularization — read them as `sc._state._DATA_DIR`, not `sc._DATA_DIR`.
    assert "sc-" in str(sc._state._DATA_DIR), f"unsandboxed: {sc._state._DATA_DIR}"
    sc._authorize_writes_for_sandbox(sc._state._DATA_DIR)   # L2 chokepoint opt-in
    
  2. _save_* helpers are nuclear-coded. Calling _save_collections, _save_model_collections, _save_library, _save_primers, _save_parts_bin, _save_features, _save_custom_grammars, _save_entry_vectors, _codon_tables_save, _save_protein_motifs, _save_experiments, _save_experiment_projects, _save_gels, _save_custom_enzymes, _save_enzyme_collections, or _safe_save_json directly from outside the four sanctioned callers (PlasmidApp.main(), pytest _protect_user_data fixture, agent HTTP server, sandboxed verifier harness) raises RuntimeError since the L2 chokepoint landed — sandbox first or use the GUI.
  3. Verifier scripts always go through .claude/skills/verifier-splicecraft.md. It enforces the sandbox + authorization at the top. Don't roll your own.

Caught failure (2026-05-22): an unsandboxed /tmp/sc_probe.py ran _save_collections([{"name": "Default", "plasmids": []}]) for test setup. It wrote directly to the user's real 160 MB collections.json, rotating the previous good state to .bak. The four-layer safety net + lost-entries spillover recovered the data, but the lesson stands: there is NO "I'll be careful this once" version of writing to the data dir. Sandbox or refuse.

Read the full file on GitHub · 144 lines

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. 3d ago Changed 3f21afce67c3
  2. 9d ago First seen · 144 lines · 9,016 tokens per session scan A 945442ae4ba0

Subscribe to this mod's changes

SpliceCraft CLAUDE.md is an instructions file published in the GitHub repository Binomica-Labs/SpliceCraft (241 stars, last pushed 8d ago), licensed MIT. It adds 9,016 tokens to every session, about $0.0451 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 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens