mold CLAUDE.md

mold CLAUDE.md is an instructions file for coding agents from utensils/mold. It costs 8,149 tokens per session, scanned A, original, MIT.

Project instructions for mold, a local command-line tool that generates images and videos with AI models on a computer or through a remote server.

In plain words
What is it for?
Use them when developing, formatting, building, or checking the mold codebase.
Why use it?
They explain the project's supported models, build commands, testing checks, and area-specific rules in one place.

Instructions file

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.

agentmods
npx agentmods add instructions/utensils/mold/claude-md
Clone the repo
git clone --depth 1 https://github.com/utensils/mold

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 mold CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/utensils/mold/claude-md.svg)](https://agentmods.dev/instructions/utensils/mold/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/utensils/mold/claude-md"><img src="https://agentmods.dev/badge/instructions/utensils/mold/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 8,149 This file is loaded in full into every session.
When invoked 8,149 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.08149 $0.08149
Opus 5 $0.04075 $0.04075
Sonnet 5 $0.01630 $0.01630
Haiku 4.5 $0.00815 $0.00815

Measured today against content hash cdfe834fcf59, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mold 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 today.

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 · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Keep lean: only things not obvious from the code, --help, or git log. Area-specific invariants live in .claude/rules/*.md (path-scoped; AGENTS.md symlinks here).

What mold is

Local AI image/video generation CLI built on candle. Supports FLUX, SD1.5, SDXL, SD3.5, Z-Image, Flux.2 Klein (distilled and base) and Dev, Qwen-Image, Wuerstchen v2, LTX-Video, LTX-2, and Wan 2.1/2.2 (T2V; the family's frame grid is 4k+1 and its sampler deliberately follows the diffusers/Lightning flow-UniPC schedule, not upstream Wan's fm_solvers_unipc.py — see crates/mold-inference/src/wan/sampler.rs; the DMD ladder tiers (wan21-t2v-1.3b:turbo, wan22-ti2v-5b:dmd) are the exception, pinned by manifest::wan_dmd_ladder and mirroring FastVideo's DmdDenoisingStage — each on the flow shift its own student was TRAINED at (8.0 and 5.0, from each FastWan*Config.flow_shift), deliberately NOT upstream's DmdDenoisingStage.__init__, which hardcodes 8.0 for every tier and would silently mis-schedule the 5B — predict x0 at each fixed rung, re-noise to the next — so the generation profile fixes steps, guidance, scheduler, and shift rather than defaulting them). Runs locally on GPU or talks to a remote mold serve over HTTP. Single binary, everything feature-gated.

Commands

# Nix (preferred)
nix build                   # Build mold (default CUDA/Metal)
nix fmt                     # treefmt (nixfmt + rustfmt), configured inline in flake.nix; no rustfmt.toml
nix flake check             # CI-equivalent gate

# Local CI runner (what to run before a PR; devshell alias: ci-local)
./scripts/ci-local.sh [rust|web|docs|contracts|gpu|nix] [-k] [--list]

# Cargo — common loops
cargo check
cargo clippy --workspace --all-targets -- -D warnings
cargo fmt --all -- --check
cargo test --workspace                       # PRs run a filtered deterministic subset; full suite only on main
cargo +1.93 check -p mold-ai --locked --features preview,discord,expand,tui,metrics,webp,mp4,mdns,pulid   # CI MSRV gate
cargo run -p mold-ai-core --bin generate_generation_profiles -- --check   # CI contract
bash scripts/tests/ci-routing-contract.sh                                 # CI contract
bash scripts/tests/candle-single-identity.sh                              # every candle crate on ONE fork rev
./scripts/coverage.sh [--html]

# Frontend (one Bun workspace at repo root; prettier scoped to studio/, desktop override in .prettierrc)
bun run check:frontend        # architecture check + tests + web/desktop builds
bun run check:architecture    # scripts/tests/frontend-architecture.sh
bun run check:dead-code       # knip
bun run fmt:check

# Local dev run (MUST prefix with ensure-web-dist so the embedded SPA isn't a stub)
./scripts/ensure-web-dist.sh && cargo run --profile dev-fast -p mold-ai \
  --features metal,preview,expand -- run "a cat"

Read the full file on GitHub · 198 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. today Changed · +61 lines · +4,146 tokens per session cdfe834fcf59
  2. 4d ago First seen · 137 lines · 4,003 tokens per session scan A 176bc7f5044c

Subscribe to this mod's changes

mold CLAUDE.md is an instructions file published in the GitHub repository utensils/mold (40 stars, last pushed today), licensed MIT. It adds 8,149 tokens to every session, about $0.0407 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.