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.
npx agentmods add instructions/utensils/mold/claude-mdgit clone --depth 1 https://github.com/utensils/moldWrote 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.
[](https://agentmods.dev/instructions/utensils/mold/claude-md)<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>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.
| Model | Per session | Once 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 |
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.
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"
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.
- today Changed · +61 lines · +4,146 tokens per session cdfe834fcf59
- 4d ago First seen · 137 lines · 4,003 tokens per session scan A 176bc7f5044c
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.
Other instructions, from other repositories
AI-fundamentals CLAUDE.md
Claude Code instructions for ForceInjection/AI-fundamentals, covering claude.md, repository overview, commit conventions, file conventions and content creation workflow.
flashinfer AGENTS.md
AGENTS.md instructions for flashinfer-ai/flashinfer: This repository’s agent instructions live in CLAUDE.md.
AI-fundamentals AGENTS.md
AGENTS.md instructions for ForceInjection/AI-fundamentals, covering 项目概览与工具使用说明 and 1 核心技术模块.
VoiceStudio CLAUDE.md
Claude Code instructions for debpalash/VoiceStudio, covering project, constraints, technology stack, conventions and architecture.
TensorRT-LLM AGENTS.md
AGENTS.md instructions for NVIDIA/TensorRT-LLM, covering agents.md, rules (read first), common commands, installation & build and reference configs.
TensorRT-LLM CLAUDE.md
Claude Code instructions for NVIDIA/TensorRT-LLM, a project described as: TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python…