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/devanshutak25/3d-resources/claude-mdgit clone --depth 1 https://github.com/devanshutak25/3d-resourcesWrote 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/devanshutak25/3d-resources/claude-md)<a href="https://agentmods.dev/instructions/devanshutak25/3d-resources/claude-md"><img src="https://agentmods.dev/badge/instructions/devanshutak25/3d-resources/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 | $0.01067 | $0.01067 |
| Opus 5 | $0.00534 | $0.00534 |
| Sonnet 5 | $0.00213 | $0.00213 |
| Haiku 4.5 | $0.00107 | $0.00107 |
Grade A, and why
3d-resources 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
3d_resources — project rules
project.md (MANDATORY)
Read project.md at the start of every session. It is the master guide: filesystem map, data model, build pipeline, rules, pending tasks, design style. Treat it as authoritative when any other doc disagrees.
Update project.md after every change. If filesystem layout, rules, goals, vocab, build steps, design conventions, or pending tasks shift, edit project.md in the same change. Stale project.md is a bug.
Controlled vocabulary (entry tags)
Source of truth: schema/vocab.yml + schema/entry.schema.json.
Rule: When adding/editing entries, only use values that already exist in the vocab for these tag groups:
license(closed enum)entry_type(closed enum)tags.workflow(closed enum)tags.output(closed enum)tags.platform(closed enum)tags.skill(closed enum)
tags.tech is freeform but curated — prefer existing values; new ones produce warnings, not errors.
Never invent new values for closed enums. If an entry seems to need one (e.g. product-design, print, visionos, tracking, rotoscoping), do NOT add it silently to vocab.yml or entry.schema.json. Instead:
- Map to the closest existing value (e.g.
product-design→product-viz,tracking/rotoscoping→compositing), OR drop the tag if no good fit. - Ask the user if a genuinely new category is needed before extending the vocab.
CI runs node scripts/validate.js — closed-enum violations exit 1 and block merge.
Validation
Run node scripts/validate.js after any data edit. Must show ✓ Validation passed. before commit.
Writing style (user-facing text)
Applies to: data/**/*.yml (descriptions, titles, readme_tags), template strings in scripts/render.js, scripts/build-html.js, scripts/build-section-pages.js, scripts/build-feed.js, scripts/build-llms-txt.js, scripts/build-og-images.js, and any other surface a site visitor reads.
Rules:
- No em-dashes (
—). Ever. In titles, use:. In prose, use.(period + capitalize next word) or,depending on context. The OG-image splitter (build-og-images.js) keys on:for two-line layout — don't reintroduce em-dashes. - No AI tells. Banned words/phrases:
comprehensive,robust,powerful,seamless(ly),leverage(s/d)(use "use"),utilize(s/d/ing)(use "use"),cutting-edge,state-of-the-art,the ultimate,game-changing,unleash. Banned trailing phrases:and more,and beyond,and so much more. - No marketing adjective stacks ("fast, free, and powerful"). One concrete attribute beats three vague ones.
- Caveman lite for descriptions. Terse, factual, 1 sentence preferred. State what it is and what it does. Drop hype.
- Internal docs/memory/CLAUDE.md/comments are exempt. Em-dashes and informal hedging are fine there.
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.
- 5d ago First seen · 72 lines · 1,067 tokens per session scan A 7fbcd919b73e
3d-resources CLAUDE.md is an instructions file published in the GitHub repository devanshutak25/3d-resources (932 stars, last pushed 2d ago), licensed CC0-1.0. It adds 1,067 tokens to every session, about $0.0053 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
awesome-python AGENTS.md
AGENTS.md instructions for vinta/awesome-python, covering agents.md and entry rules.
awesome-ai-gateway CLAUDE.md
Claude Code instructions for cuihuan/awesome-ai-gateway, covering claude.md — working rules for this repository, what this repository is, the two goals — judge every change against these, non-negotiable rules and before you commit.
Paperlab AGENTS.md
AGENTS.md instructions for NourMtir0722/Paperlab, covering paperlab — for coding agents, integrating paperlab into a project, stage mode — paper as architecture, content types and lighting is data, not an enum.
Unity-AI-Animation CLAUDE.md
Instructions for IvanMurzak/Unity-AI-Animation, covering claude.md, what this is, build / run, critical invariants and find detail in.
awesome-defold AGENTS.md
Instructions for astrochili/awesome-defold: When asked to process the resource inbox, use GitHub issue #16 unless another issue is named.
awesome-ai-scientists CLAUDE.md
Instructions for natnew/awesome-ai-scientists, covering claude.md, north star, resolver — load per task, first-pass workflow and stop conditions.