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 skills add linegel/threejs-complete-set-of-skill --skill product-from-scratchgit clone --depth 1 https://github.com/linegel/threejs-complete-set-of-skillWrote 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/skills/linegel/threejs-complete-set-of-skill/product-from-scratch)<a href="https://agentmods.dev/skills/linegel/threejs-complete-set-of-skill/product-from-scratch"><img src="https://agentmods.dev/badge/skills/linegel/threejs-complete-set-of-skill/product-from-scratch/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.
<a href="https://agentmods.dev/skills/linegel/threejs-complete-set-of-skill/product-from-scratch"><img src="https://agentmods.dev/badge/skills/linegel/threejs-complete-set-of-skill/product-from-scratch.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00079 | $0.03393 |
| Opus 5.5 | $0.00032 | $0.01357 |
| Sonnet 5.5 | $0.00016 | $0.00679 |
| Haiku 4.5 | $0.00008 | $0.00339 |
Grade A, and why
product-from-scratch 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 1mo 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product from scratch
Decide what a person will see and do before code constrains it: the user, the outcome, the journey, the interactions, the states, the failures, and the recovery. When implementation exposes a real constraint, reopen the decision that owns it instead of redesigning around the code.
Cost rules
- Design effort stays proportionate to consequence and unresolved uncertainty. For an ordinary change it costs materially less than implementing the change twice.
- Every artifact and every field must force a distinct decision or improve verification. Remove one that repeatedly does neither.
- Reuse existing canon before authoring anything. Touching the interface does not earn a new document.
When work grows without resolving a decision or reducing a plausible risk, cut process. A process defect is never fixed with another process layer: no manifests, hashes, computed statuses, approval records, evidence taxonomies, reviewer machinery, or artifact quotas. Document lint proves mechanics; it never approves a design.
The chain
BRD when business intent changes
PRD when product behaviour changes
XDS when a material experience decision exists
SDD when a material technical decision exists
then implementation, then verification
A layer is used only when its decision exists. Conditionality prevents dummy documents; it does not permit leaving a decision unresolved. A new capability or cross-surface journey normally uses every layer.
| Artifact | Use when | Owns | Must not own |
|---|---|---|---|
| BRD, business requirements | Business intent, target users, outcomes, scope, or non-negotiable qualities change | Why the work deserves to exist, user and business outcomes, acceptable effort, qualities that may not be traded away | Controls, layout, copy, colour |
| PRD, product requirements | A new capability or a material behaviour change needs a durable rule | Product stories, rules, data, permissions, required outcomes and invariants under success, failure, interruption, recovery, and return, observable acceptance | Control choice, choreography, layout, copy, hierarchy, motion, technical realization |
| XDS, experience design (a short UX note in the PR counts) | A new or materially changed journey, seam, hierarchy, state model, shared control, or interaction choice needs design | Journey, states and transitions, controls and events, copy, feedback ownership, preservation, retry, return, responsive composition, motion, alternatives | New business or product requirements, technical realization |
| SDD, solution design | Architecture, data, security, deployment, performance, or cross-module behaviour needs a durable technical decision | Schemas, APIs, persistence, performance, security, technical failure handling | Redesigning the experience |
What ships with it
2 files 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.
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.
- 1mo ago Changed · -79 lines · -97 tokens per session c12042a80cd8
- 2mo ago First seen · 339 lines · 176 tokens per session scan A d2162a895d00
product-from-scratch is a skill published in the GitHub repository linegel/threejs-complete-set-of-skill (11 stars, last pushed 1mo ago), licensed ISC. It adds 79 tokens to every session and 3,393 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
duckduckgo-search
Free keyless web, news, and image search via ddgs.
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
safe-refactor
Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
create-tech-design
Only use when the user explicitly invokes this skill by name.