Borrowing it
Nothing to install: this file belongs to textura-agency/ai-design-vault. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/textura-agency/ai-design-vault/main/.claude/skills/stack-adapt/SKILL.mdgit clone --depth 1 https://github.com/textura-agency/ai-design-vaultWrote 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/textura-agency/ai-design-vault/stack-adapt)<a href="https://agentmods.dev/skills/textura-agency/ai-design-vault/stack-adapt"><img src="https://agentmods.dev/badge/skills/textura-agency/ai-design-vault/stack-adapt/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/textura-agency/ai-design-vault/stack-adapt"><img src="https://agentmods.dev/badge/skills/textura-agency/ai-design-vault/stack-adapt.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 | $0.00114 | $0.01753 |
| Opus 5.5 | $0.00046 | $0.00701 |
| Sonnet 5.5 | $0.00023 | $0.00351 |
| Haiku 4.5 | $0.00011 | $0.00175 |
Grade A, and why
stack-adapt 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 23d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adapt the kit to this project
The kit ships framework-neutral. This procedure fits it to the host project once, so every rule, skill and check afterwards points at real paths and real packages.
Detect from evidence, not from vibes. A package.json dependency, a config
file, a directory that exists — those are evidence. "It's probably Next" is not.
1. Gather evidence
.claude/scripts/detect-stack.sh
Read its output fully. Then open what it flagged: the manifest, the framework
config file, the top-level source tree. If the framework is one you have not
seen in this exact version, read the installed docs rather than recalling an
API (node_modules/<framework>/**, the framework's own docs site). Frameworks
rename things between majors — that is exactly what this kit warns about.
references/frameworks.md in this skill folder holds the mapping for the common
stacks: paths, bindings, capabilities and the trap each one carries. Use it as a
starting point, then confirm each value against the real repo — a project is
allowed to lay itself out however it likes, and the repo wins over the table.
2. Resolve every field
Work through .claude/stack.schema.json field by field. Rules:
- Paths must exist, or be deliberately created. Never record a path that is
not there. The one exception is
paths.views— most frameworks have no such concept, and the route→view convention is one of the kit's load-bearing rules (seeobsidian/frontend/routing-views.md). Create the directory, and say so. paths.protectedstarts empty unless the project actually carries a vendored motion engine or generated code that must not be hand-edited.paths.routeEntryGlobmatters where any file is a route. Astro (["*.astro"]) and Nuxt (["*.vue"]) name pages freely; leave it empty where the framework has a fixed entry filename. Get this wrong and the route→view check silently inspects nothing.- Bindings come from what is installed. Read
package.json— do not assume the house default is present. A binding that does not exist yet isnull. envPublicPrefixis not cosmetic. It is whatverify.shuses to tell a leaked secret from a public value. Get it right per framework (ViteVITE_, SvelteKit/AstroPUBLIC_, NextNEXT_PUBLIC_, NuxtNUXT_PUBLIC_).- Commands are verbatim, with the package manager —
pnpm build, notbuild. Take them fromscriptsin the manifest; if a script is missing, recordnullrather than inventing one. - Capabilities decide which checks run.
serverComponents: falseon a SPA is correct and makes the server-first check skip instead of failing noise. notes[]is for what the fields cannot say — a non-standard layout, a deliberate deviation, a quirk you hit while detecting. Later agents read it.
What ships with it
1 file 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.
- 23d ago First seen · 148 lines · 114 tokens per session scan A 12f75c56ce6d
stack-adapt is a skill published in the GitHub repository textura-agency/ai-design-vault (25 stars, last pushed 2mo ago), licensed Unlicense. It adds 114 tokens to every session and 1,753 once invoked, about $0.0005 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 2026-10-14.
stack-adapt compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| stack-adapttextura-agency/ai-design-vault | Skill | 25 | 2mo ago | Unlicense | A | 114 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |