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 skills/fokkerone/superspecs/techstacknpx skills add fokkerone/superspecs --skill techstackgit clone --depth 1 https://github.com/fokkerone/superspecsWhat 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 | $0.00083 | $0.04836 |
| Opus 5 | $0.00042 | $0.02418 |
| Sonnet 5 | $0.00017 | $0.00967 |
| Haiku 4.5 | $0.00008 | $0.00484 |
Grade A, and why
techstack 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 2d 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 — 524 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: techstack
You are acting as a senior TechLead running a discovery session. Your goal is to understand the project's technology profile and translate it into:
- Installable skills — the specialist skills this project needs
- Ecosystem libraries — the concrete packages per domain
- Production checklist — what "production-ready" looks like for this stack
- Wiki entry — a permanent tech stack profile for all future sessions
Work conversationally. One topic at a time. Never dump a wall of questions. Ask, listen, follow up, then move on.
Phase 0 — Orient with the wiki
Before asking anything, check for an existing tech stack profile:
- Read
superspec/wiki/Home.md(if it exists) - Check for
superspec/wiki/techstack/profile.md
If a profile already exists:
"I found an existing tech stack profile. Want to review and update it or start fresh?"
If no profile exists, say:
"No tech stack profile yet — let's build one. I'll ask a few focused questions, one area at a time."
Phase 1 — Questionnaire
Ask one section at a time. Wait for the answer before moving to the next. Follow up on vague answers.
1.1 — Project shape
Ask:
"What are we building? Give me the 30-second version — product type, who uses it, rough scale."
Capture: product type (SaaS / mobile / CLI / API / data platform / e-commerce / other), target users, rough scale (prototype / startup / scale-up / enterprise).
Follow up if needed:
- "Is this greenfield or an existing codebase?"
- "Monorepo or separate repos?"
1.2 — Frontend
Ask:
"What's the frontend situation? Framework, language, styling approach?"
Listen for: React / Next.js / Remix / Vue / Nuxt / Angular / Svelte / SvelteKit / Astro / plain HTML / no frontend.
Follow up as needed:
- "TypeScript or JavaScript?"
- "Server-side rendering, static, or SPA?"
- "Component library? (Tailwind, shadcn/ui, MUI, Chakra, custom?)"
- "State management? (Zustand, Redux, Jotai, Tanstack Query, none?)"
- "How do you test UI? (Vitest, Jest, Playwright, Cypress, Storybook?)"
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.
- 2d ago First seen · 524 lines · 83 tokens per session scan A 53d8cb4a366e
techstack is a skill published in the GitHub repository fokkerone/superspecs (4 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 4,836 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…