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 ivan-szz/spec-writer-skill --skill spec-writergit clone --depth 1 https://github.com/ivan-szz/spec-writer-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/ivan-szz/spec-writer-skill/spec-writer)<a href="https://agentmods.dev/skills/ivan-szz/spec-writer-skill/spec-writer"><img src="https://agentmods.dev/badge/skills/ivan-szz/spec-writer-skill/spec-writer/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/ivan-szz/spec-writer-skill/spec-writer"><img src="https://agentmods.dev/badge/skills/ivan-szz/spec-writer-skill/spec-writer.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 | $0.00046 | $0.02766 |
| Opus 5 | $0.00023 | $0.01383 |
| Sonnet 5 | $0.00009 | $0.00553 |
| Haiku 4.5 | $0.00005 | $0.00277 |
Grade A, and why
spec-writer 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 9d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Writer Skill
Author well-structured specification documents through an interactive dialogue. The agent is an interlocutor, not a generator — it asks, probes, challenges, and clarifies before writing anything. Every spec produced is a complete, self-contained .md file that can be reviewed, versioned, and traced to implementation.
Core Principle
Never generate a spec from a one-liner. When the user says "write a spec for X", start a dialogue. The quality of the spec is determined by the quality of the questions asked, not by the speed of generation.
Setup
Before doing anything:
- Read the project context. Check for
AGENTS.md,CLAUDE.md,*.instructions.md, or similar project instruction files. Understand the tech stack, conventions, and existing specs. - Check for existing specs. Look in
specs/for any.spec.mdfiles. If one exists for the requested feature, warn the user and ask whether to refine the existing one or create a new version. - Check for spec template. Load
specs/spec-template.mdas the structural reference. This is the single source of truth for spec structure.
Commands
| Command | Description |
|---|---|
write <feature> |
Start a dialogue to create a new spec |
refine <spec-path> |
Review and improve an existing spec |
validate [spec-path] |
Validate one or all specs against the rule set |
Routing
- No argument: show available specs in
specs/, suggest next actions. - First word matches a command: load and execute it.
- First word doesn't match, but intent maps (e.g. "spec for auth" →
write auth): route to the matching command. - Ambiguous: ask once which command the user wants.
The Dialogue Flow
When the user invokes write, follow this flow. Do not skip steps. Do not generate the spec before completing the dialogue.
Round 1 — Understand the Shape
Ask 2-3 focused questions to understand what the feature IS:
- What does it do? — One sentence. Not a paragraph. If the user gives a paragraph, help them distill it to one sentence.
- Who uses it? — End user, admin, external service, another system? Different users mean different interfaces.
- What's the primary interface? — REST endpoint? CLI command? Library function? WebSocket event? This determines the spec structure.
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.
- 9d ago First seen · 234 lines · 46 tokens per session scan A 2c4e9df97302
spec-writer is a skill published in the GitHub repository ivan-szz/spec-writer-skill (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 2,766 once invoked, about $0.0002 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…