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 Oriolshhh/runware-image-mcp --skill spec-detailedgit clone --depth 1 https://github.com/Oriolshhh/runware-image-mcpWrote 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/oriolshhh/runware-image-mcp/spec-detailed)<a href="https://agentmods.dev/skills/oriolshhh/runware-image-mcp/spec-detailed"><img src="https://agentmods.dev/badge/skills/oriolshhh/runware-image-mcp/spec-detailed/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/oriolshhh/runware-image-mcp/spec-detailed"><img src="https://agentmods.dev/badge/skills/oriolshhh/runware-image-mcp/spec-detailed.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 | $0.00018 | $0.01204 |
| Opus 5 | $0.00009 | $0.00602 |
| Sonnet 5 | $0.00004 | $0.00241 |
| Haiku 4.5 | $0.00002 | $0.00120 |
Grade A, and why
spec-detailed 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 8d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/spec-detailed — Create a detailed spec with deeper questioning
Purpose
Produce a more exhaustive, less assumption-heavy specification when the user wants the agent to ask more questions and pin down exactly what should be built.
Use this when precision matters more than speed: product flows, UX details, security-sensitive behavior, migrations, billing, permissions, API contracts, or anything where a wrong default would be expensive.
Invocation
/spec-detailed <description of the work>
Accepted input
A request, problem statement, ticket, mockup, screenshot, user story, or rough idea, with any known constraints and desired level of strictness.
Prerequisites
A HarnessKit workspace (harnesskit init). No approved spec required.
Procedure
- Read
.agent/context/README.mdand routing when present. Inspect task-relevant source, existing specs, tests, UI routes, APIs, schemas, and configuration before asking questions. Do not ask for facts available in the repository. - Apply
requirements-triageand create a discovery map with:- confirmed facts;
- unknowns;
- assumptions that would affect implementation;
- preferences that affect UX, API shape, rollout, compatibility, or tests;
- decision-changing blockers.
- Ask a structured question batch. Unlike
/spec, this command is intentionally more interrogative:- normally ask 6–12 focused questions;
- never ask more than 15 in one batch;
- group them by product behavior, UX/API/data, edge cases, rollout, and validation;
- mark each question as blocking, recommended, or optional;
- provide a proposed default for every recommended or optional question.
- Wait for the user's answers when any blocking question remains. If the user asks you to proceed with defaults, record those defaults explicitly.
- Select and announce one planning path:
direct-specfor still-small work where detail was needed mainly for clarity;specialist-assisted-specfor cross-cutting work needing one to three specialist planning reviews;full-council-specfor high-risk, irreversible, architectural, security-sensitive, or product-contested work.
- Use
specialist-routingfor any relevant planning reviews. Give specialists the same brief and context capsule. Use isolated parallel reports only where the tool supports native subagents; otherwise use clearly labelled sequential or simulated role passes. - Produce a complete spec with the normal
/specstructure plus these detailed sections:- Decision log — each answered question, chosen default, and reason;
- Alternative behaviors considered — rejected options and why;
- Acceptance examples — concrete examples or scenarios for critical requirements;
- Observability and rollout — metrics, logs, flags, migration, rollback when relevant.
- Save it to
.agent/specs/<kebab-case-name>.mdusing the standard spec frontmatter contract below. - Present a concise plain-language decision summary using
/sum-spec's output contract. Stop and request approval explicitly. Do not start implementation workers.
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.
- 8d ago First seen · 126 lines · 18 tokens per session scan A 78b10f1e8c3a
spec-detailed is a skill published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 1,204 once invoked, about $0.0001 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 2026-09-03.
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…