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 councilgit 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/council)<a href="https://agentmods.dev/skills/oriolshhh/runware-image-mcp/council"><img src="https://agentmods.dev/badge/skills/oriolshhh/runware-image-mcp/council/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/council"><img src="https://agentmods.dev/badge/skills/oriolshhh/runware-image-mcp/council.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 | $0.00016 | $0.01541 |
| Opus 5 | $0.00008 | $0.00771 |
| Sonnet 5 | $0.00003 | $0.00308 |
| Haiku 4.5 | $0.00002 | $0.00154 |
Grade A, and why
council 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/council — Convene the solution council
Purpose
Produce a defensible implementation recommendation for an ambiguous or high-impact
request, using only the specialists the decision needs. The council never writes
production code; it stops at human approval and hands off to /spec.
Invocation
/council <feature idea, problem, or proposed change>
Examples
/council add multi-tenant API keys with per-tenant rate limits/council should we replace our bespoke cache with Redis?/council the importer is slow on large files — what should we change?/council migrate the config format from JSON to YAML
Accepted input
A feature idea, problem statement, or proposed change — however rough.
Prerequisites
- A HarnessKit workspace (
harnesskit init). - Runs inside the consuming AI coding tool; the HarnessKit CLI calls no model API.
- Fresh
.agent/context/is recommended; run/build-contextfirst if missing or stale.
Procedure
- Discovery —
product-discoveryreuses.agent/context/viacontext-discovery, inspects repository evidence, and produces a decision brief (facts, assumptions, preferences, blockers). Ask at most 3 (max 5) grouped, decision-changing questions; otherwise state defaults and continue. Build one task context capsule and pass it with the brief to every specialist so they do not independently reload the context pack. - Routing —
council-routerselects the smallest relevant specialist set (always architecture and product; add security, testing, operations, UX, data, frontend design/system/accessibility/motion, or others only on evidence) and explains each choice. Skip the full council for trivial, low-risk changes. Applymodel-routing: the router may be light, each specialist uses its declared default or an evidence-based escalation, and chair synthesis stays heavy/high. Never use a light model to adjudicate heavy specialist reports. - Independent review — each selected specialist produces a first-pass report from the brief without seeing the others' reports. Run them in the strongest isolation your platform supports (see Execution modes).
- Challenge — exactly one bounded round.
devils-advocate(plus selected specialists) challenges the leading proposal with evidence-based objections, unsupported assumptions, and premature-consensus checks. No further rounds. - Synthesis —
council-chairintegrates reports and rebuttals into one decision record (recommended path, confidence, rejected alternatives, risks, preserved dissent, unresolved questions). It synthesizes; it does not vote. - Approval — stop and present the decision record for explicit human approval.
- Handoff — only after approval, run
/specto enter spec-to-implementation. The council itself writes no production code.
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 · 144 lines · 16 tokens per session scan A c4af01894e5f
council is a skill published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 1,541 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 2026-08-31.
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…