spec

spec is a command for Claude Code from Oriolshhh/runware-image-mcp. It costs 30 tokens per session (992 once invoked), scanned A, original, MIT.

A command that turns a coding request into a reviewable specification, asking only questions that affect the decision, and waits for approval before code changes.

In plain words
What is it for?
Use it to plan small or complex changes, choose between direct planning and specialist or council review, record assumptions and acceptance criteria, and preserve approval gates for risky work.
Why use it?
It gives developers a tested plan without requiring them to decide every implementation detail upfront or memorize the available workflows.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions subagents.

Install

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.

agentmods
npx agentmods add commands/oriolshhh/runware-image-mcp/spec
Clone the repo
git clone --depth 1 https://github.com/Oriolshhh/runware-image-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for spec

README.md
[![agentmods](https://agentmods.dev/badge/commands/oriolshhh/runware-image-mcp/spec.svg)](https://agentmods.dev/commands/oriolshhh/runware-image-mcp/spec)
Your own site
<a href="https://agentmods.dev/commands/oriolshhh/runware-image-mcp/spec"><img src="https://agentmods.dev/badge/commands/oriolshhh/runware-image-mcp/spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 992 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.00992
Opus 5 $0.00015 $0.00496
Sonnet 5 $0.00006 $0.00198
Haiku 4.5 $0.00003 $0.00099

Measured 5d ago against content hash 998790ffc169, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

spec 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 5d 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.

.agent/commands/spec.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/spec — Create a spec and wait for approval

Purpose

Turn a request into an approved, testable specification before any code.

Invocation

/spec <short description of the work>

Accepted input

A request, problem statement, or ticket, with any links or constraints.

Prerequisites

A HarnessKit workspace (harnesskit init). No approved spec required.

Procedure

  1. Read .agent/context/README.md and routing when present, assess freshness, and inspect task-relevant source. Do not ask questions answered by the repo.
  2. Triage facts, assumptions, preferences, and blockers. If needed, ask one grouped batch of normally at most three questions (absolute maximum five), then wait for the answers. State reasonable defaults for non-blockers.
  3. Select and announce one path:
    • direct-spec for small, local, reversible, clear work.
    • specialist-assisted-spec for medium/cross-cutting work needing one to three relevant specialist planning reviews.
    • full-council-spec for high-risk, irreversible, architectural, security- sensitive, or product-contested work. Execute /council first, or consume its already-approved decision record. Apply model-routing: direct-spec may downgrade to standard/medium; specialist-assisted planning uses each selected agent's declared tier; and full-council planning plus final synthesis remains heavy/high.
  4. In specialist-assisted mode, use specialist-routing; issue the same brief and coordinator-built context capsule to the smallest relevant set of agents; tell them to start from the capsule rather than reload the context pack. Collect independent first-pass reports in parallel when native isolated subagents are supported, and otherwise use honestly labelled native- or simulated-sequential passes. Specialists research and advise only.
  5. Synthesize the evidence and produce a complete spec: title, goal, background, user stories, requirements, non-goals, UI/UX notes, data and API changes, edge cases, test plan, planning path and consultations, dependency-aware implementation tasks, review checklist, and open questions.
  6. For every implementation task include: ID, owner role, requirement IDs, dependencies, ownership area, acceptance criteria, required tests, parallelizable, and integration point/order.
  7. Save it to .agent/specs/<kebab-case-name>.md.
  8. Present a concise plain-language decision summary using /sum-spec's output contract. Stop and request approval explicitly. Do not start implementation workers.

Read the full file on GitHub · 108 lines

Changes

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.

  1. 5d ago First seen · 108 lines · 30 tokens per session scan A 998790ffc169

Subscribe to this mod's changes

spec is a command published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 992 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.