sum-spec

sum-spec is a command for Claude Code from Oriolshhh/runware-image-mcp. It costs 29 tokens per session (649 once invoked), scanned A, original, MIT.

A command that turns an existing software specification into a short, plain-language explanation before anyone approves it.

In plain words
What is it for?
Use it after creating a specification or whenever you need a quick explanation of its requirements, exclusions, risks, tests, rollout plan, and unanswered questions.
Why use it?
It helps developers understand the planned work without reading every technical section, while keeping the original scope and uncertainties intact.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

Good fit Use it after creating a specification or whenever you need a quick explanation of its requirements, exclusions, risks, tests, rollout plan, and unanswered questions.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/oriolshhh/runware-image-mcp/sum-spec
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.

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 sum-spec

README.md
[![agentmods](https://agentmods.dev/badge/commands/oriolshhh/runware-image-mcp/sum-spec.svg)](https://agentmods.dev/commands/oriolshhh/runware-image-mcp/sum-spec)
Your own site
<a href="https://agentmods.dev/commands/oriolshhh/runware-image-mcp/sum-spec"><img src="https://agentmods.dev/badge/commands/oriolshhh/runware-image-mcp/sum-spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 649 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00029 $0.00649
Opus 5 $0.00015 $0.00324
Sonnet 5 $0.00006 $0.00130
Haiku 4.5 $0.00003 $0.00065

Measured 7d ago against content hash 5132ba47f27e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sum-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 7d 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/sum-spec.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sum-spec — Explain a specification clearly

Purpose

Turn a complete specification into a short, decision-ready explanation without changing its meaning, editing it, or approving it.

Invocation

/sum-spec [spec name or path]

Accepted input

An explicit .agent/specs/*.md path, a spec name, or the current spec from the conversation.

Prerequisites

An existing specification. This command does not create or repair one.

Procedure

  1. Resolve the requested spec. Prefer an explicit path or name, then the spec identified in the conversation. If neither is available, use the only spec with status: awaiting-approval. If multiple candidates remain, list them briefly and ask the user to choose; never guess.
  2. Read the entire spec, including frontmatter, requirements, non-goals, tasks, test plan, risks, migrations, rollout, and open questions. Do not broadly scan the repository unless the user asks you to verify the spec.
  3. Translate implementation language into plain language while preserving concrete behavior, scope boundaries, dependencies, and uncertainty. Expand unfamiliar acronyms once. Do not invent missing details.
  4. Produce the output below. Keep it under 500 words by default; use up to 800 only when shortening further would hide a material risk or decision.
  5. End with exactly what approval authorizes and any question that must be answered first. Do not change spec status or begin implementation.

Expected output

Use these headings:

  1. In one sentence — the intended outcome.
  2. What will change — three to seven concrete user or system behaviors.
  3. How it will be built — affected areas and implementation sequence, without line-by-line task repetition.
  4. How we will know it works — the important tests and validation gates.
  5. Risks and boundaries — material risks, compatibility or rollout work, non-goals, and assumptions.
  6. Decisions needed — unresolved questions, or None.
  7. Approval means — the precise scope the agent may implement next.

Read the full file on GitHub · 71 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. 7d ago First seen · 71 lines · 29 tokens per session scan A 5132ba47f27e

Subscribe to this mod's changes

sum-spec is a command published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 649 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.