blueprint-compare-pair

blueprint-compare-pair is a skill for Claude Code, Codex from receptron/mulmoterminal. It costs 46 tokens per session (759 once invoked), scanned A, original, MIT.

A document comparison task that matches each article in an old version with the corresponding article in a new version. It records whether each article stayed the same, changed, was added, or was removed.

In plain words
What is it for?
It is for comparing two versions of policies, contracts, regulations, or other structured documents and saving the results as a JSON file.
Why use it?
It helps people compare revised documents without relying on article numbers, which may change when provisions move. The original documents are left untouched.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for comparing two versions of policies, contracts, regulations, or other structured documents and saving the results as a JSON file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/receptron/mulmoterminal/pair
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.

Any agent
npx skills add receptron/mulmoterminal --skill pair
Clone the repo
git clone --depth 1 https://github.com/receptron/mulmoterminal

Made for: Claude Code, Codex.

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 blueprint-compare-pair

README.md
[![agentmods](https://agentmods.dev/badge/skills/receptron/mulmoterminal/pair/github.svg)](https://agentmods.dev/skills/receptron/mulmoterminal/pair)
Your own site
<a href="https://agentmods.dev/skills/receptron/mulmoterminal/pair"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/pair/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.

agentmods 80×15 button for blueprint-compare-pair

Your own site · 80×15
<a href="https://agentmods.dev/skills/receptron/mulmoterminal/pair"><img src="https://agentmods.dev/badge/skills/receptron/mulmoterminal/pair.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 759 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 $0.00046 $0.00759
Opus 5.5 $0.00018 $0.00304
Sonnet 5.5 $0.00009 $0.00152
Haiku 4.5 $0.00005 $0.00076

Measured 24d ago against content hash 40d925f36e8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

blueprint-compare-pair 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 24d 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.

blueprints/compare/skills/pair/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pair the articles of the two versions

.blueprint/answers.json names the old version (old), the new version (new) — one file each — and what the person wants looked at first (focus, may be empty). Read both in full. The person may not be an engineer: say what you do in plain words.

Change nothing in the repository: neither version is touched. Write only under .blueprint/.

Find the articles

Run sh <base pack>/checks/chaff.sh tree <file> --format json on each version. Every node whose kind is article is one article; its address ("4") is how you name it below, and attrs.label (第4条, Article 4) is how the person reads it. The check uses the same tree, so an article chaff does not read as one is not yours to pair.

Pair them

For each article of the old version, find the article of the new version that carries the same provision — by what it says, not by its number: a provision that moved or was renumbered (old 第9条 is new 第8条) is one pair. Then write .blueprint/comparison.json:

{ "rows": [
  { "old": "1", "new": "1", "change": "same" },
  { "old": "4", "new": "4", "change": "changed", "what": "委託料が月額200,000円から220,000円になった" },
  { "old": null, "new": "5", "change": "added", "what": "毎月5日までの報告の条が足された" },
  { "old": "8", "new": null, "change": "removed", "what": "成果物の扱いの条が消えた" },
  { "old": "9", "new": "8", "change": "same" }
] }
  • same / changed — both old and new. changed needs what: one line, in the person's language, saying what is different, with the words or numbers from both versions. A change in a paragraph or an item is a change to the article that holds it.
  • added — only new; removed — only old. A what saying what the article is about helps the person.
  • Every article of each version appears in exactly one row.

Whether a pair is same or changed is not a judgement: the check compares the two articles' text (spacing aside, and leaving out the article's own number) and refuses a same whose text differs and a changed whose text does not. When you pair two articles that the check calls different but you think the change is trivial (punctuation, a character's width), it is still changed: say so in what.

Read the full file on GitHub · 52 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. 24d ago First seen · 52 lines · 46 tokens per session scan A 40d925f36e8a

Subscribe to this mod's changes

blueprint-compare-pair is a skill published in the GitHub repository receptron/mulmoterminal (245 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 759 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-01.

Related

Other skills, from other repositories