What is pair-intelligence?

A workflow for asking a second AI model for an independent view, then checking its claims against the source. It is intended as a second opinion, not as an automatic authority.

It is for reviewing plans and diffs, settling disputed technical decisions, brainstorming, diagnosing problems, checking screenshots, researching the web, and driving a browser through another model.

It can expose missed issues or alternative explanations in plans, code changes, diagnoses, screenshots, and research, while requiring the first model to verify the response.

pair-intelligence — Skill for Claude Code by shaharsha/claude-skills

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 shaharsha/claude-skills --skill pair-intelligence

Clone the repo

git clone --depth 1 https://github.com/shaharsha/claude-skills

Made for: Claude Code.

Or install engineering-decisions, the plugin that ships this one along with the rest of its 2 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/shaharsha/claude-skills/pair-intelligence/github.svg)](https://agentmods.dev/skills/shaharsha/claude-skills/pair-intelligence)

Your own site

<a href="https://agentmods.dev/skills/shaharsha/claude-skills/pair-intelligence"><img src="https://agentmods.dev/badge/skills/shaharsha/claude-skills/pair-intelligence/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/shaharsha/claude-skills/pair-intelligence"><img src="https://agentmods.dev/badge/skills/shaharsha/claude-skills/pair-intelligence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,626 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.

Model	Per session	Once invoked
Fable 5.1	$0.00120	$0.02626
Opus 5.5	$0.00048	$0.01050
Sonnet 5.5	$0.00024	$0.00525
Haiku 4.5	$0.00012	$0.00263

Measured today against content hash dea6d61b0857, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pair-intelligence 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 today.

The scan reads SKILL.md. This mod also ships 18 executable files (scripts/agy_gate.py, scripts/codex_lockdown.sh, scripts/codex_review.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/pair-intelligence/SKILL.md · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pair intelligence

Ask a second model (Codex/GPT or Gemini) through its CLI, then judge its answer against the source. The other model returns claims, not verdicts. The value is an independent read plus your adjudication; relaying an answer unchecked launders a guess into an authority.

The user's instructions take precedence over this skill.

When it's worth it

Worth it: a plan or change about to land (especially money, auth, migrations, concurrency, permissions, deletion), a contested decision, a diagnosis you cannot settle, ideas that need a different lineage, a screenshot or live page that needs a second pair of eyes.

Also worth it: your own recommendation, before you present it to the user.

Not worth it: work still changing, anything the tests already settle, a question you can answer by reading the code yourself, and mechanical commits (lint, a re-stamp, an unused import): read those diffs yourself. A small config or docs change gets the short template at medium effort and one round, not the full review (see references/review.md).

Pick the mode

Mode	Use for	Session	Read first
`review`	a plan, a diff, or code against its plan, before it lands	fresh reviewer every round	`references/review.md`
`consult`	choosing between options, a diagnosis, checking a claim or your own recommendation, critiquing a non-code document	fresh; one resumed follow-up to dispute a claim	`references/consult.md`
`ideate`	brainstorming, naming, exploring a design space	one named session, at most 3 rounds	`references/ideate.md`
`research`	web search and reading docs, with sources	fresh, empty scratch directory	`references/research.md`
`browse`	opening, clicking and screenshotting real pages	fresh, allow-listed domains only	`references/research.md`

Read the mode's file before you write the prompt. Images work in any mode: add --image (how to ask about one: references/research.md).

Pick the engine

Read the full file on GitHub · 186 lines

Files

What ships with it

28 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

today Changed · +3 lines dea6d61b0857
yesterday Changed · +8 lines e88e8e000788
4d ago Changed · +14 lines · +9 tokens per session 3d79df734f81
5d ago First seen · 161 lines · 111 tokens per session scan A 63f42480f79b

Subscribe to this mod's changes

pair-intelligence is a skill published in the GitHub repository shaharsha/claude-skills (6 stars, last pushed today), licensed MIT. It adds 120 tokens to every session and 2,626 once invoked, about $0.0005 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 2026-11-02.

Building agents Code review

pair-intelligence next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pair-intelligenceshaharsha/claude-skills	Skill	6	today	MIT	A	120	Claude Code
autoreviewopenclaw/clawhub	Skill	9.5k	yesterday	MIT	A	17	Claude Code, Codex
agent-teams-simplify-and-hardenLeoYeAI/openclaw-master-skills	Skill	2.2k	6d ago	MIT	A	115	Claude Code, Codex
omh-code-reviewrlaope/oh-my-hermes	Skill	5.2k	yesterday	MIT	A	48	Claude Code, Codex
revdiff-planumputun/revdiff	Skill	945	2d ago	MIT	A	84	Claude Code
explore-unknownsdzhng/skills	Skill	1.4k	2d ago	MIT	A	162	Claude Code, Codex
re0-mergeLilMGenius/paperthin	Skill	1.4k	4d ago	MIT	A	70	Claude Code