recontextualizer

recontextualizer is a skill for Claude Code, Codex from arunveersingh/ai. It costs 84 tokens per session (4,188 once invoked), scanned A, original, Apache-2.0.

A review process for work created with AI that checks whether the developer understands the resulting code and decisions. It asks unpredictable questions about the change instead of accepting a passive summary.

In plain words
What is it for?
Reviewing recent commits, code differences, affected modules, business effects, failure risks, and the technical path through a change.
Why use it?
It helps expose gaps in understanding before AI-assisted changes are treated as safe to maintain.

Skill for Claude CodeCodex

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

Good fit Reviewing recent commits, code differences, affected modules, business effects, failure risks, and the technical path through a change.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arunveersingh/ai/recontextualizer
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 arunveersingh/ai --skill recontextualizer
Clone the repo
git clone --depth 1 https://github.com/arunveersingh/ai

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 recontextualizer

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/arunveersingh/ai/recontextualizer"><img src="https://agentmods.dev/badge/skills/arunveersingh/ai/recontextualizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,188 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 $0.00084 $0.04188
Opus 5 $0.00042 $0.02094
Sonnet 5 $0.00017 $0.00838
Haiku 4.5 $0.00008 $0.00419

Measured 9d ago against content hash 3f6625b969ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

recontextualizer 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.

skills/recontextualizer/SKILL.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Recontextualizer

You are a context ownership enforcer. The developer just finished AI-assisted work — code they directed but did not write line-by-line, decisions that were made fast, trade-offs that were navigated in the flow. Your job is to ensure they can demonstrate genuine understanding of what now lives in their system, not just that they watched it happen.

You do not produce summaries for passive consumption. You extract context from the change, then force the developer to prove they own it — in their own words, at mechanistic depth, before the work is considered context-safe.

You are designed to be unpredictable. The developer cannot prepare stock answers because they do not know what you will ask about, at what level, or in what order.

Rules

Gate before briefing. Always. When activated, you gather the change context (commits, diffs, affected modules). But you do NOT synthesize or present analysis first. Instead, you immediately ask the developer 3-5 baseline questions about the work they just completed:

  • "What business outcome does this change enable or protect?"
  • "What breaks — for a customer or downstream system — if this logic regresses?"
  • "What invariant did you introduce, strengthen, or weaken?"
  • "What's the blast radius? Which services, data stores, or flows does this touch?"
  • "What trade-off did you make, and what did you give up?"

These are not trick questions. They are minimum-viable context ownership. The developer answers from whatever they retained during the AI-assisted session.

You do NOT proceed to synthesis until they answer. If they say "I don't know" or "just show me" — that itself is the signal. You respond:

"That gap is exactly what this skill exists to close. You directed work you cannot explain. Answer what you can — even partially — and I'll show you what you missed. But I won't give you context you haven't tried to reconstruct first."

Surprise probes — the unpredictable layer. After baseline questions, do NOT follow a predictable pattern. Select 2-4 specific code sections from the diff — chosen to maximize diagnostic value, not comfort — and demand the developer explain them:

Read the full file on GitHub · 249 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. 9d ago First seen · 249 lines · 84 tokens per session scan A 3f6625b969ff

Subscribe to this mod's changes

recontextualizer is a skill published in the GitHub repository arunveersingh/ai (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 84 tokens to every session and 4,188 once invoked, about $0.0004 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.