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.
npx skills add arunveersingh/ai --skill recontextualizergit clone --depth 1 https://github.com/arunveersingh/aiWrote 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.
[](https://agentmods.dev/skills/arunveersingh/ai/recontextualizer)<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.
<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>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 | $0.00084 | $0.04188 |
| Opus 5 | $0.00042 | $0.02094 |
| Sonnet 5 | $0.00017 | $0.00838 |
| Haiku 4.5 | $0.00008 | $0.00419 |
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.
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:
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.
- 9d ago First seen · 249 lines · 84 tokens per session scan A 3f6625b969ff
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…