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 agentmods add skills/ackeskin/contexture/new-hooknpx skills add AcKeskin/contexture --skill new-hookgit clone --depth 1 https://github.com/AcKeskin/contextureWrote 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/ackeskin/contexture/new-hook)<a href="https://agentmods.dev/skills/ackeskin/contexture/new-hook"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/new-hook.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.03198 |
| Opus 5 | $0.00035 | $0.01599 |
| Sonnet 5 | $0.00014 | $0.00640 |
| Haiku 4.5 | $0.00007 | $0.00320 |
Grade B, and why
new-hook scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
description: "Scaffold a new Claude Code hook end-to-end from a recipe — produces the hook file, payload fixtures, a Node-based runner, and the ~/.claude/settings.json registration (diff previewed). Use when the user typ How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
new-hook
The hook scaffold organ. Closes the gap that no other skill helps with: building new Claude Code hooks correctly, including the matcher / event vocabulary, the fail-open exit-code contract, and the high-stakes ~/.claude/settings.json registration edit.
When to run
- User types
/new-hook(explicit trigger). - User says "scaffold a hook," "add a new hook," "create a PreToolUse blocker for X."
- Do not auto-fire. No session-start or event-hook triggers. Mode A only — every run goes through the interview.
Inputs
- Triggering message. Anything after
/new-hookis hint text — used to bias recipe selection but never enough to skip the interview. - Bootstrap state. Whether
contexture/hooks/is the symlink source for~/.claude/hooks/. Detected at scaffold time, not configured. - Existing hooks tree.
~/.claude/hooks/(andcontexture/hooks/when bootstrapped) — used for the collision check on the chosen hook name. - Existing settings.
~/.claude/settings.json— read once for the merge contract.
Procedure
1. Recipe selection
List the recipes available in recipes/. Each recipe folder has a README.md with a one-line description, the matcher, and the event. Show them as a numbered list:
Which recipe?
1. bash-command-blocker (PreToolUse, matcher: Bash) — pattern-match a Bash command, block on hit
2. file-write-blocker (PreToolUse, matcher: Write|Edit|MultiEdit|NotebookEdit) — block file writes by path
3. mcp-tool-blocker (PreToolUse, matcher: mcp__*) — block a specific MCP tool by exact name
4. context-injector (SessionStart, matcher: startup|compact) — inject context at session start
5. session-recovery-advisory (SessionStart, matcher: clear|compact) — scan the prior transcript and nudge to recover something lost across a clear/compact
6. rule-prime (SessionStart[startup|clear|compact] + UserPromptSubmit) — mechanically prime resolved architectural rules into context; floor at session start, incremental tiers per prompt
What ships with it
27 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.
- lib/runner-template.js 3.6 KB runs code
- lib/settings-merge.js 3.7 KB runs code
- lib/settings-merge.test.js 4.1 KB runs code
- recipes/bash-command-blocker/allow.json.template 77 B
- recipes/bash-command-blocker/block.json.template 86 B
- recipes/bash-command-blocker/README.md 2.5 KB
- recipes/bash-command-blocker/template.js 440 B runs code
- recipes/context-injector/allow.json.template 120 B
- recipes/context-injector/block.json.template 112 B
- recipes/context-injector/README.md 3.3 KB
- recipes/context-injector/template.js 1.2 KB runs code
- recipes/file-write-blocker/allow.json.template 120 B
- recipes/file-write-blocker/block.json.template 109 B
- recipes/file-write-blocker/README.md 2.8 KB
- recipes/file-write-blocker/template.js 710 B runs code
- recipes/mcp-tool-blocker/allow.json.template 86 B
- recipes/mcp-tool-blocker/block.json.template 55 B
- recipes/mcp-tool-blocker/README.md 2.0 KB
- recipes/mcp-tool-blocker/template.js 323 B runs code
- recipes/rule-prime/allow.json.template 112 B
- recipes/rule-prime/block.json.template 126 B
- recipes/rule-prime/README.md 4.3 KB
- recipes/rule-prime/template.js 17 KB runs code
- recipes/session-recovery-advisory/allow.json.template 159 B
- recipes/session-recovery-advisory/block.json.template 171 B
- recipes/session-recovery-advisory/README.md 4.6 KB
- recipes/session-recovery-advisory/template.js 3.1 KB runs code
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.
- 2d ago First seen · 213 lines · 70 tokens per session scan B 4473171f27f2
new-hook is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 3,198 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
ai-ml-development
AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
email-systems
Transactional email (Resend, SendGrid, SES), templates (React Email, MJML), deliverability (SPF/DKIM/DMARC), and inboxing best practices. Use when building email infrastructure, designing templates, or troubleshooting deliverability.
ios-development
Comprehensive guide for building native Apple platform applications.
ai-policy-generator
AI governance policy creation for nonprofits and enterprises with frameworks, risk assessment, ethical guidelines, and compliance templates. Use when drafting AI usage policies, responsible AI frameworks, or organizational AI governance documents.
battle-card-builder
Competitive battle card creation for sales teams combining competitive intelligence, sales enablement, and document formatting. Use when building battle cards, competitive analysis decks, or win/loss analysis materials.