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 instructions/ourobx/agent-ebpf/skill-official-updatergit clone --depth 1 https://github.com/ourobx/agent-ebpfWrote 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/instructions/ourobx/agent-ebpf/skill-official-updater)<a href="https://agentmods.dev/instructions/ourobx/agent-ebpf/skill-official-updater"><img src="https://agentmods.dev/badge/instructions/ourobx/agent-ebpf/skill-official-updater.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 | $0.01581 | $0.01581 |
| Opus 5 | $0.00790 | $0.00790 |
| Sonnet 5 | $0.00316 | $0.00316 |
| Haiku 4.5 | $0.00158 | $0.00158 |
Grade C, and why
skill-official-updater scanned grade C 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 today.
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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Copilot Instruction Telemetry: This file was auto-generated by Claude Skills Manager --> How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-official-updater
Official Anthropic Skills Updater
Keeps a local copy of Anthropic's official skills
(https://github.com/anthropics/skills, under skills/) in sync with this
repo's skills_library/, without silently overwriting unrelated or
hand-edited skills.
State file
skills_library/.official-skills-state.json (create if missing):
{
"repoSha": "<last-synced commit SHA of anthropics/skills>",
"skills": {
"pdf": "<commit SHA of skills/pdf/ at last sync>",
"docx": "<commit SHA of skills/docx/ at last sync>"
}
}
Only skill names listed under skills are "managed" by this updater - a
same-named skill in skills_library/ that ISN'T listed there is assumed to
be a hand-written/customized skill and must never be overwritten without an
explicit user decision.
1. Cheap check (every session)
Automation: When the Claude Skills extension is active and this workspace
has skills_library/, it installs a Claude Code SessionStart hook
(official-skills-watch.js) that runs the check below on startup,
resume, and clear. If updates exist, the hook injects context telling
you to read this skill and sync immediately — do not ask the user which
skills to pull.
Manual / fallback (same logic):
git ls-remote https://github.com/anthropics/skills.git HEAD
Compare the returned SHA to repoSha in the state file (treat a missing
file as "no state yet"). If unchanged, say nothing further - this step
should be silent and near-instant.
VS Code: Claude Skills: Check Official Anthropic Skill Updates runs the same check from the Command Palette. Enable Official Skills Session Check re-installs the SessionStart hook if needed.
2. When the repo SHA has changed (or no state file yet)
List the current skill directories upstream:
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 cc792faf9d89
- yesterday Changed 50b8b24f00f0
- 5d ago First seen · 148 lines · 1,581 tokens per session scan C 2c38e9b99725
skill-official-updater is an instructions file published in the GitHub repository ourobx/agent-ebpf (1 stars, last pushed yesterday), licensed MIT. It adds 1,581 tokens to every session, about $0.0079 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
aigis CLAUDE.md
Claude Code instructions for killertcell428/aigis, covering aigis — project guidelines, zenn記事管理(zenn cli + github連携), ディレクトリ構成, 記事の作成 and プレビュー.
casbin-gateway CLAUDE.md
Claude Code instructions for apache/casbin-gateway, covering claude.md, code style and chinese translations.
preloop AGENTS.md
AGENTS.md instructions for preloop/preloop, covering preloop development guide, commands, cli dev builds, git workflow and keep sample data generic.
xops-cli AGENTS.md
AGENTS.md instructions for wentf9/xops-cli, covering ai 助手开发协作指南 (agents.md), 🎨 1. 编码规范 (coding standards), 📦 2. git 规范 (git standards) and 🛠️ 3. 测试、构建与 ci (testing, building & ci).
fwskillsshare AGENTS.md
Instructions for fastrevmd-lab/fwskillsshare, covering firewall skills repository instructions, purpose and architecture, setup and development, required checks and skill description constraints.
esp32_nat_router CLAUDE.md
Claude Code instructions for martin-ger/esp32_nat_router, covering claude.md and code exploration policy.