agentmods.dev

ask

ask is a skill for Claude Code, Codex from jeffy-w/AgentSkills. It costs 41 tokens per session (570 once invoked), scanned A, original, MIT.

A local command-line helper for asking Claude, Gemini, or Codex for focused questions, reviews, brainstorming, or a second opinion. It saves the request, response, summary, and follow-up actions as a reusable Markdown file.

In plain words
What is it for?
Use it for code reviews, bug analysis, architecture questions, brainstorming, and second opinions. It can also apply saved role prompts such as reviewer, architect, or debugger.
Why use it?
It gives you another model’s view without manually copying prompts and results between tools. Saved artifacts make the advice available for later reference.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: runs codex exec; mentions Codex.

not rated 2repo 4mo ago A scan 41 tokens original MIT

Good fit Use it for code reviews, bug analysis, architecture questions, brainstorming, and second opinions. It can also apply saved role prompts such as reviewer, architect, or debugger.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeffy-w/agentskills/ask
View source ↗ jeffy-w/AgentSkills
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 jeffy-w/AgentSkills --skill ask
Clone the repo
git clone --depth 1 https://github.com/jeffy-w/AgentSkills

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 ask

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeffy-w/agentskills/ask/github.svg)](https://agentmods.dev/skills/jeffy-w/agentskills/ask)
Your own site
<a href="https://agentmods.dev/skills/jeffy-w/agentskills/ask"><img src="https://agentmods.dev/badge/skills/jeffy-w/agentskills/ask/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 ask

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeffy-w/agentskills/ask"><img src="https://agentmods.dev/badge/skills/jeffy-w/agentskills/ask.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 570 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 $0.00041 $0.00570
Opus 5.5 $0.00016 $0.00228
Sonnet 5.5 $0.00008 $0.00114
Haiku 4.5 $0.00004 $0.00057

Measured 2mo ago against content hash cca84b8c08f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ask 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/ask.js), 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.

ask/SKILL.md · 75 lines

What it actually says

Ask

使用本 skill 时，直接调用本机安装的 claude、gemini 或 codex CLI，并把结果保存为可复用 artifact。

When to use

  • 用户明确说要使用本地顾问 CLI 能力。
  • 需要本地 Claude / Gemini 做一轮 review、二次确认、brainstorming。
  • 需要保留原始任务、最终 prompt、原始输出和 action items。

Script

主脚本：

ask/scripts/ask.js

Direct usage

node ask/scripts/ask.js claude "请 review 当前改动"
node ask/scripts/ask.js gemini --prompt "分析这个 bug 根因"
node ask/scripts/ask.js codex --prompt "给我第二视角分析当前实现"
node ask/scripts/ask.js claude --agent-prompt code-reviewer "请检查这次重构风险"

Behavior

  1. 校验 provider 只允许 claude、gemini 或 codex。
  2. 可选读取 prompts/<role>.md，将角色 prompt 与用户 prompt 拼接。
  3. 直接调用本地 CLI：
    • claude -p -- "<prompt>"
    • gemini -p "<prompt>"
    • codex exec --skip-git-repo-check --sandbox read-only "<prompt>"
  4. 将输出写入：
.artifacts/ask/<provider>-<slug>-<timestamp>.md

artifact 至少包含：

  1. Original user task
  2. Final prompt
  3. Raw CLI output
  4. Concise summary
  5. Action items

Role prompts

角色 prompt 目录：

ask/prompts/

如果需要新增角色，直接新增同名 .md 文件，例如：

  • code-reviewer.md
  • architect.md
  • debugger.md

Guardrails

  • 本 skill 只走本地 CLI，不要静默切换到 MCP 或远端 provider。
  • 如果本地 binary 缺失，应直接报错并提示用户安装。
  • codex provider 默认走非交互 codex exec，并使用只读沙箱，适合作为问答 / review / 分析顾问，不适合直接让它改代码。
  • 回答时优先总结 artifact 里的结论，再决定是否继续落实现或 review。
Files

What ships with it

4 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.

  1. 2mo ago First seen · 75 lines · 41 tokens per session scan A cca84b8c08f9

Subscribe to this mod's changes

ask is a skill published in the GitHub repository jeffy-w/AgentSkills (2 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 570 once invoked, about $0.0002 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 2026-08-31.

Building agents
Related

ask compared with skills from other repositories

ask next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
askjeffy-w/AgentSkillsSkill24mo agoMITA41Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code