find-skills

find-skills is a skill for Codex from asaotomo/DeepSentry. It costs 65 tokens per session (973 once invoked), scanned C, original, Apache-2.0.

A discovery and review workflow for finding third-party agent skills from ClawHub and skills.sh. It compares candidates, checks their metadata and instructions, and installs one only after the user clearly authorizes it.

In plain words
What is it for?
Searching skill markets, inspecting candidates, comparing authorship and maintenance, reviewing security risks, installing an approved skill, and reporting its source, version, hash, and review results.
Why use it?
It helps developers find relevant extensions while reducing the risk of installing duplicate, suspicious, or unsafe skills that read secrets, run unwanted commands, or alter the system.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Searching skill markets, inspecting candidates, comparing authorship and maintenance, reviewing security risks, installing an approved skill, and reporting its source, version, hash, and review results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/asaotomo/deepsentry/find-skills
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 asaotomo/DeepSentry --skill find-skills
Clone the repo
git clone --depth 1 https://github.com/asaotomo/DeepSentry

Made for: 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 find-skills

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/asaotomo/deepsentry/find-skills"><img src="https://agentmods.dev/badge/skills/asaotomo/deepsentry/find-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 973 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00065 $0.00973
Opus 5 $0.00032 $0.00487
Sonnet 5 $0.00013 $0.00195
Haiku 4.5 $0.00006 $0.00097

Measured 9d ago against content hash 507db6afe5d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

find-skills scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

使用 DeepSentry 原生 `skill_market` 工具发现兼容 `SKILL.md` 的第三方能力。不要用 Shell 调用 `npx`、`clawhub`、`curl | sh`,也不要直接复制未知仓库;原生工具会限制市场域名、下载体积、文件数量和路径,并在安装前做静态审查。

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

使用 DeepSentry 原生 `skill_market` 工具发现兼容 `SKILL.md` 的第三方能力。不要用 Shell 调用 `npx`、`clawhub`、`curl | sh`,也不要直接复制未知仓库;原生工具会限制市场域名、下载体积、文件数量和路径,并在安装前做静态审查。
skills/find-skills/SKILL.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Find Skills

使用 DeepSentry 原生 skill_market 工具发现兼容 SKILL.md 的第三方能力。不要用 Shell 调用 npxclawhubcurl | sh,也不要直接复制未知仓库;原生工具会限制市场域名、下载体积、文件数量和路径,并在安装前做静态审查。

工作流

  1. 从用户目标中提取具体领域和任务,先搜索,不安装:
{"action":"tool","tool_name":"skill_market","tool_args":{"action":"search","query":"linux log forensics","market":"all","limit":"8"}}
  1. 比较候选时优先考虑:

    • 官方或声誉明确的作者;
    • 安装/下载量与近期维护情况;
    • 描述与当前任务是否精确匹配;
    • 是否包含脚本、外部服务、凭据或系统修改要求;
    • 是否与已有 Skill 重名或功能重复。
  2. 推荐前至少检查一个候选。ClawHub 可查看完整元数据、版本、市场安全状态和 SKILL.md 预览:

{"action":"tool","tool_name":"skill_market","tool_args":{"action":"inspect","source":"clawhub:security-audit"}}

skills.sh 结果使用 skills:<owner>/<repo>@<skill>,安装时只下载匹配的 Skill 子目录。

  1. 清楚告诉用户候选来源、用途、流行度、风险和安装引用。仅当用户明确说“安装/下载/添加这个 Skill”后才安装;确认不能从一次普通搜索或能力询问中推断。
{"action":"tool","tool_name":"skill_market","tool_args":{"action":"install","source":"skills:owner/repo@skill-name","confirm_install":"true"}}
  1. 如果市场将候选标为可疑,或下载后的本地静态审查发现管道执行、密钥读取、强制删除或持久化等模式,先展示原因并请求用户重新确认。只有收到针对该风险的明确同意后,才可传 acknowledge_risk=true。市场标为恶意的 Skill 永远不得安装。

  2. 安装完成后报告安装目录、来源版本/提交、SHA-256 和静态审查结果。新会话会自动发现;当前会话需要时使用 load_skill/skill load <name>

维护、更新与回滚

列出由市场管理的 Skill:

{"action":"tool","tool_name":"skill_market","tool_args":{"action":"managed"}}

审查用户级 Skill:

{"action":"tool","tool_name":"skill_market","tool_args":{"action":"audit"}}

先只读检查更新,再经用户明确授权更新:

{"action":"tool","tool_name":"skill_market","tool_args":{"action":"check_updates"}}
{"action":"tool","tool_name":"skill_market","tool_args":{"action":"update","name":"log-audit","confirm_update":"true"}}

需要稳定复现时使用 pin 冻结当前版本,解除时用 unpin。覆盖安装和更新都会保留旧版本;rollback 必须带 confirm_rollback=trueuninstall 必须带 confirm_remove=true,默认移动到可恢复备份,不永久删除。

静态审查只是供应链防线之一,不证明 Skill 的业务逻辑安全。遇到会执行脚本、读取密钥、联网、修改持久化配置或删除文件的工作流,仍应在实际执行相应动作时按 DeepSentry 风险确认流程处理。

无结果时

尝试更具体的同义词,或分别搜索 clawhubskills.sh。仍无合适结果时,说明没有找到可信候选,并建议直接完成任务或创建一个最小、可审查的新 Skill;不要为了“有结果”推荐低质量或不相关项目。

Read the full file on GitHub · 76 lines

Files

What ships with it

1 file 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. 9d ago First seen · 76 lines · 65 tokens per session scan C 507db6afe5d5

Subscribe to this mod's changes

find-skills is a skill published in the GitHub repository asaotomo/DeepSentry (26 stars, last pushed 6d ago), licensed Apache-2.0. It adds 65 tokens to every session and 973 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

skill-creator

Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.

zhayujie/CowAgent · 61 tokens

image-generation

Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.

zhayujie/CowAgent · 41 tokens

knowledge-wiki

Manage the personal knowledge wiki. Use when the user shares articles, documents, or asks to organize knowledge; when a conversation produces insights worth preserving as structured knowledge; or when the user asks about the knowledge base.

zhayujie/CowAgent · 46 tokens

smart-docs

AI-powered comprehensive codebase documentation generator. Analyzes project structure, identifies architecture patterns, creates C4 model diagrams, and generates professional technical documentation. Use when users need to document codebases, understand software architecture, create technical specs, or generate…

sopaco/deepwiki-rs · 80 tokens

ai-context

Project knowledge base for coding agents. Activate when: (1) starting a new session in this project, (2) encountering unfamiliar code patterns or architecture decisions, (3) user asks about project design or rationale, (4) before making significant structural changes. Contains tiered knowledge from stable design…

sopaco/deepwiki-rs · 67 tokens

deepwiki-rs

AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation. Use when Claude needs to analyze source code, understand software architecture, generate technical specs, or create professional documentation from any programming…

sopaco/deepwiki-rs · 53 tokens