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/netresearch/cli-tools-skill/cli-toolsnpx skills add netresearch/cli-tools-skill --skill cli-toolsgit clone --depth 1 https://github.com/netresearch/cli-tools-skillWhat 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 | $0.00071 | $0.00918 |
| Opus 5 | $0.00036 | $0.00459 |
| Sonnet 5 | $0.00014 | $0.00184 |
| Haiku 4.5 | $0.00007 | $0.00092 |
Grade A, and why
cli-tools scanned grade A 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 yesterday.
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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| No sudo | `cargo install`, `pip install --user`, manual binary; on Debian/Ubuntu `apt-get download` + `dpkg -x` | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
29 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.
- references/binary_to_tool_map.md 1.8 KB
- references/preferred-tools.md 3.7 KB
- references/project_type_requirements.md 3.2 KB
- references/resolution-workflow.md 1.6 KB
- references/troubleshooting.md 8.0 KB
- scripts/auto_update.sh 31 KB runs code
- scripts/check_environment.sh 6.9 KB runs code
- scripts/detect_project_type.sh 4.2 KB runs code
- scripts/install_composer.sh 2.0 KB runs code
- scripts/install_tool.sh 2.6 KB runs code
- scripts/installers/aws_installer.sh 1.5 KB runs code
- scripts/installers/dedicated_script.sh 1.2 KB runs code
- scripts/installers/github_clone.sh 2.3 KB runs code
- scripts/installers/github_release_binary.sh 9.7 KB runs code
- scripts/installers/hashicorp_zip.sh 2.6 KB runs code
- scripts/installers/npm_global.sh 2.1 KB runs code
- scripts/installers/npm_self_update.sh 1.4 KB runs code
- scripts/installers/package_manager.sh 5.8 KB runs code
- scripts/installers/uv_tool.sh 2.0 KB runs code
- scripts/lib/capability.sh 6.9 KB runs code
- scripts/lib/catalog.sh 1.9 KB runs code
- scripts/lib/common.sh 2.2 KB runs code
- scripts/lib/dependency.sh 7.1 KB runs code
- scripts/lib/install_strategy.sh 2.5 KB runs code
- scripts/lib/path_check.sh 13 KB runs code
- scripts/lib/policy.sh 7.6 KB runs code
- scripts/lib/reconcile.sh 11 KB runs code
- scripts/lib/root.sh 755 B runs code
- scripts/lib/scope_detection.sh 16 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.
- yesterday First seen · 89 lines · 71 tokens per session scan A cbe1976494fa
cli-tools is a skill published in the GitHub repository netresearch/cli-tools-skill (6 stars, last pushed 4d ago), with no licence file. It adds 71 tokens to every session and 918 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
web-clone
网站复刻 / 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树，覆盖静态站 / React-Vue-Next 内容站 / WebGL-Canvas 重前端站三大分支，并强制核对任何 AI 二手分析里的可执行代码。.
jira-communication
Use when interacting with Jira issues - searching, creating, updating, moving, transitioning, commenting, logging work, downloading attachments, managing sprints, boards, issue links, web links, fields, or users. Auto-triggers on Jira URLs and issue keys (PROJ-123). Also use when MCP Atlassian tools fail or are…
jira-communication
Use when handling Jira issues, sprints, boards, links, fields, worklogs, attachments, or users, or on any Jira intent without a key ("create/find a ticket", "pick a project"). Auto-triggers on Jira URLs and issue keys (PROJ-123). Also use when MCP Atlassian tools fail or are unavailable for Jira Server/DC.
jira-syntax
Use when writing or formatting Jira descriptions, comments, or any text destined for Jira. Converts Markdown to Jira wiki markup, provides templates (bug reports, feature requests), and validates syntax before submission. Trigger on any Jira content authoring task.
agent-rules
Use when creating or updating AGENTS.md files, .github/copilot-instructions.md, or other AI agent rule files, onboarding AI agents to a project, standardizing agent documentation, or when anyone mentions AGENTS.md, agent rules, project onboarding, or codebase documentation for AI agents.
ppt-speech-writer
Read a real .pptx using text extraction, OOXML inspection, slide rendering, OCR, visual inventory, and vision-capable screenshot review; then write academic speaker notes grounded in every visible slide element, generate a complete display-version document, and inject clean notes into the PowerPoint notes pane. Use…