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/dianel555/dskills/context7npx skills add Dianel555/DSkills --skill context7git clone --depth 1 https://github.com/Dianel555/DSkillsWrote 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/dianel555/dskills/context7)<a href="https://agentmods.dev/skills/dianel555/dskills/context7"><img src="https://agentmods.dev/badge/skills/dianel555/dskills/context7.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 | $0.00193 | $0.01970 |
| Opus 5 | $0.00097 | $0.00985 |
| Sonnet 5 | $0.00039 | $0.00394 |
| Haiku 4.5 | $0.00019 | $0.00197 |
Grade A, and why
context7 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 6d 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.
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.
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context7
Fetch current library/framework/API documentation from the Context7 API, so answers cite authoritative docs instead of relying on outdated training data. This skill uses the co-located Node CLI in context7-api.cjs; no MCP dependency is required.
Architecture
| Piece | Role | Recommended Use |
|---|---|---|
| context7 (this file) | Intent detection, library selection, answer integration | Default path |
| context7-fetcher | Optional low-context wrapper around the same CLI | Use only if your runtime truly supports isolated workers/subtasks |
The canonical execution path is to run the co-located CLI directly. Do not require a Task/Bash-specific subtask mechanism, and do not hardcode repo-relative paths like skills/context7/context7-api.cjs — that breaks when the skill is installed globally outside the source repo.
Call Flow
User Query → context7 (detect trigger + extract library)
↓ shell / worker → node <context7-skill-dir>/context7-api.cjs search <library> <query>
→ JSON libraries[] (+ raw results[])
context7 (select best match: name / trustScore / version)
↓ shell / worker → node <context7-skill-dir>/context7-api.cjs context <libraryId> <query>
→ JSON results[] (+ raw codeSnippets[] / infoSnippets[])
context7 (integrate relevant snippets into answer)
Implementation Layout
context7-api.cjs- Node CLI entrypoint (HTTPS client,.env+ env-var API key, MSYS path fix, response normalization)context7-fetcher.md- Optional helper wrapper around the same CLI.env.example- API key template (copy to.env)tests/test_context7_api.cjs- Regression tests for response-shape compatibility and error exits
Execution Method
# Prerequisites: Node.js 18+ (no npm install needed; stdlib only)
# Environment: CONTEXT7_API_KEY (optional; public rate limits apply if unset)
# Run from the context7 skill directory
node ./context7-api.cjs search "<library-name>" "<user-query>"
node ./context7-api.cjs context "<library-id>" "<specific-query>"
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.
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.
- 6d ago First seen · 184 lines · 193 tokens per session scan A 1d1a4d78c0eb
context7 is a skill published in the GitHub repository Dianel555/DSkills (64 stars, last pushed today), licensed MIT. It adds 193 tokens to every session and 1,970 once invoked, about $0.0010 per session on Opus 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 2026-08-30.
Other skills, from other repositories
casely
Virtual QA Lead that turns requirement documents into review-ready, TestRail-importable test cases in one conversation — no commands to memorize. Use this skill whenever the user has requirements, a spec, a user story, or acceptance criteria (PDF, DOCX, XLSX, TXT, MD, or pasted text) and wants test cases, a test plan…
battle-tested-engineer
Engineering judgment for code write/refactor/test and frontend UI. Trigger on code review, legacy cleanup, tests, UI with data, bloat/over-engineer complaints — even with no explicit mention, before any diff/rewrite/test suite. Output ultra-terse caveman style; code, commits, PR desc, security warnings stay normal…
geekx-gate
当用户审查需求、工程计划、架构提案、路线图、最小可行范围或智能体输出，并担心过度设计、范围过大、未来假设太多、缺少非目标、缺少必要性证据，或想判断重写、框架、插件系统、工作流引擎、多智能体架构、模块边界等难撤回技术决定现在该不该做时使用。典型触发词：必要性审判、反过度设计、范围审查、砍噪音、最小必要升级、复杂度税、承诺闸门、技术决定、重写、开庭、多线程审判。.
geekx-grilling
当用户希望通过连续追问压力测试计划、决定、想法、需求或方案，要求 grill me、grilling、拷问我、追问到底、挑战假设、梳理决策树，或需要在行动前逐项消除关键歧义时使用。尤其适合存在多个选项、依赖关系、过度设计风险或尚未形成共同理解的场景。.
tryworld-paper
Create branded 试界TryWorld AI-knowledge videos in the fixed "Paper Algorithm" (纸上算法) style with HyperFrames. Input is a Chinese voiceover script and optional images; output is a 16:9 horizontal video with Azure YunxiNeural (真·云希) voiceover, word-synced captions, ink/paper animations and unified transitions, an…
tryworld-koubo
试界TryWorld AI 口播视频的统一定位入口，覆盖口播全流程（选题/写稿/优化/出片）。涉及口播的请求都应触发：做口播/口播视频/口播稿/写口播稿/帮我选题/口播选题/这周做什么口播/AI 资讯盘点，或直接粘贴口播稿要求优化出片。自动识别两种模式：①直接给稿 → $tryworld-paper 优化并出片；②要选题 → $tryworld-topics 拉 AIHOT 资讯产选题清单 → 挑选 → 写稿 → 优化 → 出片。子命令：只要选题/只要写稿/只优化不出片。交付附四平台推荐发布时间。无需同时引用其他技能。.