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/mishahanin/heading-os/context7npx skills add mishahanin/heading-os --skill context7git clone --depth 1 https://github.com/mishahanin/heading-osWrote 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/mishahanin/heading-os/context7)<a href="https://agentmods.dev/skills/mishahanin/heading-os/context7"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/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 | $0.00102 | $0.00874 |
| Opus 5 | $0.00051 | $0.00437 |
| Sonnet 5 | $0.00020 | $0.00175 |
| Haiku 4.5 | $0.00010 | $0.00087 |
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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context7 - Library Documentation
Fetch live, version-specific documentation for any library or framework via the Context7 REST API. Returns authoritative docs formatted for LLM consumption.
Naming note. A user-level Claude Code plugin also exposes a skill called
context7:context7(namespaced form). When the user types/context7without the namespace, the local skill in this file wins per Claude Code's bare-name lookup precedence (local > plugin). To force the plugin variant, type the namespaced form explicitly. Both skills do similar things; the local one uses the workspace's own CONTEXT7_API_KEY andscripts/context7.py, the plugin uses its own MCP-style backend.
Prerequisites
CONTEXT7_API_KEY should be set in the workspace .env file. The script auto-loads it via python-dotenv.
# In the workspace root .env file:
CONTEXT7_API_KEY=ctx7sk-your-key-here
Get a free key at: https://context7.com/dashboard
The API works without a key but with lower rate limits.
Workflow
-
Parse the user input: first word is the library name, remainder is the query. If only a library name is given, use "documentation" as the default query.
-
Run the script:
python scripts/context7.py "<library_name>" "<query>"
Examples:
/context7 react hooks->python scripts/context7.py "react" "hooks"/context7 nextjs app router middleware->python scripts/context7.py "nextjs" "app router middleware"/context7 python-pptx->python scripts/context7.py "python-pptx" "documentation"
-
Use the returned documentation as authoritative context. Prefer it over training data when writing or validating code.
-
If the library is not found, try alternative names (e.g., "next.js" instead of "nextjs", "react-dom" instead of "reactdom").
Script Flags
| Flag | Purpose |
|---|---|
--list |
List matching libraries without fetching docs |
--version v15 |
Pin to a specific library version |
--json |
Output structured JSON instead of text |
--limit 5000 |
Cap returned token count |
What ships with it
2 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 · 82 lines · 102 tokens per session scan A 6b6d28f2aa10
context7 is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 102 tokens to every session and 874 once invoked, about $0.0005 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
duckduckgo-search
Free keyless web, news, and image search via ddgs.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
complete-partial-pr
Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.