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 skills add julianobarbosa/claude-code-skills --skill context7git clone --depth 1 https://github.com/julianobarbosa/claude-code-skillsWrote 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/julianobarbosa/claude-code-skills/context7)<a href="https://agentmods.dev/skills/julianobarbosa/claude-code-skills/context7"><img src="https://agentmods.dev/badge/skills/julianobarbosa/claude-code-skills/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 | $0.00134 | $0.02883 |
| Opus 5 | $0.00067 | $0.01442 |
| Sonnet 5 | $0.00027 | $0.00577 |
| Haiku 4.5 | $0.00013 | $0.00288 |
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 7d 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context7
Query up-to-date, version-specific documentation and code examples directly from source libraries via Context7's documentation aggregation platform.
Why Context7
| Benefit | Description |
|---|---|
| Current APIs | No hallucinated or outdated patterns - documentation comes from actual sources |
| Version-Specific | Gets docs for exact library versions you're using |
| Code Examples | Real, working code extracted from actual documentation |
| Broad Coverage | 1000+ libraries including React, Next.js, Vue, Go, Python, Kubernetes, etc. |
Setup
# Install dependencies
cd ~/.claude/skills/context7/Tools
bun install
# Optional: link binaries globally so c7-lookup / c7-resolve / c7-query are on PATH
bun link
# Optional: API key for higher rate limits
export CONTEXT7_API_KEY="ctx7sk_your_key_here" # context7.com/dashboard
Available CLI Tools
| Tool | Purpose | Short form (after bun link) |
Long form |
|---|---|---|---|
lookup |
Resolve + query in one shot | c7-lookup <library> <query> |
bun src/cli/lookup.ts <library> <query> |
resolve |
Find Context7 library ID | c7-resolve <library> [query] |
bun src/cli/resolve.ts <library> [query] |
query |
Query docs by known ID | c7-query <library_id> <query> |
bun src/cli/query.ts <library_id> <query> |
CLI Flags
All three CLIs accept the same flag set.
| Flag | Effect |
|---|---|
--json |
Emit JSON on stdout; suppress decorative output. Pipe to jq. |
--quiet, -q |
Suppress info/success logs (warn/error still print to stderr). |
--no-cache |
Skip the 24h disk cache (~/.cache/context7/resolved.json) for this call. |
--clear-cache |
Wipe the disk cache and exit. |
--timeout <ms> |
HTTP timeout in milliseconds. Default 30000. |
--max-retries <n> |
Retry budget for 429 Rate Limit responses (with Retry-After). Default 1. |
--api-key <key> |
Override CONTEXT7_API_KEY env var. |
--version, -V |
Print version and exit. |
--help, -h |
Print usage and exit. |
What ships with it
18 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.
- Tools/.gitignore 14 B
- Tools/bun.lock 1.2 KB
- Tools/package.json 660 B
- Tools/src/cli/lookup.ts 6.0 KB runs code
- Tools/src/cli/query.ts 3.9 KB runs code
- Tools/src/cli/resolve.ts 5.1 KB runs code
- Tools/src/index.ts 728 B runs code
- Tools/src/lib/cache.ts 2.2 KB runs code
- Tools/src/lib/context7.ts 11 KB runs code
- Tools/src/lib/errors.ts 2.1 KB runs code
- Tools/src/lib/flags.ts 3.0 KB runs code
- Tools/tests/cache.test.ts 2.5 KB runs code
- Tools/tests/errors.test.ts 2.6 KB runs code
- Tools/tests/flags.test.ts 3.1 KB runs code
- Tools/tsconfig.json 477 B
- Workflows/FullLookup.md 2.8 KB
- Workflows/QueryDocs.md 3.2 KB
- Workflows/ResolveLibrary.md 3.3 KB
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.
- 7d ago First seen · 250 lines · 134 tokens per session scan A 4bfa887a3bbf
context7 is a skill published in the GitHub repository julianobarbosa/claude-code-skills (10 stars, last pushed 11d ago), licensed MIT. It adds 134 tokens to every session and 2,883 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
ast-grep
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for…
platform-detection
Identify a .NET project's test platform, framework, command mode, and SDK-style vs classic project system. Use only for "which test platform/framework?", "VSTest or MTP?", or "what runner does this project use?", including bridge settings, UseVSTest opt-outs, and incompatible or conflicting VSTest/MTP configuration.…
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
omh-rust
This is a Hermes-native rust workflow skill.
axiom-concurrency
Use when writing ANY async code, actors, threads, or seeing ANY concurrency error. Covers Swift 6 concurrency, @MainActor, Sendable, data races, async/await patterns.