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/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.
<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="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.5 | $0.00054 | $0.01153 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 (14 stars, last pushed 11d ago), licensed MIT. It adds 134 tokens to every session and 2,883 once invoked, about $0.0005 per session on Opus 5.5. 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
erlang-otp-behaviors
Use when oTP behaviors including genserver for stateful processes, genstatem for state machines, supervisors for fault tolerance, genevent for event handling, and building robust, production-ready Erlang applications with proven patterns.
omh-rust
This is an OMH rust workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
axiom-concurrency
Use when writing ANY async code, actors, or threads in an Apple-platform app, or seeing ANY concurrency error. Covers Swift 6 concurrency, @MainActor, Sendable, data races, async/await patterns.
haskell-pro
Expert Haskell engineer specializing in advanced type systems, pure functional design, and high-reliability software. Use PROACTIVELY for type-level programming, concurrency, and architecture guidance.
splitting-oversized-modules
Split an oversized Python module (a thousand-plus-line logic.py, models.py, api.py, or its test file) into a package of one module per concern, mechanically and provably without changing behavior. Use on a request to split / break up / decompose a god module or move functions out of one, once a human has agreed to…
migrate-better-result-3
Migrate a TypeScript codebase from better-result 2.x to 3.0. Use when upgrading better-result across the TaggedError syntax, removed Result serialization helpers, recovery inference, matching, or retry APIs.