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/melodic-software/claude-code-plugins/lookupnpx skills add melodic-software/claude-code-plugins --skill lookupgit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWhat 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 | $0.00153 | $0.01767 |
| Opus 5 | $0.00077 | $0.00883 |
| Sonnet 5 | $0.00031 | $0.00353 |
| Haiku 4.5 | $0.00015 | $0.00177 |
Grade A, and why
lookup 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 2d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-computed context
Installed CLI version: !ctx7 --version 2>/dev/null || echo "not installed (run: npm install -g ctx7@latest)"
MCP availability: check your own tool list. If mcp__context7__resolve-library-id / mcp__context7__query-docs are present, the MCP path is configured.
Purpose
A primary source of up-to-date library documentation. Two equivalent interfaces: CLI (ctx7) via npm, and the Context7 HTTP MCP server (mcp__context7__*) when the consuming project has it configured. Both read the same backend. Pick by workflow (see When to use CLI vs MCP).
Philosophy: training data is stale by the time you use it. Library APIs, framework defaults, best practices change. Before claiming how a library works, verify against Context7, even for libraries you "know."
Actions
| Action | When | Loads |
|---|---|---|
lookup <library> <query> (default) |
User asks about a library | context/lookup.md |
update |
Drift check + CLI upgrade + upstream skill changes | context/update.md |
If the argument is bare (no action keyword), treat as lookup.
First-time setup covers CLI install, CONTEXT7_API_KEY auth, optional MCP server wiring, and the Windows Git Bash gotcha. It lives in its own skill: run /context7:setup.
Lookup (happy path)
Two-step: resolve library name → fetch docs with resolved ID.
# Step 1: name → Context7 library ID
ctx7 library "<name>" "<question>"
# Step 2: ID → docs (Windows Git Bash: prefix with MSYS_NO_PATHCONV=1 — see context/cli.md)
MSYS_NO_PATHCONV=1 ctx7 docs "<libraryId>" "<question>"
Equivalent via MCP when the consuming project has the Context7 MCP server configured (no Windows gotcha, cleaner output, returns ~1.5-2× more content):
mcp__context7__resolve-library-id(libraryName: "...", query: "...")
mcp__context7__query-docs(libraryId: "/org/project", query: "...")
You MUST call library / resolve-library-id first to get a valid ID, UNLESS the user provides one in /org/project format. One concept per query. When a question spans several independent topics, run a separate lookup per topic. Do not run more than 3 lookup commands per topic. If you cannot find what you need, fall back to training knowledge and tell the user Context7 didn't cover it.
What ships with it
9 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.
- 2d ago First seen · 105 lines · 153 tokens per session scan A 351e7c248c3c
lookup is a skill published in the GitHub repository melodic-software/claude-code-plugins (12 stars, last pushed 2d ago), licensed MIT. It adds 153 tokens to every session and 1,767 once invoked, about $0.0008 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
deep-research
Conducts iterative deep research on any topic using web search, progressive exploration, and structured synthesis. Use when asked for comprehensive research, deep investigation, thorough analysis, or multi-source exploration of any topic. Triggers: research, investigate, deep dive, comprehensive analysis, explore…
error-ux
Principles and patterns for writing error messages that help users recover. Use when auditing, writing, or improving error messages in code. Triggers: error messages, user experience, error handling, exception messages, validation errors.
adversarial-patterns
Library of realistic adversarial attack vectors and anti-patterns to avoid. Contains examples of valid attacks and subtle gaming patterns to reject.
documentation-testing
Provides heuristics for identifying incomplete or broken documentation. Use when validating README setup instructions, testing onboarding flows, or auditing documentation quality. Triggers: docs, readme, onboarding, setup validation, documentation audit.
adversarial-analysis
Analyze code to identify explicit contracts, implicit usage patterns, and realistic boundary conditions. Contains concrete formulas for calculating input realism limits. Use before generating adversarial tests.
propagate-then-search
For constraint problems: eliminate impossibilities before guessing, reduce search space through inference, fail fast on contradictions.