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/mnlt/teleport/context7npx skills add mnlt/teleport --skill context7git clone --depth 1 https://github.com/mnlt/teleportWhat 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 | $0.00079 | $0.01926 |
| Opus 5 | $0.00039 | $0.00963 |
| Sonnet 5 | $0.00016 | $0.00385 |
| Haiku 4.5 | $0.00008 | $0.00193 |
Grade B, and why
context7 scanned grade B with 2 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Do NOT suggest editing `~/.claude/settings.local.json` manually.** Stop execution until the user has run the command and restarted. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sL -H "Authorization: Bearer $CONTEXT7_API_KEY" \ How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context7
Live documentation lookup for libraries, frameworks, and SDKs. Operates Context7 via its public REST API — no MCP server required.
Use this instead of training memory whenever the answer depends on the library's current behavior (current major version, recent API changes, new methods, deprecations). Training data goes stale fast for active libraries.
When to use vs. skip
| Use Context7 | Skip Context7 |
|---|---|
| "How do I do X in Next.js 15 / React 19 / Prisma 6?" | "What's a closure in JavaScript?" (language concept) |
| "What's the right way to set up Auth.js v5 middleware?" | "Fix this TypeError in my code" (debugging user's own code) |
| "Did the Supabase client API change for storage uploads?" | "Convert this loop to a map" (pure refactor, no SDK) |
| Anything where you'd otherwise hedge with "as of my training cutoff…" | Std-lib (fs, os, collections) unless asking about a recent runtime version |
If you catch yourself about to write code from memory for a library that's released in the last 18 months, stop and call this skill first.
Credentials check
[ -n "$CONTEXT7_API_KEY" ] && echo "CONTEXT7_API_KEY: PRESENT" || echo "CONTEXT7_API_KEY: MISSING"
Never echo the variable directly — the value would land in the conversation transcript.
If MISSING, respond to the user with EXACTLY this message (do NOT paraphrase, do NOT suggest manual JSON edits):
I need your context7 credential. Run this in another terminal — it'll open the signup page, validate format, and save it safely with masked input:
teleport-setup add-key context7Then restart Claude Code (
/exit, thenclaude) and ask me again.
Do NOT suggest editing ~/.claude/settings.local.json manually. Stop execution until the user has run the command and restarted.
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.
- 3d ago First seen · 137 lines · 79 tokens per session scan B f482fb72c822
context7 is a skill published in the GitHub repository mnlt/teleport (9 stars, last pushed 4mo ago), licensed MIT. It adds 79 tokens to every session and 1,926 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
xcodebuildmcp-structured-output-review
Use when reviewing XcodeBuildMCP structured output schema changes, schema versioning, manifest outputSchema metadata, and JSON fixture compatibility.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
cortex-automate
Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…
tabnexus-mcp-evals
Generate, validate, and run isolated Codex-to-TabNexus MCP evaluations with a curated 600-query dataset, executable gold tool labels, safety checks, and best-of-three stability scoring. Use when testing TabNexus MCP tool coverage, Agent behavior, regression quality, destructive-action safety, prompt changes, or a…
compare
Structured comparison of 2+ alternatives with consistent criteria and decision matrix.
concept-synthesis
Deduplicate and synthesize raw concept stubs into a tiered intellectual map (T1 Canon to T4 Riff), tracing idea evolution across sources over time. Transforms thousands of raw concept pages into a curated intellectual fingerprint.