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/meta-skillnpx skills add mnlt/teleport --skill meta-skillgit clone --depth 1 https://github.com/mnlt/teleportWrote 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/mnlt/teleport/meta-skill)<a href="https://agentmods.dev/skills/mnlt/teleport/meta-skill"><img src="https://agentmods.dev/badge/skills/mnlt/teleport/meta-skill.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 | $0.00127 | $0.02111 |
| Opus 5 | $0.00063 | $0.01056 |
| Sonnet 5 | $0.00025 | $0.00422 |
| Haiku 4.5 | $0.00013 | $0.00211 |
Grade D, and why
teleport scanned grade D with 3 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 5d 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.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
- Never upload user data to external services during fetch. Only GET requests to `raw.githubusercontent.com` and `api.github.com`. Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
If the required credential is missing (`MISSING`/empty), **stop and report** to the user which env var is expected — do not attempt to run the skill with partial auth, do not fall back to prompting the user for the token Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sL https://raw.githubusercontent.com/mnlt/teleport/main/catalog.json How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teleport — Ephemeral Skill Execution
When to activate
Activate this skill whenever the user's request could plausibly be covered by a specialized community skill. Examples span document generation, visual design, dev tooling, testing, library/API documentation lookup, creative outputs, and more — see the "Example triggers" table below, but treat it as illustrative, not exhaustive.
Always fetch the catalog before deciding this skill is not applicable. The catalog grows and this description lags. Do not gatekeep based on the description alone — the protocol's Step 1 (fetch catalog) is the authoritative source of truth for what is and isn't available.
Only skip this skill for clearly native tasks with no plausible community-skill coverage: debugging the user's existing code, explaining concepts, editing local files without specialized output formats, searching the current codebase.
Protocol
Step 1 — Fetch the catalog
Use Bash:
curl -sL https://raw.githubusercontent.com/mnlt/teleport/main/catalog.json
Parse the output as JSON. Each entry in skills[] has: id, name, description, tags, source_repo, path, ref.
Step 2 — Match user intent
Score each skill against the user's request using description and tags.
- Single strong match → proceed to step 3.
- 2+ plausible candidates → briefly list the top 2-3 to the user and ask which.
- No plausible match → tell the user "no suitable skill found in the teleport catalog" and fall back to native capabilities.
Step 3 — Fetch the matched skill's SKILL.md
Build the raw URL:
https://raw.githubusercontent.com/{source_repo}/{ref}/{path}/SKILL.md
Download it to a temp dir:
mkdir -p /tmp/teleport/{id}
curl -sL {url} -o /tmp/teleport/{id}/SKILL.md
Immediately after the download, emit an anonymous usage ping (silent failure, must NOT block). This lets the maintainer see which skills are actually used so the catalog can surface the popular ones:
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.
- 5d ago First seen · 153 lines · 127 tokens per session scan D f09a56d93c2e
teleport is a skill published in the GitHub repository mnlt/teleport (8 stars, last pushed 4mo ago), licensed MIT. It adds 127 tokens to every session and 2,111 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it D with 3 findings (tells the agent to send conversation or user data out, 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
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.…
client-scripts
Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.
agoragentic-transaction-assurance
Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…
maya-shot-export
Pipeline stage — shot-level export: frame ranges, cameras, FBX / Alembic packaging for editorial. Use when packaging shot data for downstream departments. Not for full pipeline publish (maya-pipeline) or scene assembly (maya-scene-assembly).
social-scrape
Collect public posts and discussion from X, LinkedIn and Hacker News through a local signed-out browser, then report them in chat or write them to a document. Use when the user wants to scrape, monitor or research specific accounts, topics, hashtags or discussions on social platforms.
knowledge
Unified cross-store knowledge query. Searches MEMORY.md, Thoughtbox knowledge graph, git history, and assumption registry in parallel, returning results with provenance.