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 jtsang4/efficient-coding --skill paseo-relaygit clone --depth 1 https://github.com/jtsang4/efficient-codingWrote 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/jtsang4/efficient-coding/paseo-relay)<a href="https://agentmods.dev/skills/jtsang4/efficient-coding/paseo-relay"><img src="https://agentmods.dev/badge/skills/jtsang4/efficient-coding/paseo-relay/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/jtsang4/efficient-coding/paseo-relay"><img src="https://agentmods.dev/badge/skills/jtsang4/efficient-coding/paseo-relay.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00056 | $0.01225 |
| Opus 5.5 | $0.00022 | $0.00490 |
| Sonnet 5.5 | $0.00011 | $0.00245 |
| Haiku 4.5 | $0.00006 | $0.00122 |
Grade A, and why
paseo-relay 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paseo Relay
Use the local paseo CLI to operate the daemon on the selected host. Relay is the network connection. Start with observation; inspecting a session does not authorize sending it a prompt, resuming, stopping, reloading, restarting, archiving, or detaching it.
1. Establish the host and connection
Record the local host, the intended remote host, and the authorized operation. Discover the installed CLI with command -v paseo, paseo --version, and command-specific --help. A host's display label is neither its SSH address nor sufficient connection information.
Read connection.md to obtain or reuse a pairing offer. The workable starting points are:
- An offer URL supplied privately by the user or stored in their explicitly authorized connection file.
- An already authorized connection to that daemon, through which Paseo can return its offer.
- Access to the target machine or its operator for first pairing. Relay must already be enabled, or enabling it must be authorized.
An offer contains the target serverId, Relay endpoint/TLS setting, and daemon public key. Use Paseo's parser and encrypted Relay transport. Keep connection materials outside the repository and out of command arguments, transcripts, and shared logs.
CLI 0.8.0 accepts an offer URL through PASEO_HOST or --host, although its help lists tcp/ssh. Prefer PASEO_HOST loaded from a private file. Verify the selected daemon's serverId and advertised hostname before choosing its resources. Some bundled 0.8.0 builds ignore the remote target for daemon status and return local status. If that command cannot prove the remote identity, use the small SDK identity check in sdk.md. Do not substitute local status for a remote handshake.
Keep subsequent commands in that same target environment. Treat (serverId, workspaceId) and (serverId, agentId) as the identifiers. Use full IDs obtained from this host; CLI prefix/title matching can select an unintended session.
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.
- 1mo ago First seen · 64 lines · 56 tokens per session scan A 13c8290a8852
paseo-relay is a skill published in the GitHub repository jtsang4/efficient-coding (2 stars, last pushed 8d ago), licensed MIT. It adds 56 tokens to every session and 1,225 once invoked, about $0.0002 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 2026-09-16.
Other skills, from other repositories
plugin-creator
Create and scaffold plugin directories for Codex with a required .codex-plugin/plugin.json, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries…
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.