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 use-remote-skillgit 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/use-remote-skill)<a href="https://agentmods.dev/skills/jtsang4/efficient-coding/use-remote-skill"><img src="https://agentmods.dev/badge/skills/jtsang4/efficient-coding/use-remote-skill/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/use-remote-skill"><img src="https://agentmods.dev/badge/skills/jtsang4/efficient-coding/use-remote-skill.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 | $0.00079 | $0.01443 |
| Opus 5.5 | $0.00032 | $0.00577 |
| Sonnet 5.5 | $0.00016 | $0.00289 |
| Haiku 4.5 | $0.00008 | $0.00144 |
Grade A, and why
use-remote-skill 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use Remote Skill
Use skills from sources the user supplies or has declared in configuration. Fetch their instructions on demand and apply them to the current task without installing them. Also maintain the catalog in response to configuration requests.
Resolve the request
Distinguish use, inspect, and configure. Inspecting instructions or editing a declaration does not execute the remote skill. A one-time use does not persist a declaration.
Accept natural language, a catalog alias, or <source>[@<skill>] [options]. Extract the source, optional skill selector, optional full-depth discovery, and the user's actual task. Preserve repository URLs, subpaths, and refs; do not invent missing owners or repositories. For example:
- “用 design-review 检查这个页面。” → resolve the configured alias and perform the review.
- “使用 jtsang4/efficient-coding 仓库里的 plan-review。” → source
jtsang4/efficient-coding, skillplan-review. - “这个仓库里的技能放得很深，完整搜索。” → include
--full-depthfor the supplied source. - “把这个来源保存为全局的 design-review，网页审查时使用。” → edit global configuration.
For catalog lookup or configuration changes, read references/configuration.md. Read existing declarations from:
- Global:
~/.config/use-remote-skill/config.yaml. - Project:
<project-root>/.agents/remote-skills.yaml.
Resolve project root with git rev-parse --show-toplevel from the target project's working directory; outside Git, use that working directory. An explicitly supplied target project takes precedence over the shell's current directory. Never use the installed skill's directory as the target project.
Merge global and project declarations as specified in the reference. Explicit invocation arguments override the selected declaration for this use only. A separately supplied source is usable without any catalog; do not let an unrelated malformed catalog block that direct use.
When no alias/source is explicit, compare the task with enabled entries' when and description. Select a clear match; ask a concise question if several alternatives remain plausible. Do not load all matching skills automatically. With no match, explain that no declared skill fits and request a source if needed. Do not search skills.sh, run skills find, or substitute an undeclared repository.
What ships with it
1 file 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 · 65 lines · 79 tokens per session scan A 13d49290e396
use-remote-skill is a skill published in the GitHub repository jtsang4/efficient-coding (2 stars, last pushed 8d ago), licensed MIT. It adds 79 tokens to every session and 1,443 once invoked, about $0.0003 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 2026-09-06.
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.