new-skill

A workflow for scaffolding a new custom skill, meaning a reusable instruction file that an agent can run for a particular kind of task.

In plain words
What is it for?
It is for designing and creating a new `SKILL.md` or slash command after gathering its purpose, name, access needs, and invocation rules.
Why use it?
It turns a loose idea into a defined command with a name, activation rules, permitted tools, and step-by-step behavior.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/zjshen14/opencli/new-skill
Any agent
npx skills add zjshen14/opencli --skill new-skill
Clone the repo
git clone --depth 1 https://github.com/zjshen14/opencli

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 606 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00028 $0.00606
Opus 5 $0.00014 $0.00303
Sonnet 5 $0.00006 $0.00121
Haiku 4.5 $0.00003 $0.00061

Measured 2d ago against content hash a7a1d1e2f16c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

new-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 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.

src/skills/builtin/new-skill/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create a new custom skill for this project.

What to build: $ARGUMENTS

Steps

  1. Gather requirements — If $ARGUMENTS is empty, ask the user:

    • What should the skill do?
    • What slash command name should invoke it (short, kebab-case, e.g. deploy, summarise-pr)?
    • Should only the user be able to invoke it, or can the model also self-activate it?
  2. Design the skill:

    • name: short kebab-case identifier matching the slash command
    • description: one precise, verb-led sentence (e.g. "Run …", "Generate …", "Analyse …") — the model uses this for auto-activation, so specificity matters
    • allowed-tools: space-separated, limited to what the skill genuinely needs (Read, Write, Edit, Glob, Grep, Bash)
    • disable-agent-invocation: set true for side-effectful or destructive skills (deploy, commit, send messages); omit for general-purpose skills
    • Body: numbered step-by-step instructions the model follows; reference $ARGUMENTS for the user-supplied target
    • Preprocessors: add !{cmd || echo "fallback"} only when useful context should be captured at activation time (e.g. current git branch, project config); always include a fallback
  3. Show the complete draft SKILL.md to the user and ask for approval or edits before writing anything.

  4. Write the file to .opencli/skills/<name>/SKILL.md using the write tool — it will prompt for confirmation before touching the filesystem.

  5. Confirm success:

    • Report the exact path written
    • Remind the user the skill is discoverable after restarting the session (invoke with /<name> [args])

SKILL.md format reference

---
name: <kebab-case-name>
description: <one sentence — verb-led, specific enough for auto-activation>
allowed-tools: <space-separated: Read Write Edit Glob Grep Bash>
# disable-agent-invocation: true   # uncomment for user-only or dangerous skills
---

<Step-by-step instructions. Use $ARGUMENTS for the user's input.>
<Optional: !{cmd || echo "fallback"} for context injected at activation time.>

Read the full file on GitHub · 51 lines

Changes

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.

  1. 2d ago First seen · 51 lines · 28 tokens per session scan A a7a1d1e2f16c

Subscribe to this mod's changes

new-skill is a skill published in the GitHub repository zjshen14/opencli (2 stars, last pushed 10d ago), licensed MIT. It adds 28 tokens to every session and 606 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

ppt-generation

Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Creates visually rich slides by generating images for each slide and composing them into a PowerPoint file.

bytedance/deer-flow · 44 tokens

smoke-test

End-to-end smoke test skill for DeerFlow. Guides through: 1) Pulling latest code, 2) Docker OR Local installation and deployment (user preference, default to Local if Docker network issues), 3) Service availability verification, 4) Health check, 5) Final test report. Use when the user says "run smoke test", "smoke…

bytedance/deer-flow · 0 tokens

podcast-generation

Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.

bytedance/deer-flow · 38 tokens

github-deep-research

Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams.…

bytedance/deer-flow · 68 tokens

vercel-deploy

Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.

bytedance/deer-flow · 69 tokens

skill-reviewer

Reviews DeerFlow skill packages for readiness, triggers, safety boundaries, resources, and evidence. Invoke when users ask to audit, grade, or production-check an existing skill.

bytedance/deer-flow · 38 tokens