writing-skills

writing-skills is a skill for Claude Code, Codex from rundesk-ai/rundesk-cli. It costs 60 tokens per session (1,716 once invoked), scanned A, original, MIT.

A guide and workflow for creating, changing, reviewing, testing, and publishing reusable Rundesk skills. A skill is a set of instructions that tells an agent when and how to act.

In plain words
What is it for?
Use it when building a reusable agent workflow, adding scripts or outside-service connections, or preparing a skill for publication.
Why use it?
It helps avoid overlapping skills and makes sure a new skill has the right instructions, checks, and catalog entry.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when building a reusable agent workflow, adding scripts or outside-service connections, or preparing a skill for publication.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rundesk-ai/rundesk-cli/writing-skills
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.

Any agent
npx skills add rundesk-ai/rundesk-cli --skill writing-skills
Clone the repo
git clone --depth 1 https://github.com/rundesk-ai/rundesk-cli

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for writing-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/rundesk-ai/rundesk-cli/writing-skills/github.svg)](https://agentmods.dev/skills/rundesk-ai/rundesk-cli/writing-skills)
Your own site
<a href="https://agentmods.dev/skills/rundesk-ai/rundesk-cli/writing-skills"><img src="https://agentmods.dev/badge/skills/rundesk-ai/rundesk-cli/writing-skills/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.

agentmods 80×15 button for writing-skills

Your own site · 80×15
<a href="https://agentmods.dev/skills/rundesk-ai/rundesk-cli/writing-skills"><img src="https://agentmods.dev/badge/skills/rundesk-ai/rundesk-cli/writing-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,716 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00060 $0.01716
Opus 5 $0.00030 $0.00858
Sonnet 5 $0.00012 $0.00343
Haiku 4.5 $0.00006 $0.00172

Measured 11d ago against content hash e0df3af97e69, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

writing-skills 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 11d 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/writing-skills/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing skills

Reuse the existing owner

Inspect existing skill catalogs before creating a package. For repository work, search the target catalog and every relevant source catalog in the authorized workspace. For authorized live-library work, use Rundesk's catalog and skill listings; do not open the live library to bypass the task's access boundary. Read the descriptions of plausible matches, then their bodies and relevant references before deciding.

Extend the existing owner when the requested capability shares its user intent, workflow, and authority. Add a supporting script, reference, or test there instead of creating a second routing surface. Create a new skill only when the capability needs distinct routing, judgment, authority, or proof; record that distinction so a nearby name is not treated as justification by itself.

Choose the artifact

  • A skill is the instruction boundary: when to act, what judgment to apply, which procedure to follow, and how to prove the outcome.
  • A workflow script is the deterministic mechanism for repeated local transformation, validation, or orchestration.
  • An integration adds an external-service boundary: credentials, accounts, network failures, permissions, or remote effects.

Keep one-off automation in its project and one agent's private repeated command in that agent's scripts area. Package a script in a skill only when future turns need routing or judgment to use it. Do not replace deterministic code with prose an agent must reinterpret.

Read Reusable workflow scripts before shipping any reusable script. Also read External-service integrations when it uses credentials, profiles, OAuth, a network, or remote effects.

Place it safely

Create a private skill in local only when live creation or installation is authorized. For a draft, review, repository change, or isolated test, stay in the named workspace or temporary directory; do not inspect or change the live library to discover where the result might later go.

Read the full file on GitHub · 156 lines

Files

What ships with it

3 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.

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. 11d ago First seen · 156 lines · 60 tokens per session scan A e0df3af97e69

Subscribe to this mod's changes

writing-skills is a skill published in the GitHub repository rundesk-ai/rundesk-cli (6 stars, last pushed 7d ago), licensed MIT. It adds 60 tokens to every session and 1,716 once invoked, about $0.0003 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.