skill-authoring-lifecycle

skill-authoring-lifecycle is a skill for Claude Code from Arenukvern/skill_steward. It costs 55 tokens per session (1,692 once invoked), scanned B, original, MIT.

A lifecycle for creating and formally reviewing installable Agent Skills in a marketplace repository.

In plain words
What is it for?
Use it to add a new skill, check SKILL.md front matter, choose supporting files, audit a skill, and prepare it for marketplace publication.
Why use it?
It reduces errors in skill structure, metadata, registry entries, and compatibility with the Agent Skills specification.

Skill for Claude Code

Written for Claude Code: paths in frontmatter. Also seen: mentions subagents; mentions Codex.

Part of the skill-steward plugin — 15 skills shipped together

Good fit Use it to add a new skill, check SKILL.md front matter, choose supporting files, audit a skill, and prepare it for marketplace publication.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arenukvern/skill_steward/skill-authoring-lifecycle
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 Arenukvern/skill_steward --skill skill-authoring-lifecycle
Clone the repo
git clone --depth 1 https://github.com/Arenukvern/skill_steward

Made for: Claude Code.

Or install skill-steward, the plugin that ships this one along with the rest of its 15 skills.

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 skill-authoring-lifecycle

README.md
[![agentmods](https://agentmods.dev/badge/skills/arenukvern/skill_steward/skill-authoring-lifecycle/github.svg)](https://agentmods.dev/skills/arenukvern/skill_steward/skill-authoring-lifecycle)
Your own site
<a href="https://agentmods.dev/skills/arenukvern/skill_steward/skill-authoring-lifecycle"><img src="https://agentmods.dev/badge/skills/arenukvern/skill_steward/skill-authoring-lifecycle/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 skill-authoring-lifecycle

Your own site · 80×15
<a href="https://agentmods.dev/skills/arenukvern/skill_steward/skill-authoring-lifecycle"><img src="https://agentmods.dev/badge/skills/arenukvern/skill_steward/skill-authoring-lifecycle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,692 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00055 $0.01692
Opus 5 $0.00028 $0.00846
Sonnet 5 $0.00011 $0.00338
Haiku 4.5 $0.00006 $0.00169

Measured 10d ago against content hash 86e83614ab46, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

skill-authoring-lifecycle scanned grade B with 1 finding 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 10d 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

1. Safely `rm -rf` the old skill directory.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/skill-authoring-lifecycle/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill authoring lifecycle

Add, review, and validate an installable skill package under skills/ in the Skill Steward marketplace.

When to use

  • User wants a new skill in this repo
  • "Review this skill" or "Is this SKILL.md valid?"
  • Bootstrapping SKILL.md for npx skills compatibility
  • PR touches skills/*/SKILL.md

Phase 1: Creation Workflow

  1. Verify intent — Does the intent overlap with an existing skill? Merge into an existing skill if they serve the same high-level goal or are two halves of the same lifecycle (ADR 0016).
  2. Collect examples — Write 2–3 concrete user prompts that should trigger the skill and 1 prompt that should not. Skip only when the request already supplies clear usage patterns.
  3. Plan resources — Decide whether the skill needs instructions only, scripts/ for repeated or fragile operations, references/ for detailed knowledge, or assets/ for templates/static files.
  4. Choose a namekebab-case, 1–64 chars, matches Agent Skills rules (see docs/STANDARDS.mdx).
  5. Create directoryskills/{name}/ (directory name must equal name in frontmatter).
  6. Copy template — from templates/skill/SKILL.md; replace placeholders.
  7. Write description — one concise block covering what and when (trigger phrases users say). Activation-critical routing belongs here, not only in a body "When to use" section.
  8. Cite sources — create references/sources.md from templates/skill/references/sources.md; add rows for every spec/repo/paper used.
  9. Write body — numbered steps, examples, output format; keep under 500 lines.
  10. Evals — T1 behavior-critical skills (see STANDARDS): references/evals.md + ≥2 evals/cases/*.yaml. Others: optional evals.md.
  11. Optional metadata — add agents/openai.yaml only when Codex app UI metadata, invocation policy, or tool dependencies are useful.
  12. Optional resources — create only the needed scripts/, references/, and assets/ directories; delete placeholder resources.
  13. Register skill:
  • Add skill id to skills.sh.json using the current repo schema.
  • Add row to root README.md skill table.
  1. Forward-test tricky skills — For broad or fragile workflows, use a fresh subagent/thread with a natural user prompt and raw artifacts. Do not leak the intended answer, suspected bug, or planned fix into the validation prompt.

Read the full file on GitHub · 146 lines

Files

What ships with it

6 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. 10d ago First seen · 146 lines · 55 tokens per session scan B 86e83614ab46

Subscribe to this mod's changes

skill-authoring-lifecycle is a skill published in the GitHub repository Arenukvern/skill_steward (11 stars, last pushed 25d ago), licensed MIT. It adds 55 tokens to every session and 1,692 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.