skill-authoring

skill-authoring is a skill for Claude Code, Codex from aksika/abtars. It costs 24 tokens per session (1,535 once invoked), scanned B, original, Apache-2.0.

A guide for creating, revising, and removing reusable skills, which are saved procedures an agent can follow again later. It also explains when to store a fact or preference as memory instead.

In plain words
What is it for?
Use it to design a new skill, improve an existing procedure, decide between a skill and stored memory, or remove an obsolete skill.
Why use it?
It prevents one-off conversation details from being mistaken for reusable instructions. It also helps avoid duplicate skills and keeps private information out of them.

Skill for Claude CodeCodex

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

Good fit Use it to design a new skill, improve an existing procedure, decide…

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

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 skill-authoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/aksika/abtars/skill-authoring.svg)](https://agentmods.dev/skills/aksika/abtars/skill-authoring)
Your own site
<a href="https://agentmods.dev/skills/aksika/abtars/skill-authoring"><img src="https://agentmods.dev/badge/skills/aksika/abtars/skill-authoring.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,535 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00024 $0.01535
Opus 5 $0.00012 $0.00767
Sonnet 5 $0.00005 $0.00307
Haiku 4.5 $0.00002 $0.00153

Measured 7d ago against content hash ea6805cc6196, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

skill-authoring scanned grade B with 2 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 7d 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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- After every change, reload and inspect the catalog. Run any scripts or commands needed to verify the changed procedure.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

bins: [jq, curl]
templates/skills/skill-authoring/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Authoring

Store reusable procedures as skills. Store facts, events, and preferences with memory_store.

Choose the right persistence

Use a skill when the knowledge explains how to do something and is likely to help again, especially when the procedure is multi-step, error-prone, or corrected by the user.

Use memory_store when the knowledge records what is true: a fact, event, decision, or preference. Do not create a skill for one conversation's outcome.

Never put credentials, tokens, private user data, or conversation transcripts in a skill. Declare required environment-variable names, not their values.

Authoring workflow

  1. Search ~/.abtars/skills/skills_catalog.md for an existing skill that already covers the procedure. Improve it instead of creating a duplicate.
  2. Choose a lowercase kebab-case name, 3-64 characters, with no leading or trailing hyphen.
  3. Write a specific description (1-120 characters) that says what the skill does and when it applies. The catalog uses this text to select skills.
  4. Keep the body procedural and imperative. Include prerequisites, ordered actions, failure handling, and a concrete verification step only when they add real value.
  5. Create the skill with skill_create. Pass only the Markdown body in content; the tool writes frontmatter.
  6. Run /skill reload, then confirm the skill appears in skills_catalog.md with the expected name and description.

skill_create writes ~/.abtars/skills/self/<skill-name>/SKILL.md. Its body must be 100-50,000 UTF-8 bytes. Prefer a concise body; move substantial supporting material into references/.

Skill shape

<skill-name>/
├── SKILL.md            # required: metadata and instructions
├── skill.json          # only for a persistent interactive skill
├── scripts/            # optional deterministic helpers
└── references/         # optional detailed guidance

A typical generated file has:

---
name: inspect-service-logs
description: Diagnose a failing service from its logs; use for startup failures and repeated crashes.
tags: [debugging, services]
related: [troubleshooting]
---

# Inspect Service Logs

1. Capture the first error and its surrounding context.
2. Trace it to the component that emitted it.
3. Verify the diagnosis by reproducing the failure or checking runtime state.

Read the full file on GitHub · 147 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. 7d ago First seen · 147 lines · 24 tokens per session scan B ea6805cc6196

Subscribe to this mod's changes

skill-authoring is a skill published in the GitHub repository aksika/abtars (9 stars, last pushed 2d ago), licensed Apache-2.0. It adds 24 tokens to every session and 1,535 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (unrestricted tool access, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.