What is skill-creator?

A guide for creating and maintaining skills, which are reusable instructions loaded only for relevant tasks. It treats skills as focused procedures rather than permanent global prompts.

Use it when creating, updating, pruning, or validating an agent skill. It helps turn repeated failures into scoped workflows and check them against skill specifications and primary sources.

It helps avoid duplicating skills, putting task-specific rules in global instructions, or encoding lessons without checking their source. It provides checks for deciding whether a skill should be created, updated, or removed.

skill-creator — Skill for Claude Code and Codex by companion-inc

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/companion-inc/introspect

agentmods

npx agentmods add skills/companion-inc/introspect/skill-creator

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/companion-inc/introspect/skill-creator/github.svg)](https://agentmods.dev/skills/companion-inc/introspect/skill-creator)

Your own site

<a href="https://agentmods.dev/skills/companion-inc/introspect/skill-creator"><img src="https://agentmods.dev/badge/skills/companion-inc/introspect/skill-creator/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/companion-inc/introspect/skill-creator"><img src="https://agentmods.dev/badge/skills/companion-inc/introspect/skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,418 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.

Model	Per session	Once invoked
Fable 5.1	$0.00059	$0.01418
Opus 5.5	$0.00024	$0.00567
Sonnet 5.5	$0.00012	$0.00284
Haiku 4.5	$0.00006	$0.00142

Measured 2mo ago against content hash 66a311aaee3c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skill-creator 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 2mo 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.

skills/skill-creator/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill creator

Core rule

A skill is not a second global prompt. It is scoped procedural memory: a compact, source-backed workflow that loads only when the task needs it.

Create or update a skill only when the lesson is reusable for a class of future tasks and too specific for always-loaded AGENTS.md. Prune a skill when evidence shows it is stale, overbroad, duplicative, or causing bad behavior. If the lesson must apply across nearly every task, edit AGENTS.md instead. If it is one-off anger, casual profanity, or trigger about an external system, make no change.

Source gate

Before writing a new skill or materially changing one:

Read the failure transcript/event that triggered the change.
Read skills/index.json and the closest existing skills/*/SKILL.md; update instead of duplicating when there is a close fit.
Read references/source-map.md in this skill, then open the primary sources relevant to the change.
Read the primary source for the skill format or behavior being encoded:
- Agent Skills specification: https://agentskills.io/specification
- OpenAI Codex Skills docs: https://developers.openai.com/codex/skills
- OpenAI API Skills docs: https://developers.openai.com/api/docs/guides/tools-skills
- Claude Agent Skills overview: https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview
- Anthropic public skills repository: https://github.com/anthropics/skills
- Anthropic skill-creator reference: https://github.com/anthropics/skills/blob/main/skills/skill-creator/SKILL.md
- Agent Skills best practices: https://agentskills.io/skill-creation/best-practices
- Agent Skills description optimization: https://agentskills.io/skill-creation/optimizing-descriptions
- Agent Skills eval guidance: https://agentskills.io/skill-creation/evaluating-skills
For self-evolving skill curation, read the research source that matches the operation:
- SAGE / skill library agents: https://arxiv.org/html/2512.17102v2
- SkillOS / skill curation: https://arxiv.org/html/2605.06614v1
- SkillRL / recursive skill evolution: https://github.com/aiming-lab/SkillRL
For domain behavior inside the skill, cite actual domain sources: repo files, docs, logs, APIs, papers, issues, or command output. Do not encode generic model folklore as a rule.
If no source supports the lesson, write nothing and log why.

Read the full file on GitHub · 99 lines

Files

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.

references/source-map.md 9.0 KB

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.

2mo ago First seen · 99 lines · 59 tokens per session scan A 66a311aaee3c

Subscribe to this mod's changes

skill-creator is a skill published in the GitHub repository companion-inc/introspect (10 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 1,418 once invoked, about $0.0002 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 2026-08-31.

Building agents

skill-creator next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
skill-creatorcompanion-inc/introspect	Skill	10	2mo ago	MIT	A	59	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code