It is for writing skills from scratch, improving their descriptions and behavior, and running performance evaluations.

It helps turn repeated instructions into reusable skills and check whether those skills work reliably.

skill-creator — Skill for Claude Code and Codex by zebbern: A skill for creating, editing, and evaluating coding-agent 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.

agentmods

npx agentmods add skills/zebbern/termstack/skill-creator

Any agent

npx skills add zebbern/termstack --skill skill-creator

Clone the repo

git clone --depth 1 https://github.com/zebbern/termstack

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/zebbern/termstack/skill-creator.svg)](https://agentmods.dev/skills/zebbern/termstack/skill-creator)

Your own site

<a href="https://agentmods.dev/skills/zebbern/termstack/skill-creator"><img src="https://agentmods.dev/badge/skills/zebbern/termstack/skill-creator.svg" alt="Measured on agentmods" height="20"></a>

Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 7,292 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin unknown 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	$0.00064	$0.07292
Opus 5	$0.00032	$0.03646
Sonnet 5	$0.00013	$0.01458
Haiku 4.5	$0.00006	$0.00729

Measured 2d ago against content hash 33567f0a43f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 2d ago.

The scan reads SKILL.md. This mod also ships 10 executable files (eval-viewer/generate_review.py, scripts/__init__.py, scripts/aggregate_benchmark.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.github/skills/skill-creator/SKILL.md · 498 lines

The source is not reproduced here

No licence file

Read it on GitHub

Files

What ships with it

35 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.

2d ago First seen · 498 lines · 64 tokens per session scan A 33567f0a43f1

Subscribe to this mod's changes

skill-creator is a skill published in the GitHub repository zebbern/termstack (5 stars, last pushed 4mo ago), with no licence file. It adds 64 tokens to every session and 7,292 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 2026-09-03.

Building agents GLM agloop ai claude claude-code codex-cli coding-agent creation development measurement skill

optim-agent

Use when the user wants to optimize configurable system parameters against a measurable scalar objective, especially for model training, inference, quantitative strategies, reinforcement learning, scientific workflows, or other expensive black-box evaluations where reading the project can improve trial selection.

Optim-Agent/optim-agent · 50 tokens

auto-devflow

Use when starting an issue, bugfix, feature, or refactor that benefits from an adaptive development workflow. Select lite, normal, pro, max, or ultra from task complexity and risk, then use only the coordination, review, and verification phases that the task actually needs.

KonghaYao/peri · 60 tokens

ultra-adlc

End-to-end delivery orchestration for explicitly requested, very large software changes that must be completely implemented and independently proven. Use when the user invokes "ultra-adlc" or asks for an Ultra-ADLC-scale full delivery; do not use for ordinary features, small fixes, reviews, or ad hoc parallel work.

KonghaYao/peri · 69 tokens

langfuse

Interact with Langfuse and access its documentation. Use when needing to (1) query or modify Langfuse data programmatically via the CLI — traces, prompts, datasets, scores, sessions, and any other API resource, (2) look up Langfuse documentation, concepts, integration guides, or SDK usage, or (3) understand how any…

KonghaYao/peri · 100 tokens

heavy-verify-loop

Runs a user-level verification and repair loop against the real Peri TUI using ./dev.sh, tmux, logs, E2E helpers, and Advisor/Coder/Reviewer subagents. Use when a feature must be exercised as a real user and repeatedly repaired until fresh end-to-end evidence shows no blocking problems.