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.
npx agentmods add skills/stippi/code-assistant/skill-creatornpx skills add stippi/code-assistant --skill skill-creatorgit clone --depth 1 https://github.com/stippi/code-assistantWhat 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 | $0.00047 | $0.00929 |
| Opus 5 | $0.00023 | $0.00464 |
| Sonnet 5 | $0.00009 | $0.00186 |
| Haiku 4.5 | $0.00005 | $0.00093 |
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.
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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
A skill is a reusable, task-specific playbook stored as a SKILL.md file in a
directory named after the skill. Skills are advertised in the system prompt by
name + description (progressive disclosure); their full instructions are loaded
on demand with the read_skill tool.
Use this skill whenever the user asks to create, author, or improve a skill.
1. Choose a scope
A skill lives in one of three scopes. Pick based on how widely it should apply:
- project —
<project_root>/.agents/skills/<name>/— specific to one repo. Load withread_skill(project="<project-name>", name="<name>"); read its resources withread_files(project="<project-name>", ...). - user —
~/.agents/skills/<name>/— your personal skills, available in every project (and shared with other agent harnesses). Addressed by the scope token:config:; load withread_skill(project=":config:", ...). - system — token
:system:— bundled skills (like this one). Usually read-only.
On a name collision, project wins over user wins over system.
2. Write SKILL.md
The file MUST start with a YAML frontmatter block delimited by --- lines,
followed by a free-form Markdown body:
---
name: my-skill
description: One-paragraph routing description the model uses to decide when to load this skill.
---
# My Skill
...instructions...
Frontmatter rules (enforced by the loader):
nameis required, must be lowercase letters, digits, and hyphens only, at most 64 characters, and must equal the directory name.descriptionis required, at most 1024 characters. Write it as a routing signal: say when to use the skill, not just what it does.disable-model-invocation(optional, defaultfalse): whentrue, the skill is hidden from the model-facing catalog and thelist_skillstool so the model never auto-invokes it. It stays loadable viaread_skill(e.g. when a user explicitly activates it) and visible in the settings UI. Use this for skills that should only run on explicit user request.- Other keys (license, allowed-tools, metadata, etc.) are allowed and ignored for now.
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 · 109 lines · 47 tokens per session scan A 36442654d18a
skill-creator is a skill published in the GitHub repository stippi/code-assistant (179 stars, last pushed 5d ago), licensed MIT. It adds 47 tokens to every session and 929 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
omd-video
视频→逐段结构化笔记 (MiMo-v2.5 原生吃画面+音频, 非 whisper 转写; 可重入管线)。讲解/课程视频里 PPT 框架图/代码/提示词是画面独有、音频拿不到的信息。产 ALL-NOTES.md 交 /omd-council 或 dagresearch 做综合。Trigger:/omd-video、抖音/B站/YouTube 讲解视频、课程系列、把这些视频学一遍/提炼、画面里有代码/图表/PPT。Skip:文字原文综合→/omd-council;网页内容→dagresearch(检索版)。.
omd-recall
主动召回 omd 自记忆:推理/写作/决策卡住时主动查既有事实,不等被动触发。经 memoryrecall 语义+词法混合检索,回带 confidence + source。Trigger:/omd-recall、查历史、以前怎么做的、翻一下记忆、有没有先例。.
testing-course-samples
Use when asked to validate, test, smoke-test, or run the course's notebook and code samples against a live Microsoft Foundry / Azure OpenAI configuration. Covers environment setup (.env, az login, packages), the scripts/validate-notebooks.ps1 runner, interpreting PASS/FAIL results, and which lessons need extra…
docs-writer
Draft or rewrite Strands Agents documentation pages. Use when writing new doc pages, rewriting pages that failed audit, drafting sections for existing pages, or writing blog posts and release notes about Strands. Also triggers on "write a doc", "draft a page", "rewrite the quickstart", "add a tutorial for X"…
tutorial
Interactive tutorial teaching Ouroboros hands-on.
learn-from-sage
Detection-gap (miss) analysis for Code Review Sage. Learn from shipped fixes, acted-on human comments, and design outcomes to close reviewer blind spots. Inline during review stages a candidate; a human triggers a one-shot AI consolidation into the live ruleset.