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 skills add stippi/code-assistant --skill skill-creatorgit clone --depth 1 https://github.com/stippi/code-assistantWrote 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.
[](https://agentmods.dev/skills/stippi/code-assistant/skill-creator)<a href="https://agentmods.dev/skills/stippi/code-assistant/skill-creator"><img src="https://agentmods.dev/badge/skills/stippi/code-assistant/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.
<a href="https://agentmods.dev/skills/stippi/code-assistant/skill-creator"><img src="https://agentmods.dev/badge/skills/stippi/code-assistant/skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00047 | $0.00929 |
| Opus 5.5 | $0.00019 | $0.00372 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 (183 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 929 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 2026-08-30.
Other skills, from other repositories
memory-audit-pattern-extraction
A method for investigating repeated mistakes by comparing related memories and checking whether an earlier reminder failed. It looks at where the reminder was stored, when it was created, and whether it was strong enough to prevent the mistake.
openai-docs
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, latest/current/default-model prompting guidance, or model upgrade and prompt-upgrade guidance; use…
3D模型与视频特效
A tool for generating 3D models from text or images and applying preset animated effects to pictures. It does not generate ordinary images or full videos.
Presentations
Read, create or edit PowerPoint or Google Slides decks. Use for presentation, slide deck, PowerPoint, PPT, PPTX, or Google Slides requests.
tencent-docs-sheet-generation
A tool for creating a new Excel workbook (.xlsx) from written requirements or reference PDF, Word, or presentation files. It is for starting without an existing spreadsheet file.
html-to-docx
A converter that turns HTML into an editable Microsoft Word document (.docx). It maps common HTML structure and styles, and can include images, tables, a table of contents, headers, and footers.