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 Zfinix/aster --skill skill-creatorgit clone --depth 1 https://github.com/Zfinix/asterWrote 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/zfinix/aster/skill-creator)<a href="https://agentmods.dev/skills/zfinix/aster/skill-creator"><img src="https://agentmods.dev/badge/skills/zfinix/aster/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/zfinix/aster/skill-creator"><img src="https://agentmods.dev/badge/skills/zfinix/aster/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 Agent Snooping · line 62 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00057 | $0.00953 |
| Opus 5.5 | $0.00023 | $0.00381 |
| Sonnet 5.5 | $0.00011 | $0.00191 |
| Haiku 4.5 | $0.00006 | $0.00095 |
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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill creator
- Check the index first. If an existing skill already covers the workflow, extend that skill's file instead of creating a near-duplicate.
- Confirm before creating. A skill is a repo or config file; say what you are about to write and where, and get a yes. Exception: the user already asked for the skill in this turn.
- Pick the root by scope. Project-specific workflow:
.aster/skills/<name>/SKILL.mdin the repo. Personal preference that applies everywhere:<aster home>/skills/<name>/SKILL.md. Kebab-case name, under 64 characters. - The description is the trigger, so write it as one. The index shows only name and description; the body loads when a request matches. State what the skill does, then the concrete situations that should fire it: "Use when the user asks to X, mentions Y, or a Z fails."
- Body format: numbered imperative rules with counter-examples. Each
rule is one behavior, stated as a command, with a literal do-this and
never-this where it helps. Write "Stage named files:
git add src/a.rs. Nevergit add -A." Never write essays about philosophy. - Capture the evidence, not the theory. Put in the exact commands that worked this session, the failure that motivated the rule, and the check that proves the workflow succeeded. A skill mined from a real session beats one written from imagination.
- Keep it small. A few hundred to a couple thousand words. Past that, split into two skills with distinct triggers.
- Frontmatter is exactly
nameanddescriptionbetween---fences, then the markdown body. Verify after writing: the skill should appear in the index next session, andread_skillshould return the body now. - Corrections are skill fuel. When the user corrects the same thing a
second time, that is the signal: offer to fold it into a skill or a
remembernote so they never repeat it again.
Loader rules and tooling
Validation enforced by aster's loader: the file must open with a ---
frontmatter fence; description is required, non-empty, max 1024 characters;
name is optional (falls back to the directory name) but when present must be
lowercase letters, digits, and hyphens, max 64 characters.
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 Changed · +7 lines 8ff4910ae34d
- 1mo ago Changed · +28 lines 5293bd4d0450
- 1mo ago First seen · 37 lines · 57 tokens per session scan A c667f464d576
skill-creator is a skill published in the GitHub repository Zfinix/aster (129 stars, last pushed 8d ago), licensed Apache-2.0. It adds 57 tokens to every session and 953 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
harness
Use when governing a workspace's control plane, code or not — the 01-TOOLS/ tooling layer, the 02-DOCS/ chaos→knowledge wiki, the root Knowledge map. Audits it, migrates legacy XX- folders, scaffolds provider tooling, sweeps the inbox, eats a file the person hands over ("cómete este fichero", "guárdalo en la…
office-xlsx
Read, create, and modify Excel workbooks (.xlsx), including data, formulas, formatting, and pandas analysis. Use for Excel inputs or deliverables. Load before running Office commands. Data and formula tasks skip visual inspection; inspect only for formatting or layout needs. Use only bundled LibreOffice unless the…
office-pptx
Create, read, edit, and check PowerPoint presentations (.pptx), including slide text, tables, images, and charts. Use when a PPTX file is an input or requested deliverable. Load this skill before running Office commands. Use only bundled LibreOffice unless the user explicitly opts out; without that opt-out, do not…
office-docx
Create, read, edit, and check Word documents (.docx), including reports, letters, and formatted tables. Use when a DOCX file is an input or requested deliverable. Load this skill before running Office commands. Use only bundled LibreOffice unless the user explicitly opts out; without that opt-out, do not search for…
ctx
Codebase intelligence and evidence-driven governance with the indexed ctx CLI. Use when exploring an unfamiliar repository, locating symbols or callers, checking for existing implementations, estimating change impact, enforcing architecture rules, scoring a branch, finding hotspots or duplication, or analyzing…
author-and-promote-skill
Use when you've drafted or improved a skill locally and want to publish it to a shared pack — walks through validating the draft, finding the target pack, running the promote script, and reviewing the staged diff before it ships.