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 mthines/agent-skills --skill create-skillgit clone --depth 1 https://github.com/mthines/agent-skillsWrote 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/mthines/agent-skills/create-skill)<a href="https://agentmods.dev/skills/mthines/agent-skills/create-skill"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/create-skill/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/mthines/agent-skills/create-skill"><img src="https://agentmods.dev/badge/skills/mthines/agent-skills/create-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, 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 157 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.
- medium MCP Rug Pull · line 193 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 351 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Prompt Injection · line 294 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00160 | $0.04722 |
| Opus 5.5 | $0.00064 | $0.01889 |
| Sonnet 5.5 | $0.00032 | $0.00944 |
| Haiku 4.5 | $0.00016 | $0.00472 |
Grade A, and why
create-skill 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 — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Skill
Author new agent skills — and audit existing ones — against the best practices distilled from Anthropic's official Skill authoring guide and the patterns already in this repo. Output is a complete skill directory plus the agent-skills.git symlink wiring and inventory updates.
This
SKILL.mdis a thin index. Detailed authoring rules live inrules/*.md, worked examples inreferences/*.md, literal scaffolding templates intemplates/*.md— all load on demand. Reading them all up-front would burn tokens you do not need yet.
Mode Detection
Parse $ARGUMENTS (first token) and detect the mode:
| Mode | Default | Trigger |
|---|---|---|
scaffold |
yes | Default. "create", "scaffold", "new skill", or no mode argument. |
review |
"review", "audit", "check this skill", or $0 == "review". |
|
upgrade |
"upgrade", "split", "convert to multi-file", or $0 == "upgrade". |
|
diagnose |
"diagnose", "why did miss this", or $0 == "diagnose". |
If the user typed a path or skill name as $ARGUMENTS, treat it as the
target for review/upgrade/diagnose; for scaffold it is the proposed
skill name.
State the detected mode and target in one line before continuing. Example:
Mode: scaffold
Target: skills/<category>/<proposed-name>/
Scaffold Workflow (default)
A seven-phase pipeline. Each phase has a gate; do not proceed until it passes.
| Phase | Name | Gate |
|---|---|---|
| 0 | Requirements | User confirmed name, description, modes, structure choice, target runtime |
| 1 | Structure decision | Single-file vs multi-file decided with reasoning |
| 2 | Frontmatter draft | Name + description + flags pass validation |
| 3 | File generation | All planned files written, none over budget |
| 4 | Wiring & inventories | Symlinks created (if local-dev), CLAUDE.md + README.md updated |
| 5 | Self-check | Mechanical pre-pass (scripts/validate-skill.mjs) is PASS, and every judgment item in rules/quality-checklist.md passes |
| 6 | Evaluation | ≥ 3 eval prompts written and at least one with-skill run observed, or the user explicitly waived it |
What ships with it
29 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.
- references/good-vs-bad-examples.md 7.6 KB
- references/skill-archetypes.md 14 KB
- rules/anti-patterns.md 9.6 KB
- rules/arguments-and-injection.md 6.1 KB
- rules/description-writing.md 6.7 KB
- rules/diagnose-mode.md 28 KB
- rules/diagnostic-surface.md 10 KB
- rules/evaluation.md 5.1 KB
- rules/frontmatter.md 11 KB
- rules/invocation-control.md 9.3 KB
- rules/progressive-disclosure.md 7.4 KB
- rules/quality-checklist.md 7.8 KB
- rules/repository-conventions.md 6.7 KB
- rules/review-lens-contract.md 6.8 KB
- rules/scripts-and-assets.md 4.3 KB
- rules/self-improvement-loop-pattern.md 9.1 KB
- rules/structure-decision.md 5.3 KB
- rules/token-economics.md 4.9 KB
- rules/workflow-patterns.md 3.9 KB
- scripts/validate-skill.mjs 45 KB runs code
- templates/diagnostic-surface.template.md 3.2 KB
- templates/evals.json 734 B
- templates/lens.md 849 B
- templates/reference.md 408 B
- templates/rule.md 920 B
- templates/SKILL.minimal.md 1.4 KB
- templates/SKILL.multi-file.md 2.6 KB
- templates/SKILL.portable.md 1.5 KB
- templates/triggers.jsonl 210 B
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 · +31 lines 4d74e0a9c499
- 1mo ago First seen · 371 lines · 160 tokens per session scan A 11376f301436
create-skill is a skill published in the GitHub repository mthines/agent-skills (19 stars, last pushed today), licensed MIT. It adds 160 tokens to every session and 4,722 once invoked, about $0.0006 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.
Other skills, from other repositories
skill-body
Call help() or help("page.click") to print signatures and uncommon options of APIs named below; it prints by itself, so do not wrap it in console.log. For installation or connection problems, read references/install.md in the ego-browser Skill directory.
ego-browser
When you need a browser, read this Skill by default. Use it to open and operate websites, fill forms, click buttons, take screenshots, extract page data, sign in, and perform other browser automation tasks, as well as web app testing, dogfooding, QA, bug investigation, and app-quality review. ego-browser (ego-lite) is…
ego-lite-simplify
Find and implement evidence-backed simplifications in the ego-lite repository. Use when reviewing the codebase for dead code, duplicated state or APIs, speculative abstractions, unnecessary compatibility layers, hand-written infrastructure, excessive tests or documentation, or when the user asks to reduce code size or…
temporal-developer
Develop, debug, and manage Temporal applications across Python, TypeScript, Go, Java, .NET, Ruby, and Rust. Use when the user is building workflows, activities, workers, or background job queues with a Temporal SDK, debugging issues like non-determinism errors, stuck workflows, or activity retries, using Temporal CLI…
custom-icons
Create or refine custom icon assets as native or traced SVGs and transparent PNG/WebP files. Use when the user asks for a bespoke icon or cohesive icon set, wants an image traced into a clean vector, or needs a detailed or 3D icon with transparency.
geekx-gate
A review framework for deciding whether an engineering idea or technical commitment is necessary, too broad, or premature. It examines the real problem, complexity, evidence, non-goals, and ease of reversal.