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 alexmond/alexmskills --skill skill-lintergit clone --depth 1 https://github.com/alexmond/alexmskillsWrote 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/alexmond/alexmskills/skill-linter)<a href="https://agentmods.dev/skills/alexmond/alexmskills/skill-linter"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/skill-linter/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/alexmond/alexmskills/skill-linter"><img src="https://agentmods.dev/badge/skills/alexmond/alexmskills/skill-linter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00125 | $0.02367 |
| Opus 5.5 | $0.00050 | $0.00947 |
| Sonnet 5.5 | $0.00025 | $0.00473 |
| Haiku 4.5 | $0.00013 | $0.00237 |
Grade A, and why
skill-linter 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 10d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex: Read the client path before applying this workflow.
skill-linter
Checks the form of a skill. Whether a skill actually works is a different and
much more expensive question — that belongs to skill-creator's eval loop, which
runs the skill against real prompts with and without it. This exists so that loop
is never spent on a typo in the frontmatter.
Being honest about that boundary matters, because the failure mode here is a green lint being mistaken for a working skill. It is not. It means nothing mechanical is wrong.
What it lints
SKILL.md files; agents/*.md (0.2.0); and since 0.4.0 commands/*.md,
hooks/hooks.json, and plugin-root structure. Skills are also classified by
shape — workflow, orchestrator, learning, reference, scripted; multi-label —
and each shape switches on its own rule pack, so a fan-out skill is asked for a
stopping rule and an output contract, a self-improving skill is asked where its
state lives (and warned when that state sits inside a versioned plugin), and a
step-sequence skill is checked for contiguous numbering. A skill with no labels
pays nothing. Agents earned their slot the
hard way: three shipped "read-only" agents used allowed-tools: (the
slash-command field, silently ignored in agents) and ran with the full tool set
for months. agent-wrong-tools-field is an error for that reason: it is not a
style problem, it is a false safety claim.
Since 0.5.0 it also checks discovery: whether npx skills add — the
installer every agent other than Claude Code uses, and the only route onto
skills.sh — will actually list each skill. Every way of missing one is silent.
The check is a port of the installer's own directory walk, so it reports the
cause: an unlisted plugin, a source without ./, a skill nested too deep or
inside another, a duplicate name, a root SKILL.md hiding the rest. It runs only
for a repo that publishes skills, and only when the run covers a collection.
Run it
What ships with it
2 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.
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.
- 10d ago Changed · +9 lines 11580feaeeef
- 1mo ago Changed · +3 lines d046cf359d7b
- 1mo ago First seen · 182 lines · 125 tokens per session scan A a32191ee4d33
skill-linter is a skill published in the GitHub repository alexmond/alexmskills (9 stars, last pushed 3d ago), licensed MIT. It adds 125 tokens to every session and 2,367 once invoked, about $0.0005 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 2026-09-05.
Other skills, from other repositories
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
safe-refactor
Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.