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.
/plugin marketplace add dotlas/skillsnpx agentmods add plugins/dotlas/skills/marketplacegit clone --depth 1 https://github.com/dotlas/skillsGrade A, and why
dotlas-skills marketplace 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "dotlas-skills",
"owner": {
"name": "Dotlas",
"url": "https://github.com/Dotlas"
},
"metadata": {
"description": "Dotlas consolidated agent skills",
"version": "1.0.0"
},
"plugins": [
{
"name": "custom-common",
"description": "Dotlas-authored general utilities.",
"source": "./",
"strict": false,
"skills": [
"./skills/custom/common/cc-launch-subagents",
"./skills/custom/common/cc-launch-workflows",
"./skills/custom/common/closed-plan",
"./skills/custom/common/introspection",
"./skills/custom/common/look-into-it",
"./skills/custom/common/plan-with-me",
"./skills/custom/common/slack",
"./skills/custom/common/unpack",
"./skills/custom/common/update-global-dotlas-skills",
"./skills/custom/common/where-were-we"
]
},
{
"name": "custom-coding",
"description": "Dotlas-authored coding workflows.",
"source": "./",
"strict": false,
"skills": [
"./skills/custom/coding/codebase-integrity",
"./skills/custom/coding/commit",
"./skills/custom/coding/import-skill",
"./skills/custom/coding/tidy-next-codebase",
"./skills/custom/coding/ui-consolidation",
"./skills/custom/coding/vercel-env-sync",
"./skills/custom/coding/vercel-logs"
]
},
{
"name": "community-common",
"description": "General-purpose agent utilities vendored from the web.",
"source": "./",
"strict": false,
"skills": [
"./skills/community/common/caveman",
"./skills/community/common/grill-me",
"./skills/community/common/grill-with-docs",
"./skills/community/common/grilling",
"./skills/community/common/handoff",
"./skills/community/common/teach",
"./skills/community/common/write-a-skill",
"./skills/community/common/writing-great-skills",
"./skills/community/common/wWhat 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 · 87 lines scan A 060833ab2e89
dotlas-skills marketplace is a plugin published in the GitHub repository dotlas/skills (2 stars, last pushed 5d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
erpaval
ERPAVal — autonomous software development workflow for Claude Code. Comprehensive standalone bundle: the erpaval workflow plus 10 vendored companion skills (product-discovery, research, ultraplan, tech-stack-builder, product-strategy, working-backwards, customer-research, meta-prompt-optimizer, product-design-shared…
dev-gtm-claude-skills marketplace
Marketing and writing skills for Claude Code — analytics, ads, CRO, copywriting, blog writing, SEO, and more.
ralph-loop-template
Generate an iterable checklist PROMPT file for Ralph Loop from a plan file or the current conversation, and output the ready-to-run /ralph-loop command.
aomi
Aomi for AI agents — drive the Aomi CLI from natural-language prompts (chat, simulate, sign on-chain transactions with account-abstraction-aware execution) and scaffold new Aomi apps from API specs. Bundle ships two skills: aomi-transact (run on-chain across 40+ DeFi/perps/CEX/social apps on EVM mainnets and L2s) and…
skillctx
Make your agent skills portable by extracting hardcoded values into a central config and embedding resolver scripts.
auth
Auth skills for Claude Code — scaffold hand-rolled auth endpoints and audit auth code against security best practices.