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 vincentkoc/dotskillsnpx agentmods add plugins/vincentkoc/dotskills/marketplacegit clone --depth 1 https://github.com/vincentkoc/dotskillsGrade A, and why
dotskills 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 3d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "dotskills",
"owner": {
"name": "vincentkoc"
},
"metadata": {
"description": "A .skills collection: prompts with resources and scripts as reusable AI runtime modules.",
"version": "1.0.0"
},
"plugins": [
{
"name": "codebase-memory-mcp",
"source": "./skills/codebase-memory-mcp",
"skills": "./",
"description": "Bring up `codebase-memory-mcp` for the owning Git checkout and prove the graph is usable before relying on it for code discovery. Keep linked worktrees on the owner's graph instead of creating one graph per branch."
},
{
"name": "codex-goal-mining",
"source": "./skills/codex-goal-mining",
"skills": "./",
"description": "Recover structured Codex goal history and convert free-form runs into evidence-backed, repeatable suites."
},
{
"name": "codex-session-recovery",
"source": "./skills/codex-session-recovery",
"skills": "./",
"description": "Recover crashed, detached, or confusing agent sessions while preserving the best restore source."
},
{
"name": "crabpot-perf-metrics",
"source": "./skills/crabpot-perf-metrics",
"skills": "./",
"description": "Turn Crabpot/OpenClaw perf artifacts into a clear read: what changed, what is real signal, what is stale/noisy, and what action is worth taking."
},
{
"name": "crawlkit",
"source": "./skills/crawlkit",
"skills": "./",
"description": "Maintain crawlkit, the shared Go library for crawl app archive infrastructure."
},
{
"name": "ghcrawl-cluster-operator",
"source": "./skills/ghcrawl-cluster-operator",
"skills": "./",
"description": "Operate ghcrawl as a local-first GitHub issue and pull request crawler: inspect the SQLite store, pull GitHub data, refresh summaries and embeddings, build clusters, and extract cluster evidence through deterministic CLI commands."
},
{
"name": "graincrawl",
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.
- 3d ago First seen · 133 lines scan A ae425d727133
dotskills marketplace is a plugin published in the GitHub repository vincentkoc/dotskills (102 stars, last pushed 11d 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 2026-08-30.
Other plugins, from other repositories
chief-of-staff
Turn Claude into your chief of staff. A behavior layer (celebrate before you optimize, close loops, verify don't claim, surface forgotten commitments) plus /chief-of-staff:setup, which scaffolds a persistent memory + daily-brief system tailored to you.
notify
Cross-platform system notifications for Claude Code — macOS and Linux with a notification cooldown.
claude-pilot
SPEC-First development workflow with TDD, Ralph Loop, and autonomous agent coordination for Claude Code.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.