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 agentmods add skills/alphacornutum/layercake/agentsyncnpx skills add alphacornutum/layercake --skill agentsyncgit clone --depth 1 https://github.com/alphacornutum/layercakeWhat 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 | $0.00146 | $0.05337 |
| Opus 5 | $0.00073 | $0.02669 |
| Sonnet 5 | $0.00029 | $0.01067 |
| Haiku 4.5 | $0.00015 | $0.00534 |
Grade C, and why
agentsync scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"deny": ["Bash(rm -rf *)", "Read(.env)"] How it starts
The opening of the file, as written. The whole thing — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working with AgentSync
Create and maintain AI agent instructions in the AgentSync format.
Structure
.ai/src/ # Source of truth. Edit ONLY here.
├── AGENTS.md # Agent identity: role, approach, principles
├── rules/ # Always-on constraints (one file per topic)
│ ├── core.md
│ └── testing.md
├── skills/ # On-demand recipes (one directory per skill)
│ └── deploy/
│ └── SKILL.md
├── commands/ # Custom slash commands (.md files)
│ ├── review.md
│ └── fix-issue.md
├── agents/ # Subagent personas (.md files)
│ └── code-reviewer.md
├── mcp.json # Shared MCP servers — applied to every tool
└── tools/ # Per-tool config and overrides
├── claude.yaml # tool config: dest paths, format options
└── claude/ # per-tool payload overrides (opt-in)
├── settings.json # permissions / settings override
├── hooks.json # hooks override
└── mcp.json # per-tool MCP override (shadows mcp.json above)
After editing, run agentsync sync to distribute to all tools.
Settings, hooks, and per-tool MCP are overrides: they only exist once you opt in (agentsync enable, agentsync customize, agentsync add mcp). When absent, AgentSync falls back to its shipped base templates. The flat settings/, mcp/, and hooks/ directories from older layouts still work but are deprecated — agentsync migrate moves them into the per-tool form above.
Scaffolding new content
Use agentsync add <kind> <name> to create a new file with the correct frontmatter and placement:
agentsync add rule <name>— creates.ai/src/rules/<name>.mdagentsync add skill <name>— creates.ai/src/skills/<name>/SKILL.mdagentsync add command <name>— creates.ai/src/commands/<name>.mdagentsync add subagent <name>— creates.ai/src/agents/<name>.mdagentsync add mcp <name> (--command CMD [--args '…'] [--env K=V,…] | --url URL)— adds a server to the shared.ai/src/mcp.json
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.
- 2d ago First seen · 288 lines · 146 tokens per session scan C ee1cebc97660
agentsync is a skill published in the GitHub repository alphacornutum/layercake (0 stars, last pushed 1mo ago), licensed MIT. It adds 146 tokens to every session and 5,337 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
after-effects-scripting
Drive a running After Effects instance directly from the shell to build, edit and render motion graphics — no MCP, plugin or panel required. Use whenever the user wants Claude to work inside After Effects: building animations, title sequences, logo stings, UI/product motion, data visualisations, or fixing an existing…
mcporter
List, auth, and call MCP servers/tools from the terminal.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…