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/lexxes-projects/obey/remembernpx skills add Lexxes-Projects/obey --skill remembergit clone --depth 1 https://github.com/Lexxes-Projects/obeyWhat 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 | $0.00041 | $0.01360 |
| Opus 5 | $0.00020 | $0.00680 |
| Sonnet 5 | $0.00008 | $0.00272 |
| Haiku 4.5 | $0.00004 | $0.00136 |
Grade C, and why
remember 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 yesterday.
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.
- "never delete with rm -rf" → tool: Bash, field: command, pattern: `rm\s+-rf` How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/remember — Save a Persistent Rule
The user wants to save a rule: $ARGUMENTS
Step 1: Parse the Rule
Extract the rule text. Strip any flags (--global, --local, --rust, --node, --python, --go) if present.
Step 2: Determine Scope
Check for explicit flags first:
--global→ scope: global (all projects, always)--localor--project→ scope: project (only this project)--rust,--node,--python,--go,--java→ scope: stack
If NO flag given, analyze the rule:
- General dev practices (git, testing, formatting, security) → global
- Language-specific (unwrap, console.log, pip, cargo, npm, types) → stack (detect with
bash ${CLAUDE_PLUGIN_ROOT}/scripts/detect-stack.sh) - References specific files, paths, or "this project"/"here" → project
- If truly ambiguous → ask the user: "Should this apply globally, to all [detected stack] projects, or just this project?"
Step 3: Determine Enforcement
Can this be blocked by matching a pattern in tool input?
Code-enforceable (mechanism: hook or both):
- "never push to main" → tool: Bash, field: command, pattern:
git\s+push.*(main|master) - "never use sudo" → tool: Bash, field: command, pattern:
\bsudo\s+ - "never delete with rm -rf" → tool: Bash, field: command, pattern:
rm\s+-rf - "never force push" → tool: Bash, field: command, pattern:
push\s+--force|push\s+-f - "never edit .env files" → tool: Write|Edit|MultiEdit, field: file_path, pattern:
\.env$|\.env\. - "never use console.log" → tool: Write|Edit|MultiEdit, field: content, pattern:
console\.log\( - "never use .unwrap()" → tool: Write|Edit|MultiEdit, field: content, pattern:
\.unwrap\(\) - "never use eval()" → tool: Write|Edit|MultiEdit, field: content, pattern:
\beval\( - "never make repos public" → tool: Bash, field: command, pattern:
--visibility\s+public - "never publish without asking" → tool: Bash, field: command, pattern:
cargo\s+publish|npm\s+publish
Instruction-only (mechanism: instruction):
- Style preferences ("prefer X over Y")
- Process rules ("always explain before coding")
- Quality standards ("keep functions under 50 lines")
- Architecture guidance ("use repository pattern")
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.
- yesterday First seen · 104 lines · 41 tokens per session scan C b2233c5cf9b1
remember is a skill published in the GitHub repository Lexxes-Projects/obey (1 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 1,360 once invoked, about $0.0002 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
wordpress-plugin-fundamentals
Modern WordPress plugin development with PHP 8.3+, OOP architecture, hooks system, database interactions, and Settings API.
dsh-hooks-authoring
编写或调试已安装的 dsh-hooks-plugin 的 hook 脚本。配置在 /.dsh/hooks.json，事件挂 PreToolUse/PostToolUse/UserPromptSubmit/SessionStart 等；命令从 toolinput.command 读，决策只能通过 stdout JSON 表达（permissionDecision deny/ask/allow），退出码不 gate，hookEventName 必须回填，Windows 上 command 由 PowerShell 解释且可能被沙箱拦外部 exe。.
claude-automation-recommender
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what…
Guard Rules
This skill should be used when a command is blocked by claude-guard, when the response contains "BLOCKED by claude-guard", when the user asks "why was my command blocked", "what commands are blocked", "guard rules", "safety rules", or when Claude is about to execute a potentially dangerous command. Covers git force…
taiyi-ui-design
TaiyiForge 第 4 阶段 — UI/UX 契约，产出 UI-DESIGN.md。四端通用。.
taiyi-evolve
TaiyiForge 辅助 — 实现后架构与文档同步（architecture-sync）。OpenCode / Claude / Codex / Cursor 通用。.