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 commands/catlog22/claude-code-workflow/preparegit clone --depth 1 https://github.com/catlog22/Claude-Code-WorkflowWhat 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 | $0.00025 | $0.01834 |
| Opus 5 | $0.00013 | $0.00917 |
| Sonnet 5 | $0.00005 | $0.00367 |
| Haiku 4.5 | $0.00003 | $0.00183 |
Grade A, and why
prepare 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Prepare Command (/memory:prepare)
1. Overview
The memory:prepare command delegates to a universal-executor agent to analyze the project and return a structured "Core Content Pack". This pack is loaded into the main thread's memory, providing essential context for subsequent agent operations while minimizing token consumption.
Core Philosophy:
- Agent-Driven: Fully delegates execution to universal-executor agent
- Read-Only Analysis: Does not modify code, only extracts context
- Structured Output: Returns standardized JSON content package
- Memory Optimization: Package loaded directly into main thread memory
- Token Efficiency: CLI analysis executed within agent to save tokens
2. Parameters
-
"task context description"(Required): Task description to guide context extraction- Example: "在当前前端基础上开发用户认证功能"
- Example: "重构支付模块API"
- Example: "修复数据库查询性能问题"
-
--tool <gemini|qwen>(Optional): Specify CLI tool for agent to use (default: gemini)- gemini: Large context window, suitable for complex project analysis
- qwen: Alternative to Gemini with similar capabilities
3. Agent-Driven Execution Flow
The command fully delegates to universal-executor agent, which autonomously:
- Analyzes Project Structure: Executes
get_modules_by_depth.shto understand architecture - Loads Documentation: Reads CLAUDE.md, README.md and other key docs
- Extracts Keywords: Derives core keywords from task description
- Discovers Files: Uses CodexLens MCP or rg/find to locate relevant files
- CLI Deep Analysis: Executes Gemini/Qwen CLI for deep context analysis
- Generates Content Package: Returns structured JSON core content package
4. Core Content Package Structure
Output Format - Loaded into main thread memory for subsequent use:
{
"task_context": "在当前前端基础上开发用户认证功能",
"keywords": ["前端", "用户", "认证", "auth", "login"],
"project_summary": {
"architecture": "TypeScript + React frontend with Vite build system",
"tech_stack": ["React", "TypeScript", "Vite", "TailwindCSS"],
"key_patterns": [
"State management via Context API",
"Functional components with Hooks pattern",
"API calls encapsulated in custom hooks"
]
},
"relevant_files": [
{
"path": "src/components/Auth/LoginForm.tsx",
"relevance": "Existing login form component",
"priority": "high"
},
{
"path": "src/contexts/AuthContext.tsx",
"relevance": "Authentication state management context",
"priority": "high"
},
{
"path": "CLAUDE.md",
"relevance": "Project development standards",
"priority": "high"
}
],
"integration_points": [
"Must integrate with existing AuthContext",
"Follow component organization pattern: src/components/[Feature]/",
"API calls should use src/hooks/useApi.ts wrapper"
],
"constraints": [
"Maintain backward compatibility",
"Follow TypeScript strict mode",
"Use existing UI component library"
]
}
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 · 241 lines · 25 tokens per session scan A 0d55f5c9739a
prepare is a command published in the GitHub repository catlog22/Claude-Code-Workflow (2,135 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 1,834 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
verify-claim
Walk a claim through the SIFT method (Stop, Investigate, Find better coverage, Trace).
beat-brief
Draft a daily beat briefing from the files in sample-docs/.
cross-review
Run GitHub Copilot CLI and OpenAI Codex against the current git diff for cross-model review.
step-research
Always research before proposing a fix. The Untether bug you're chasing is often a known upstream engine quirk, a previously-fixed regression, or a documented config gotcha.
whats-next
Show current project status and suggest next steps.
ox-session-pause
belongs in the ox CLI JSON output (guidance field), not here. Skills are agent-specific wrappers; ox serves all agents (Codex, etc.). --> Suspend the current session recording. Local cache continues to receive entries, but the upload at stop time will exclude the suspended range.