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/addgit 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 | $0.00023 | $0.07602 |
| Opus 5 | $0.00012 | $0.03801 |
| Sonnet 5 | $0.00005 | $0.01520 |
| Haiku 4.5 | $0.00002 | $0.00760 |
Grade A, and why
add 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 — 895 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto Mode
When --yes or -y: Auto-categorize and add entry without confirmation.
Spec Add Command (/workflow:spec:add)
Overview
Unified command for adding structured knowledge entries one at a time. Supports 4 knowledge types with optional extended fields for complex entries (bug debugging, code patterns, architecture decisions).
Key Features:
- 4 knowledge types:
bug,pattern,decision,rule - Unified entry format:
- [type:tag] summary (date) - Extended fields for complex types (bug/pattern/decision)
- Interactive wizard with type-specific field prompts
- Direct CLI mode with auto-detection
- Backward compatible:
[tag]=[rule:tag]shorthand - Auto-confirm mode (
-y/--yes) for scripted usage
Knowledge Type System
| Type | Purpose | Format | Target File |
|---|---|---|---|
bug |
Debugging experience (symptoms → cause → fix) | Extended | learnings.md |
pattern |
Reusable code patterns / reference implementations | Extended | coding-conventions.md |
decision |
Architecture / design decisions (ADR-lite) | Extended | architecture-constraints.md |
rule |
Hard constraints, conventions, general insights | Simple (single line) | By content (conventions / constraints) |
Extended Fields Per Type
bug (core: 原因, 修复 | optional: 症状, 参考):
- [bug:api] API 返回 502 Bad Gateway (2026-03-06)
- 原因: 路由处理器未在 server.ts 路由分发中注册
- 修复: 在路由分发逻辑中导入并调用 app.use(newRouter)
- 参考: src/server.ts:45
pattern (core: 场景, 代码 | optional: 步骤):
- [pattern:routing] 添加新 API 路由标准流程 (2026-03-06)
- 场景: Express 应用新增业务接口
- 步骤: 1.创建 routes/xxx.ts → 2.server.ts import → 3.app.use() 挂载
- 代码:
```typescript
if (pathname.startsWith('/api/xxx')) {
if (await handleXxxRoutes(routeContext)) return;
}
```
decision (core: 决策, 理由 | optional: 背景, 备选, 状态):
- [decision:db] 选用 PostgreSQL 作为主数据库 (2026-03-01)
- 决策: 使用 PostgreSQL 15
- 理由: JSONB 支持完善，PostGIS 扩展成熟
- 备选: MySQL(JSON弱) / SQLite(不适合并发)
- 状态: accepted
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 · 895 lines · 23 tokens per session scan A 2786f136087e
add is a command published in the GitHub repository catlog22/Claude-Code-Workflow (2,135 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 7,602 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.