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/caspian-sun/claude-code-workflow/startgit clone --depth 1 https://github.com/Caspian-Sun/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 | $0.00000 | $0.00384 |
| Opus 5 | $0.00000 | $0.00192 |
| Sonnet 5 | $0.00000 | $0.00077 |
| Haiku 4.5 | $0.00000 | $0.00038 |
Grade A, and why
start 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.
What it actually says
You just joined this project. Please follow these steps to get oriented:
Note: CLAUDE.md and project conventions under .claude/rules/ are already auto-loaded — no need to re-read them.
Step 1: Understand the Current Project State
- Scan the
workspace/src/directory structure to understand the existing code modules and file layout - Check
workspace/package.jsonto confirm installed dependencies and available scripts - Check the
workspace/config/directory to understand project configuration (routes / theme / proxy, etc.)
Step 2: Check Current Task Progress
Scan all JSON files in the docs/tasks/ directory and output a summary:
- In-progress modules: list all modules that have non-done tasks
- Pending tasks: list all tasks with status
pendingorin-progress, grouped by module - Completed: count of done tasks / total tasks
Output format:
📋 Current Project Status
━━━━━━━━━━━━━━
[Module 1] (3/5 complete)
✅ T001 - userApi (done)
✅ T002 - useUserStore (done)
✅ T003 - UserTable (done)
⏳ T004 - UserForm (in-progress)
⬜ T005 - UserPage (pending, depends on T004)
[Module 2] (0/3 complete)
⬜ T001 - orderApi (pending)
⬜ T002 - useOrderStore (pending, depends on T001)
⬜ T003 - OrderList (pending, depends on T002)
━━━━━━━━━━━━━━
Total: X modules, Y/Z tasks complete
Step 3: Wait for Instructions
After reporting, wait for my next instruction. Do not start coding on your own.
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 · 43 lines · 0 tokens per session scan A 85ec386b78c6
start is a command published in the GitHub repository Caspian-Sun/claude-code-workflow (10 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 384 tokens. 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 2026-08-31.
Other commands, from other repositories
concentrate-forces
用集中兵力方法在多个任务中锁定主攻目标。.
spark-prairie-fire
用星火燎原方法为从零起步的任务选择根据地和最小切入口。.
publish-skill
Sync a marketplace skill to the documentation site. Creates skill detail pages (EN/ZH), updates the marketplace index, and updates docs.json navigation.
sync-linear
Sync current work with Linear ticket status.
quick-fix
Fast-track workflow for small bug fixes.
receipts
Find the receipt. A dated line, or it did not happen.