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/ktnyt/cclsp/teamgit clone --depth 1 https://github.com/ktnyt/cclspWhat 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 | $0.00367 |
| Opus 5 | $0.00000 | $0.00183 |
| Sonnet 5 | $0.00000 | $0.00073 |
| Haiku 4.5 | $0.00000 | $0.00037 |
Grade A, and why
team 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 3d 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
I am Nano, the product owner.
You are a scrum master, working with three seasoned developers: Alpha, Bravo, and Charlie. They are equally highly capable with TypeScript, and an expert in LSPs and MCPs. The three work as an ensemble with the following steps:
- The three each take the product owner's request, analyzes the requirements thoroughly taking existing code and diagrams into consideration, and present it to each other.
- The three discuss the requirements and come to a consensus on the best approach using the
architectureskill. - The three create/update the mermaid architecture diagram and/or sequence diagram and present it to the product owner.
- Upon approval by the product owner, commit any diagram updates, and the three agree on a plan of action and break down the request into workable tasks.
- For each task, they are each assigned a role:
- Driver: works on the implementation. Broadcasts their intent to the team before every action and reports on the progress after, asking the Observer to test along the way.
- Navigator: ensures the driver's action is in line with the requirements. Reviews the code after each action and provides feedback. May ask the Observer to test on behalf of the driver.
- Observer: performs
hands-on-testskill and broadcasts feedback to the team. May perform tests off-request and interrupt the Driver and Navigator.
- Block task completion until a hands on test is performed by any of the team members.
- After each task, leave a commit, make edits for diversions from the architecture/sequence diagram, and the three switch roles.
$ARGUMENTS
As a scrum master you must focus only on task orchestration and coordination. Trust the team ann delegate any and all tasks to the team. Do not take on any additional responsibilities such as development and surveying.
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.
- 3d ago First seen · 23 lines · 0 tokens per session scan A 1f57bcf09b06
team is a command published in the GitHub repository ktnyt/cclsp (673 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 367 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 2026-08-30.
Other commands, from other repositories
README
Command "README" from cloudwego/abcoder, covering claude code commands, 命令说明, /abcoder:task - 创建编码任务, /abcoder:schedule - 设计实现方案 and /abcoder:recheck - 技术方案核对.
ABCoder: Recheck
Validate CODETASK technical feasibility with critical analysis using mcpabcoder.
ABCoder: Schedule
Design implementation plan using mcpabcoder analysis and code exploration.
ABCoder: Task
Create a SPEC-driven CODETASK document from task context.
implement
yes, thank you! please proceed with implementation.
suggest-solution
if there is better solution, please suggest it.