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/agentscope-ai/agentteams/coding-cli-managementnpx skills add agentscope-ai/AgentTeams --skill coding-cli-managementgit clone --depth 1 https://github.com/agentscope-ai/AgentTeamsWhat 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 | $0.00046 | $0.01851 |
| Opus 5 | $0.00023 | $0.00925 |
| Sonnet 5 | $0.00009 | $0.00370 |
| Haiku 4.5 | $0.00005 | $0.00185 |
Grade C, and why
coding-cli-management scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Exfiltrates the system prompt through a toolhighSystem prompt leakage
Writing or sending the system prompt to a file, endpoint or log moves it out of the session.
# 4. Save prompt to file How it starts
The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coding CLI Management
This skill enables the Manager to execute AI coding CLI tools (claude/gemini/qodercli) on behalf of Workers. Workers generate precise prompts; the Manager runs the CLI in the Worker's workspace and returns the result.
Config File
Path: ~/coding-cli-config.json
{
"enabled": true,
"cli": "claude",
"confirmed_at": "2026-02-23T10:00:00Z"
}
enabled |
cli |
Meaning |
|---|---|---|
false |
any | Admin declined; use normal task flow |
true |
"claude" / "gemini" / "qodercli" |
Active — use this CLI |
Step 1: First-Time Detection (before assigning a coding task)
Run when ~/coding-cli-config.json does not exist:
bash /opt/agentteams/agent/skills/coding-cli-management/scripts/detect-available-cli.sh
If no CLIs are available (available array is empty):
echo '{"enabled":false,"cli":null,"confirmed_at":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' \
> ~/coding-cli-config.json
Proceed with normal task assignment (Worker codes on their own).
If CLIs are available, ask the admin via the primary channel or Matrix DM — in the language the admin used:
I found the following AI coding CLI tools available: [list]. Would you like to enable CLI delegation mode? Workers will generate coding prompts, and I'll use the CLI tool to make the code changes. Reply with the tool name (claude/gemini/qodercli) to enable, or 'no' to have workers code on their own.
On admin reply:
- Tool name (
claude/gemini/qodercli):echo '{"enabled":true,"cli":"<chosen-tool>","confirmed_at":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' \ > ~/coding-cli-config.json "no"or decline:echo '{"enabled":false,"cli":null,"confirmed_at":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' \ > ~/coding-cli-config.json
Step 2: Assigning a Coding Task (CLI mode enabled)
When coding-cli-config.json has enabled: true:
- Ensure the Worker has the
coding-cliskill. Query its Worker CR:
Ifagt get workers <worker> -o json | jq '.skills'coding-cliis missing, distribute it:bash /opt/agentteams/agent/skills/worker-management/scripts/push-worker-skills.sh \ --worker <worker-name> --skill coding-cli
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 201 lines · 46 tokens per session scan C ee129ecfdc36
coding-cli-management is a skill published in the GitHub repository agentscope-ai/AgentTeams (5,537 stars, last pushed 11d ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,851 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (exfiltrates the system prompt through a tool). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-eval-canvas
Create a BitFun Canvas for single-case agent evaluation and trajectory diagnosis. Use when the user asks to analyze one agent run, trace, case, benchmark item, failure trajectory, eval result, or critical failure step, and wants an incident-review style report covering verdict, step timeline, root cause, error…
find-skills
Discover and install reusable agent skills when users ask for capabilities, workflows, or domain-specific help that may already exist as an installable skill.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
zeroclaw
Help users operate and interact with their ZeroClaw agent instance — through both the CLI (zeroclaw commands) and the REST/WebSocket gateway API. Use this skill whenever the user wants to: send messages to ZeroClaw, manage memory or cron jobs, check system status, configure channels or providers, hit the gateway API…
add-dial-tool
Give chosen NanoClaw agents a real phone number as a container tool — the dial CLI baked into the agent image plus OneCLI credential injection for api.getdial.ai, scoped per agent, so the agents you pick can send SMS, place AI voice calls, and receive verification codes from inside the sandbox. Independent of the Dial…
slack-agent-flow
Let an existing Slack agent create new agents that arrive as their own Slack bots — provisioned app, operator DM, and a shared three-way room, hot-started without a host restart.