Borrowing it
Nothing to install: this file belongs to AgentlyHQ/use-agently. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AgentlyHQ/use-agently/main/.agents/skills/cli-for-agent/SKILL.mdgit clone --depth 1 https://github.com/AgentlyHQ/use-agentlyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/agentlyhq/use-agently/cli-for-agent)<a href="https://agentmods.dev/skills/agentlyhq/use-agently/cli-for-agent"><img src="https://agentmods.dev/badge/skills/agentlyhq/use-agently/cli-for-agent.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 108 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Excessive Agency · line 171 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 193 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
What 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 5.1 | $0.00045 | $0.02487 |
| Opus 5 | $0.00023 | $0.01243 |
| Sonnet 5 | $0.00009 | $0.00497 |
| Haiku 4.5 | $0.00005 | $0.00249 |
Grade A, and why
cli-for-agent 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 8d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cli-for-agent — 100% identical, 38 lines differ
How it starts
The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building CLI Tools for AI Agents
When to Use
Use this skill when:
- Designing a new CLI tool that AI agents will invoke
- Adapting an existing CLI to be agent-friendly
- Reviewing a CLI for agent compatibility issues
- Adding commands or subcommands to an agent-facing CLI
Core Principle
Agents are not humans. They cannot see colors, navigate interactive menus, interpret spinner animations, or respond to TTY prompts. A CLI built for agents must communicate entirely through structured text on stdout, clear error messages on stderr, and meaningful exit codes. If an agent can't parse your output or recover from your errors in one retry, your CLI has failed.
Design Rules
1. No TTY Assumed — Ever
Never use interactive prompts, confirmation dialogs, readline, cursor movement, or progress spinners. Every command must run unattended in scripts, CI pipelines, and agent tool-call chains without a terminal.
# Bad — blocks waiting for input
Are you sure? [y/N]
# Good — flag-driven, no interaction
$ my-cli delete --confirm resource-id
If a command is destructive, require an explicit --confirm or --yes flag instead of prompting.
TTY-only decoration. Colors, boxes (boxen), tables, spinners, and progress bars are fine — but only when stdout is a TTY. When piped, output must be plain. Check isatty(stdout) (or your language's equivalent) and strip all decoration when it returns false. Never use box-drawing libraries like boxen in non-TTY mode — they break grep and head.
2. Pipeline-Friendly Output
Your output will be piped through head, tail, grep, jq, awk, and wc. Every design decision flows from this.
One record per line. Each line must be a self-contained unit of meaning. This is the single most important rule — it makes every standard Unix tool work for free.
For a single object response, emit one compact JSON line:
$ my-cli status --output json
{"name":"my-service","status":"running","uptime_seconds":13320}
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.
- 8d ago First seen · 252 lines · 45 tokens per session scan A 7f7f88b60e26
cli-for-agent is a skill published in the GitHub repository AgentlyHQ/use-agently (72 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 2,487 once invoked, about $0.0002 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 skills, from other repositories
prometheus
Prometheus monitoring and alerting for cloud-native observability. Use when implementing metrics collection, PromQL queries, alerting rules, service discovery, recording rules, and scrape config.
approval
Approval workflow skill. View pending approval tasks and approve or reject service requests.
preapproval-agent
Approval pre-review agent. Process webhook-driven approval items, analyze request reasonableness, and execute auditable approve/reject decisions.
request-decomposition-agent
Request decomposition agent. Split broad natural-language infrastructure or application needs into structured, reviewable multi-service request drafts.
create-provider
Create new AtlasClaw providers with proper structure, documentation, and skills. Use when building integrations with external systems like APIs, ITSM, CRM, or custom services.
create-atlasclaw-skill
Create new AtlasClaw skills with proper structure, metadata, and documentation. Use when building executable skills, markdown skills, or provider skills for the AtlasClaw AI Agent.