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/halo-dev/cli/halo-cli-sharednpx skills add halo-dev/cli --skill halo-cli-sharedgit clone --depth 1 https://github.com/halo-dev/cliWhat 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 | $0.00080 | $0.00578 |
| Opus 5 | $0.00040 | $0.00289 |
| Sonnet 5 | $0.00016 | $0.00116 |
| Haiku 4.5 | $0.00008 | $0.00058 |
Grade A, and why
halo-cli-shared 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
Halo CLI Shared
Start here when the task says "use Halo CLI" but does not yet say whether it is auth, content, search, operations, or moderation.
Install And Verify
Install globally:
npm install -g @halo-dev/cli
Binary name:
halo
Check version and top-level help:
halo --version
halo --help
Top-Level Areas
authpostsingle-pagesearchpluginthemeattachmentbackupmomentcommentnotificationcompletion <shell>— Generate shell completion script (bash, zsh, fish, powershell)
Shared Rules
- Most command areas require an authenticated profile.
- Use
halo auth loginto create a profile. - Use
--profile <name>when more than one profile exists. - Use
--jsonwhen output is meant for automation or follow-up parsing. - In non-interactive mode, dangerous commands usually require
--force. - Read
--helpbefore guessing flags for a specific command.
Public vs Authenticated
Most areas require auth.
The main public workflow is halo search, which can use a direct site URL without login:
halo search --keyword "halo" --url https://www.halo.run
Config And Secrets
Profile metadata is stored in:
$HALO_CLI_CONFIG_DIR/config.jsonifHALO_CLI_CONFIG_DIRis set- otherwise
$XDG_CONFIG_HOME/halo/config.json - otherwise
~/.config/halo/config.json
Credentials are stored in the system keyring.
Routing
- Use
halo-cli-authfor login, current profile, profile list/use/delete, and credential repair. - Use
halo-cli-contentfor posts and single pages. - Use
halo-cli-searchfor public site search. - Use
halo-cli-operationsfor themes, plugins, attachments, backups, and moments. - Use
halo-cli-moderation-notificationsfor comments, replies, and notifications.
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 · 89 lines · 80 tokens per session scan A 8e533864db3f
halo-cli-shared is a skill published in the GitHub repository halo-dev/cli (29 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 578 once invoked, about $0.0004 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
swarmclaw
AI agent runtime and multi-agent orchestration platform. Teaches agents how to use SwarmClaw's 6 primitive tools, persistent memory, dreaming, delegation, connectors, credentials, and the skill system. Use when an agent is running on SwarmClaw and needs to understand the platform's capabilities.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
prose
OpenProse VM skill pack. Activate on any prose command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.
skill-creator
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating…
feishu-safety-guide
One-click deployment Skill for Feishu security governance and message anti-data-leakage guide, responsible for Feishu message security, credential protection, permission auditing, interaction logging and periodic security reporting.
healthcheck
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).