agentmods.dev

halo-docs

halo-docs is a skill for Codex from jaxhu1108/halo-mcp. It costs 54 tokens per session (579 once invoked), scanned A, original, MIT.

A skill for managing standard documents in Halo, a documentation platform. It covers publishing, editing, searching, importing, exporting, restoring, and maintaining documents such as plans, guides, reports, and knowledge-base articles.

In plain words
What is it for?
Creating and updating Halo posts and pages, publishing or scheduling them, managing drafts and attachments, searching and rebuilding the index, exchanging Markdown, and restoring earlier versions.
Why use it?
It provides a controlled workflow for keeping Halo documents current, avoiding duplicates, protecting concurrent edits, and checking that changes were written correctly.

Skill for Codex

Written for Codex: agents/openai.yaml present.

not rated 0repo 2mo ago A scan 54 tokens original MIT

Good fit Creating and updating Halo posts and pages, publishing or scheduling them, managing drafts and attachments, searching and rebuilding the index, exchanging Markdown, and restoring earlier versions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jaxhu1108/halo-mcp/halo-docs
View source ↗ jaxhu1108/halo-mcp
Install

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.

Any agent
npx skills add jaxhu1108/halo-mcp --skill halo-docs
Clone the repo
git clone --depth 1 https://github.com/jaxhu1108/halo-mcp

Made for: Codex.

Wrote 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.

agentmods badge for halo-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/jaxhu1108/halo-mcp/halo-docs/github.svg)](https://agentmods.dev/skills/jaxhu1108/halo-mcp/halo-docs)
Your own site
<a href="https://agentmods.dev/skills/jaxhu1108/halo-mcp/halo-docs"><img src="https://agentmods.dev/badge/skills/jaxhu1108/halo-mcp/halo-docs/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for halo-docs

Your own site · 80×15
<a href="https://agentmods.dev/skills/jaxhu1108/halo-mcp/halo-docs"><img src="https://agentmods.dev/badge/skills/jaxhu1108/halo-mcp/halo-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 579 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.00579
Opus 5.5 $0.00022 $0.00232
Sonnet 5.5 $0.00011 $0.00116
Haiku 4.5 $0.00005 $0.00058

Measured 2mo ago against content hash b47ce4412b0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

halo-docs 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/halo-health.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/halo-docs/SKILL.md · 39 lines

What it actually says

Halo 文档管理

Halo 是文档的规范发布位置。优先使用 halo_* MCP 工具；API 或 MCP 可用时，不使用浏览器自动化处理 Halo 文档。

必须遵循的流程

  1. 连接状态未知时先调用 halo_health。
  2. 创建前调用 halo_search_content，必要时再调用 halo_list_posts，避免重复文档。
  3. 能识别现有文档时必须原位更新，并保留 slug、可见性和发布状态，除非用户明确要求变更。
  4. 新文档使用稳定、可读的 slug；用户未明确要求发布时默认创建草稿。
  5. 更新时优先传入 expectedVersion 或 expectedHeadSnapshot，避免覆盖并发修改；仅在确认冲突原因后才使用强制覆盖。
  6. 每次写入后都要回读验证；涉及公开内容时还要检查 release snapshot。
  7. 删除使用回收站，不执行不可恢复的永久删除；需要恢复时使用快照。
  8. 不输出 PAT、密码、Cookie、Authorization 请求头或环境文件内容。

常用操作

  • 创建/更新文章：halo_create_post、halo_update_post
  • 创建/更新页面：halo_create_page、halo_update_page
  • 发布/定时：halo_publish_post、halo_schedule_post
  • 下线/回收/恢复：halo_unpublish_post、halo_recycle_post、halo_restore_post
  • 搜索同步：halo_sync_index、halo_rebuild_index、halo_search_content
  • 版本恢复：halo_list_snapshots、halo_revert_snapshot
  • Markdown 交换：halo_import_markdown、halo_export_markdown
  • 附件：halo_upload_attachment

详细参数与安全说明见 references/tools.md。MCP 无法连接时，运行 node scripts/halo-health.mjs，该脚本只输出脱敏后的连接结果。

发布规则

  • 用户明确要求“发布”时立即发布并验证 release snapshot。
  • 未明确要求发布时，保持用户指定状态；新文档默认采用配置的可见性并保持草稿。
  • Halo 是内容真源；本地 Markdown 与 SQLite 仅作为源码、交换文件或可重建缓存。
Files

What ships with it

3 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.

Changes

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.

  1. 2mo ago First seen · 39 lines · 54 tokens per session scan A b47ce4412b0f

Subscribe to this mod's changes

halo-docs is a skill published in the GitHub repository jaxhu1108/halo-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 579 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.

Documents
Related

halo-docs compared with skills from other repositories

halo-docs next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
halo-docsjaxhu1108/halo-mcpSkill02mo agoMITA54Codex
orbit-notionnexu-io/open-designSkill107ktodayApache-2.0A117Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-pluginsSkill35kyesterdayApache-2.0A123Claude Code
apify-youtube-transcript-scrapersickn33/agentic-awesome-skillsSkill49kyesterdayMITA48Claude Code
legal-holdanthropics/claude-for-legalSkill9.9kyesterdayApache-2.0A68Claude Code
report-to-pdfasgeirtj/system_prompts_leaksSkill71kyesterdayCC0-1.0A17Claude Code, Codex
artifact-template-minimal-letterheadasgeirtj/system_prompts_leaksSkill71kyesterdayCC0-1.0A54Claude Code, Codex