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.
git clone --depth 1 https://github.com/mizukaizen/hive-doctrine-mcpWrote 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/commands/mizukaizen/hive-doctrine-mcp/draft)<a href="https://agentmods.dev/commands/mizukaizen/hive-doctrine-mcp/draft"><img src="https://agentmods.dev/badge/commands/mizukaizen/hive-doctrine-mcp/draft.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.00547 |
| Opus 5 | $0.00000 | $0.00273 |
| Sonnet 5 | $0.00000 | $0.00109 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
draft 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Command: /draft
Start a new content piece from topic selection through to first draft.
Usage
/draft [topic or keyword]
Process
Step 1: Keyword and Intent Research
Identify:
- Primary keyword: The main search term to target
- Secondary keywords: 2-3 related terms to include naturally
- Search intent: What does someone searching this actually want?
- Informational ("how to...", "what is...")
- Comparison ("X vs Y", "best tools for...")
- Transactional ("buy...", "pricing for...")
Step 2: Competitive Analysis
Review what currently ranks for this keyword:
- What topics do the top results cover?
- What angle or information is missing?
- What is the typical content length?
- What can you add that they have not?
Step 3: Create Outline
Build a structured outline:
# [Headline — includes primary keyword, under 60 chars]
**Meta description:** [150-160 chars, includes keyword, compelling]
**Primary keyword:** [keyword]
**Secondary keywords:** [keyword 2], [keyword 3]
**Target length:** [X] words
**Search intent:** [informational/comparison/transactional]
## [H2: Opening section — hook and problem statement]
## [H2: Core concept or solution]
### [H3: Sub-topic 1]
### [H3: Sub-topic 2]
## [H2: Practical application or examples]
## [H2: Common mistakes or misconceptions]
## [H2: Conclusion and next steps]
Step 4: Write First Draft
Following the approved outline, write the full draft:
- Open with a hook that establishes why this matters
- Each H2 section addresses one main point
- Include at least one concrete example per major section
- Close with a clear takeaway and call to action
Step 5: Save and Handoff
Save to content/blog/[YYYY-MM-DD]-[slug].md with frontmatter:
---
title: "[Headline]"
date: [YYYY-MM-DD]
status: draft
keyword: "[primary keyword]"
description: "[meta description]"
---
Flag the draft for editorial review.
Rules
- Do not skip the outline step. Writing without structure produces unfocused content.
- The outline must be approved (or at least reviewed) before drafting begins.
- First drafts are allowed to be rough. Get the ideas down; editing comes next.
- If keyword research reveals the topic is too competitive or too low-volume, report back and suggest alternatives before drafting.
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 · 82 lines · 0 tokens per session scan A 9bc14dc0e252
draft is a command published in the GitHub repository mizukaizen/hive-doctrine-mcp (0 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 547 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 2026-08-31.
Other commands, from other repositories
mega-approve
Approve the mega-plan and start feature execution. Creates worktrees and generates PRDs for each feature. Usage: /plan-cascade:mega-approve [--flow ] [--tdd ] [--confirm] [--no-confirm] [--spec ] [--first-principles] [--max-questions N] [--auto-prd] [--agent ] [--prd-agent ] [--impl-agent ].
auto
AI auto strategy executor. Analyzes task and automatically selects and executes the best strategy: direct execution, hybrid-auto PRD generation, hybrid-worktree isolated development, or mega-plan multi-feature orchestration.
design-generate
Generate a technical design document. Auto-detects level: project-level from mega-plan.json, or feature-level from prd.json. Provides architectural context for story execution.
design-review
Review and interactively edit the current designdoc.json. Displays the design document in a readable format and allows modifications to components, patterns, decisions, and story mappings.
resume
Auto-detect and resume any interrupted Plan Cascade task. Detects mega-plan, hybrid-worktree, or hybrid-auto context and routes to the appropriate resume command.
worktree
Start a new task in an isolated Git worktree for parallel multi-task development. Creates a task branch, worktree directory with planning files, and leaves the main directory untouched. Usage: /plan-cascade:worktree [task-name] [target-branch]. Example: /plan-cascade:worktree feature-login main.