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 commands/agentii-ai/blog-tech-kit/blogkit.plangit clone --depth 1 https://github.com/agentii-ai/blog-tech-kitWrote 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/agentii-ai/blog-tech-kit/blogkit.plan)<a href="https://agentmods.dev/commands/agentii-ai/blog-tech-kit/blogkit.plan"><img src="https://agentmods.dev/badge/commands/agentii-ai/blog-tech-kit/blogkit.plan.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 | $0.00012 | $0.03238 |
| Opus 5 | $0.00006 | $0.01619 |
| Sonnet 5 | $0.00002 | $0.00648 |
| Haiku 4.5 | $0.00001 | $0.00324 |
Grade A, and why
blogkit.plan 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 6d 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:
- blogkit.plan — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding (if not empty).
Outline
The text the user typed after /blogkit.plan in the triggering message is the technical context for the blog plan. Assume you always have it available in this conversation even if $ARGUMENTS appears literally below. Do not ask the user to repeat it unless they provided an empty command.
Given the blog strategy specification and the technical context, create a comprehensive editorial and technical plan:
-
Load Required Specification Files:
- Read
spec.mdfrom the current feature directory - Extract: Blog Type, Target Audience, Content Pillars, Publishing Cadence, Success Criteria
- Read
-
Validate Content-First Principle:
- Confirm spec.md contains ZERO technology mentions (no CMS, frameworks, hosting, analytics)
- If technology found in spec: REJECT and ask user to revise spec first
- Continue only when spec is Content-First
-
Parse Technical Context from User Input:
- Extract technology choices from $ARGUMENTS
- Identify: CMS Platform, Framework, Hosting, Analytics, Newsletter, Distribution Tools
- Document rationale for each choice
-
Simplicity & Focus Gate:
- If user mentions custom CMS BEFORE 10 published posts: WARN "Custom CMS before 10 posts violates Simplicity principle. Recommend using battle-tested platform first."
- If user mentions overly-complex architecture for blog MVP: WARN "Over-engineered solution detected. Recommend simplifying to core features first."
- Document warnings but allow override if user explicitly justifies
-
Generate Research Phase (if needed):
- Check if spec.md contains [NEEDS CLARIFICATION] markers
- If > 3 markers exist: Create
research.mdwith investigation plan - If markers exist but ≤ 3: Document clarifications in plan.md Assumptions section
-
Create Editorial Workflow Section:
- Define content production process (Research → Draft → Review → Copyedit → Publish)
- Map to User Blog Type's recommended timeline:
- Authority: 6-week sprint per post
- Practitioner: 2-week sprint per post
- Community: 1-week sprint per spotlight
- Thought Leadership: 4-week sprint per piece
- Define roles: Writer, SME, Copyeditor, Marketing
- CRITICAL: Technical review by SME who didn't write post (No Self-Validation principle)
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.
- 6d ago First seen · 304 lines · 12 tokens per session scan A 99711132923c
blogkit.plan is a command published in the GitHub repository agentii-ai/blog-tech-kit (10 stars, last pushed 9mo ago), licensed MIT. It adds 12 tokens to every session and 3,238 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
excalibur-blog-run
Excalibur BLOG — полный прогон статьи через оркестратор и субагентов.
excalibur-blog-setup
Excalibur BLOG — интерактивная инициализация и настройка проекта.
upgrade
Upgrade the skillshare CLI binary and/or the built-in skillshare skill.
init
Initialize configurations for Supabase local development.
migrate
Command "migrate" from chohra-med/expo_boilerplate, covering invocation, steps and rule.
release
Walk the llmwiki release process step by step.