blogkit.implement

blogkit.implement is a command for coding agents from agentii-ai/blog-tech-kit. It costs 12 tokens per session (2,931 once invoked), scanned A, original, MIT.

A command for carrying out a blog's content-production plan from project files such as tasks.md, plan.md, and an editorial guide. It follows defined stages such as research, drafting, review, publishing, and measurement.

In plain words
What is it for?
Use it to run blog tasks in dependency order, identify work that can happen in parallel, and track progress by sprint and phase.
Why use it?
It keeps a multi-step blog workflow organized and records what is complete, underway, or blocked. It also applies the project's quality and style requirements as work progresses.

Command

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.

agentmods
npx agentmods add commands/agentii-ai/blog-tech-kit/blogkit.implement
Clone the repo
git clone --depth 1 https://github.com/agentii-ai/blog-tech-kit

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 blogkit.implement

README.md
[![agentmods](https://agentmods.dev/badge/commands/agentii-ai/blog-tech-kit/blogkit.implement.svg)](https://agentmods.dev/commands/agentii-ai/blog-tech-kit/blogkit.implement)
Your own site
<a href="https://agentmods.dev/commands/agentii-ai/blog-tech-kit/blogkit.implement"><img src="https://agentmods.dev/badge/commands/agentii-ai/blog-tech-kit/blogkit.implement.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,931 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00012 $0.02931
Opus 5 $0.00006 $0.01465
Sonnet 5 $0.00002 $0.00586
Haiku 4.5 $0.00001 $0.00293

Measured 3d ago against content hash 520c100a9cad, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

blogkit.implement 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 3d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.blogkit/templates/commands/blogkit.implement.md · 334 lines

How it starts

The opening of the file, as written. The whole thing — 334 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

Execute content production tasks systematically from tasks.md with quality gates and progress tracking:

  1. Load Required Files:

    • Read tasks.md from current feature directory
    • Read plan.md to understand tech stack and quality standards
    • Read editorial-guide.md (if exists) for style/voice standards
    • Extract blog type, editorial workflow, team roles
  2. Parse Task Breakdown:

    • Extract all sprint phases (Sprint 0, Sprint 1-5)
    • Extract all task phases within each sprint (Research, Draft, Review, Copyedit, Publish, Measure)
    • Identify task dependencies and sequential/parallel execution markers [P]
    • Build execution graph (tasks must complete in order respecting dependencies)
  3. Initialize Execution Tracking:

    • Create or load execution state file: .blogkit/execution-state.md
    • Track: Current sprint, current phase, tasks completed, tasks in progress, blockers
    • Initialize progress dashboard:
      Blog Content Production Progress
      ════════════════════════════════════════
      Sprint 0: Platform Setup
        [████████░░░░░░░░░░░░░░░░] 40% (8/20 tasks)
      
      Sprint 1: Foundation Post
        [░░░░░░░░░░░░░░░░░░░░░░░░] 0% (0/38 tasks)
      
  4. Validate Preconditions:

    • Verify all required files exist (spec.md, plan.md, tasks.md)
    • Verify Constitution Check passed (from plan.md)
    • Verify no [NEEDS CLARIFICATION] markers remain in spec/plan
    • Verify team roles and SME assignments documented
    • If preconditions fail: STOP and report what's missing
  5. Execute Sprint 0: Platform Setup (if starting):

    • Orchestrate platform setup tasks (18 tasks total)
    • Verify deployment successful (platform live on domain)
    • Confirm analytics configured (tracking enabled)
    • Confirm newsletter integrated (signup working)
    • Confirm SEO configured (XML sitemap, robots.txt, GSC)
    • Quality gate: All platform tasks checked off
    • On completion: Mark Sprint 0 COMPLETE, ready for first post

Read the full file on GitHub · 334 lines

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. 3d ago First seen · 334 lines · 12 tokens per session scan A 520c100a9cad

Subscribe to this mod's changes

blogkit.implement 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 2,931 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.