content-plan

content-plan is a command for Claude Code from fatihkan/badi. It costs 0 tokens per session (743 once invoked), scanned A, original, MIT.

A weekly planning command for organizing a brand’s content themes, publishing targets, and production work for the following week.

In plain words
What is it for?
Use it to review last week’s content, choose daily themes, and set format and platform targets for posts, carousels, videos, and other content.
Why use it?
It replaces scattered planning with one review of recent output and a structured plan based on events, seasons, campaigns, and customer questions.

Command for Claude Code

Part of the badi plugin — 28 commands, 30 agents shipped together

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/fatihkan/badi/content-plan
Clone the repo
git clone --depth 1 https://github.com/fatihkan/badi

Made for: Claude Code.

Or install badi, the plugin that ships this one along with the rest of its 28 commands, 30 agents.

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 content-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/fatihkan/badi/content-plan.svg)](https://agentmods.dev/commands/fatihkan/badi/content-plan)
Your own site
<a href="https://agentmods.dev/commands/fatihkan/badi/content-plan"><img src="https://agentmods.dev/badge/commands/fatihkan/badi/content-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 743 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 $0.00000 $0.00743
Opus 5 $0.00000 $0.00371
Sonnet 5 $0.00000 $0.00149
Haiku 4.5 $0.00000 $0.00074

Measured 3d ago against content hash 93808f40ddab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

content-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 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.

.claude/commands/content-plan.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Weekly content planning session command. Sets next week's content strategy, themes, and production targets.

Required Tools

  • Read (brand voice, past calendars, performance)
  • Write (new calendar file)
  • Grep (past content analysis)
  • Glob (file search)
  • Bash (date calculations)

Procedure (6 Steps)

Step 1: Last Week's Review

Analyze the last 7 days of production output:

  • How much content was produced? (per platform)
  • Which were planned, which spontaneous?
  • Any planned content left unfinished?
  • Which format do you produce most? (post, carousel, video)

Ask:

  • What were your 3 best pieces? (by engagement or satisfaction)
  • Which was the hardest? (why was it hard?)

Step 2: Next Week's Themes

Build the week's theme map:

Data sources:

  • Special days and events (check the calendar)
  • Seasonal opportunities
  • Current topics (brand-fit)
  • Ongoing campaigns
  • Customer questions / FAQ

Set 1 main theme per day:

Monday: [theme] — [why]
Tuesday: [theme]
...

Step 3: Platform Distribution

Set a weekly target per platform:

Platform Format Target Count Theme Link
Instagram Post ... ... ...
Instagram Reel ... ... ...
Twitter/X ... ... ...
LinkedIn ... ... ...
TikTok ... ... ...

Note: 3-5 items per platform is enough (quality > quantity).

Step 4: Build the Content Matrix

Clear planning per day and platform:

Monday:
  - IG Post: "[topic]" (theme: [theme])
  - Twitter: thread "[topic]"

Tuesday:
  - IG Reel: 30s "[topic]"
  - LinkedIn: "[topic]"

...

Step 5: Production Cadence

Plan when you will produce the content:

  • Batch production day (example: Monday morning for the whole week)
  • Daily production (each day for that day)
  • Mixed model (prepared ahead + current)

Tip: batch production is efficient, but topical content keeps things dynamic.

Step 6: Save the Calendar File

Create the detailed file with the /content-calendar command, or suggest the badi content calendar "[week-date]" CLI command.

Read the full file on GitHub · 137 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 · 137 lines · 0 tokens per session scan A 93808f40ddab

Subscribe to this mod's changes

content-plan is a command published in the GitHub repository fatihkan/badi (7 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 743 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.