Claudegram: Skill for Claude Code

.claude/skills/plan-my-content/SKILL.md

plan-my-content is a skill for Claude Code from vvselijah/Claudegram. It costs 87 tokens per session (709 once invoked), scanned A, original, MIT.

A planning aid that examines an Instagram account's actual performance data to identify which posts work and what to publish next.

In plain words
What is it for?
Use it to review posts, compare their performance, find useful posting times and audience patterns, and plan future content.
Why use it?
It avoids judging content mainly by likes and instead considers viewing time, early skips, shares, and saves relative to reach.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is vvselijah/Claudegram's own configuration. It tells Claude Code how to work on Claudegram itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Claudegram configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vvselijah/Claudegram. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vvselijah/Claudegram/main/.claude/skills/plan-my-content/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vvselijah/Claudegram

Made for: Claude Code.

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 plan-my-content

README.md
[![agentmods](https://agentmods.dev/badge/skills/vvselijah/claudegram/plan-my-content/github.svg)](https://agentmods.dev/skills/vvselijah/claudegram/plan-my-content)
Your own site
<a href="https://agentmods.dev/skills/vvselijah/claudegram/plan-my-content"><img src="https://agentmods.dev/badge/skills/vvselijah/claudegram/plan-my-content/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 plan-my-content

Your own site · 80×15
<a href="https://agentmods.dev/skills/vvselijah/claudegram/plan-my-content"><img src="https://agentmods.dev/badge/skills/vvselijah/claudegram/plan-my-content.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 709 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 $0.00087 $0.00709
Opus 5 $0.00044 $0.00354
Sonnet 5 $0.00017 $0.00142
Haiku 4.5 $0.00009 $0.00071

Measured 9d ago against content hash 6a46e8da4f6b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

plan-my-content 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 9d 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/skills/plan-my-content/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan my content (data-grounded)

Use the user's actual numbers, never generic advice. Workflow:

1. Refresh, then load the data

  • Run python refresh.py first (unless they just did) so the numbers are current.
  • Read data/stats.md for the quick read, then parse data/data.js (window.DASHBOARD_DATA = {…};) for detail. Key fields per post: insights.views / reach / saved / shares / total_interactions, ig_reels_avg_watch_time, reels_skip_rate (0..1), like_count, comments_count, category, media_product_type, timestamp. Account-level: daily (reach, views split by follower/non-follower), online_followers (best times), demographics (who follows them).

2. Score by what 2026 actually rewards (NOT likes / follower count)

Rank content by these, per post, normalized to reach where it makes sense:

  • Watch-time / retention (ig_reels_avg_watch_time) — the #1 reels lever.
  • Skip-rate (reels_skip_rate, lower is better) — a strong negative signal.
  • Sends / shares per reach (shares / reach) — a share is a recommendation; weighted far above a like.
  • Saves per reach (saved / reach) — reference value; drives re-surfacing.
  • Use likes/comments only as secondary context. A post with big likes but a high skip-rate or low watch-time is NOT a winner — say so plainly.

3. Find the levers

  • Under-supplied winners: categories with high views-per-post but a low post count → tell them to make more of that.
  • Over-supplied losers: categories they post a lot that under-return → cut back.
  • Best time to post: read online_followers (hour-of-day histogram).
  • Reach vs follower split: if most views_non_followers >> views_followers, they're in discovery mode — lean into broad hooks; if reversed, they're preaching to existing followers — push shareable/save-worthy content to break out.
  • Who they reach vs who follows: compare reached behavior to demographics.

4. Deliver

Give them, concretely:

  1. A 2–3 line honest read of what's working and what isn't (with the real numbers).
  2. The single highest-leverage change.
  3. 2–3 specific next-post ideas in THEIR voice, each with a hook line, the format (reel/carousel/photo), and why the data supports it.

Read the full file on GitHub · 49 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. 9d ago First seen · 49 lines · 87 tokens per session scan A 6a46e8da4f6b

Subscribe to this mod's changes

plan-my-content is a skill published in the GitHub repository vvselijah/Claudegram (51 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 709 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens