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 skills/freespirits/social-auto-engine/post-formatternpx skills add Freespirits/social-auto-engine --skill post-formattergit clone --depth 1 https://github.com/Freespirits/social-auto-engineWrote 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/skills/freespirits/social-auto-engine/post-formatter)<a href="https://agentmods.dev/skills/freespirits/social-auto-engine/post-formatter"><img src="https://agentmods.dev/badge/skills/freespirits/social-auto-engine/post-formatter.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 | $0.00122 | $0.00998 |
| Opus 5 | $0.00061 | $0.00499 |
| Sonnet 5 | $0.00024 | $0.00200 |
| Haiku 4.5 | $0.00012 | $0.00100 |
Grade A, and why
post-formatter 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.
This is a copy
100% identical to post-formatter — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Post Formatter
CRITICAL: Auto-start on load
When this skill triggers, go straight to Step 1. Do not summarise. Start input gathering immediately.
Step 1. Gather inputs
Call AskUserQuestion:
[
{
"question": "What topic do you want to post about?",
"header": "Topic",
"multiSelect": false,
"options": [
{"label": "I will type the topic", "description": "Single sentence describing the subject"},
{"label": "Paste a context dump", "description": "Notes, stats, transcripts to turn into a post"}
]
},
{
"question": "Which framework?",
"header": "Framework",
"multiSelect": false,
"options": [
{"label": "PAS", "description": "Problem, Agitation, Solution"},
{"label": "AIDA", "description": "Attention, Interest, Desire, Action"},
{"label": "BAB", "description": "Before, After, Bridge"},
{"label": "STAR", "description": "Situation, Task, Action, Result"},
{"label": "SLAY", "description": "Story, Lesson, Actionable advice, You"},
{"label": "Pick for me", "description": "Recommend the best framework based on the topic"}
]
}
]
Ask one follow-up:
Anything else I should know? Facts, stats, tone notes, or who this is for.
Wait for response.
Step 2. Write the post
Apply these global rules to every output:
- Maximum 20 lines, 200 to 250 words total (~1,200 characters)
- Blank line after every line
- Most lines: one sentence, 55 characters or fewer
- Up to 4 lines may be mini-paragraphs (2 to 3 sentences, 110 characters or fewer)
- Grade 6 words. Zero adverbs, zero jargon, zero fluff
- No em dashes
- No questions unless the hook itself is a question
- No emojis except checkmarks for numbered lists (1. 2. 3.) and the recycle symbol in the CTA
- Rule of Three: use at most two trios per post
- Vary sentence starts. Do not over-use "I"
Step 3. Structure
- Line 1 (Hook): Bold. 50 characters or fewer.
- Line 2 (Twist / Contrast): 50 characters or fewer. Opposes or surprises the hook.
- Lines 3 to 18 (Core): The chosen framework, split across 3 to 5 lines per stage. Any list inside a stage must have exactly three items (1. 2. 3.). Use arrows to show flow where useful.
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 · 99 lines · 122 tokens per session scan A 9af34ac7b893
post-formatter is a skill published in the GitHub repository Freespirits/social-auto-engine (23 stars, last pushed 1mo ago), licensed MIT. It adds 122 tokens to every session and 998 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to post-formatter, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
repo-eco-mcp-app
Inline Claude Desktop widget for any public Eco game server - live player counts, meteor countdown, world stats. A hand-rolled MCP Apps reference implementation in Python (no bundler, no React). Triggers - eco-mcp-app, claude-desktop-eco-widget, mcp-apps-reference-implementation.
mcp-host-styling-integration
Integrates MCP App UI with host theming system. Applies host CSS variables, handles onhostcontextchanged, safe area insets, display mode detection, and fullscreen configuration.
cog-knowledge-consolidation
Build structured knowledge frameworks from scattered vault notes with source attribution.
context-engineering
Dynamic context injection, mode switching (dev/review/research), selective loading, and strategic compaction for token optimization.
plan-implementation
Disciplined execution of approved plans with step-by-step verification, phase checkpoints, failure investigation, and mandatory code/security reviews.
consensus-mechanisms
Multi-protocol consensus for agent swarms supporting Raft leader election, Byzantine fault tolerance, Gossip state propagation, and CRDT conflict-free merging.