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 skills add indranilbanerjee/socialforge --skill parse-calendargit clone --depth 1 https://github.com/indranilbanerjee/socialforgeWrote 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/indranilbanerjee/socialforge/parse-calendar)<a href="https://agentmods.dev/skills/indranilbanerjee/socialforge/parse-calendar"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/socialforge/parse-calendar/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.
<a href="https://agentmods.dev/skills/indranilbanerjee/socialforge/parse-calendar"><img src="https://agentmods.dev/badge/skills/indranilbanerjee/socialforge/parse-calendar.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.00899 |
| Opus 5.5 | $0.00012 | $0.00360 |
| Sonnet 5.5 | $0.00006 | $0.00180 |
| Haiku 4.5 | $0.00003 | $0.00090 |
Grade A, and why
parse-calendar scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 19d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- parse-calendar — 88% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/socialforge:parse-calendar — Calendar Parser
Parse a monthly social media content calendar into structured JSON that drives the entire production pipeline.
Context efficiency
Asset-heavy skill. Grep before Read the asset catalog (${CLAUDE_PLUGIN_DATA}/socialforge/brands/<brand>/asset-index.json) — never list the asset directory. Reference generated images / videos by path, not by loading metadata. Brand profile loads once per session.
Supported Formats
| Format | How It Works |
|---|---|
| DOCX | Read tables and structured text from Word documents |
| XLSX | Read rows from Excel spreadsheets (one row per post) |
| Notion | Read from Notion database via MCP (requires Notion connector) |
| Structured text | Parse markdown or plain text with consistent formatting — pasted inline (--paste) or from a .txt path |
Required Fields Per Post
Every post in the calendar must have (or the system will ask for missing ones):
| Field | Required | Description |
|---|---|---|
| post_id | Auto-generated | Unique identifier (e.g., P01, P02) |
| date | Yes | Publishing date (YYYY-MM-DD) |
| platform | Yes | Target platform(s) — linkedin, instagram, x, facebook, etc. |
| content_type | Yes | static, carousel, video, story, reel, text_only |
| tier | Yes | HERO, HUB, or HYGIENE |
| topic | Yes | What the post is about |
| caption_brief | Yes | Brief description of the copy direction |
| visual_brief | Recommended | What the image should show |
| hashtags | Optional | Post-specific hashtags (brand hashtags added automatically) |
| cta | Optional | Call-to-action text or link |
| campaign | Optional | Campaign this post belongs to |
| notes | Optional | Special instructions |
Process
- Detect format — Check file extension or URL pattern
- Extract posts — Parse each post entry from the source
- Validate fields — Check required fields present. For missing fields, ask the user.
- Normalize — Standardize dates, platform names, content types to schema format
- Assign post IDs — Sequential (P01, P02, ...) if not already present
- Cross-reference platforms — Check all platforms exist in brand's platform-config.json
- Flag issues — Duplicate dates, missing briefs, unsupported content types
- Save — Write calendar-data.json to
${CLAUDE_PLUGIN_DATA}/socialforge/output/{brand}/{YYYY-MM}/(falls back to~/socialforge-workspace/output/...when${CLAUDE_PLUGIN_DATA}is unset)
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.
- 19d ago Changed · -67 tokens per session 559e6a865df1
- 23d ago Changed b0db314f3834
- 1mo ago First seen · 83 lines · 98 tokens per session scan A 84e3cd6c4b30
parse-calendar is a skill published in the GitHub repository indranilbanerjee/socialforge (42 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 899 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
data-analysis-skills
A data-analysis workflow for turning CSV, Excel, JSON, or TSV files into an industry-aware report with findings, conclusions, and visualizations.
markitdown
Konwersja dowolnego dokumentu (PDF, Word, Excel, PowerPoint, HTML, EPUB, audio, obrazy, YouTube) na Markdown dla LLM. Użyj gdy użytkownik mówi "konwertuj PDF", "przerób Word na markdown", "zamień PPT na MD", "markdown z Excela", "wyciągnij tekst z PDF", albo daje plik Office/PDF do analizy. Microsoft MarkItDown (pip)…
ingestao
Converte documento em markdown estruturado antes de qualquer análise, roteando cada tipo de arquivo para o conversor certo. Use quando o usuário subir ou apontar para PDF, Word, Excel, PowerPoint, EPUB, imagem, áudio ou repositório de código, e quando um PDF científico precisar preservar fórmula, tabela e ordem de…
storyboard-designer
A tool for turning a narration or story script into a structured storyboard spreadsheet for AI video projects. The spreadsheet includes shot planning, character design, first- and last-frame prompts, narration, and sound effects.
comparator
Generic Comparison Matrix Builder: creates, populates, and maintains weighted XLSX comparison matrices for ANY domain and ANY pair (or set) of solutions. Evidence comes from whatever is available — CIRs produced by MultAI's solution-researcher, documents in the working folder, LLM knowledge, or user description. A CIR…
parse-calendar
Parse a content calendar or plan from DOCX, XLSX, Notion or pasted text into structured posts. "load this month's calendar".