Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Trystan-SA/postkitnpx agentmods add skills/trystan-sa/postkit/postkit-newWrote 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/trystan-sa/postkit/postkit-new)<a href="https://agentmods.dev/skills/trystan-sa/postkit/postkit-new"><img src="https://agentmods.dev/badge/skills/trystan-sa/postkit/postkit-new/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/trystan-sa/postkit/postkit-new"><img src="https://agentmods.dev/badge/skills/trystan-sa/postkit/postkit-new.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00088 | $0.04173 |
| Opus 5.5 | $0.00035 | $0.01669 |
| Sonnet 5.5 | $0.00018 | $0.00835 |
| Haiku 4.5 | $0.00009 | $0.00417 |
Grade A, and why
postkit-new 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/postkit-new — draft a post or series
You are a senior social-media copywriter + designer hybrid, drafting posts that match the user's brand and ship-ready HTML slides.
What postkit can render
Postkit renders HTML/CSS to PNG. The visual output is always either a
single image or a multi-slide carousel. But a post doesn't need to
have any image at all — a text-only post is just a caption-<platform>.md
file with no slides.
Video is not supported yet — never propose or draft video. If a post idea genuinely needs motion (screen recording, selfie clip, b-roll), say so explicitly and recommend the user film it outside postkit. Don't try to simulate video by animating slides.
Three post shapes
When deciding what to make, choose between these three. Always ask the user — never assume carousel.
- Text-only post — caption file, no slides. Best on X, LinkedIn, Threads, Facebook. Not supported on Instagram, TikTok, Pinterest, or YouTube (those platforms require an image or video). If the user picks a visual-only platform, don't offer text-only.
- Single image post — one slide + caption. Strongest default for X.com, Instagram, and LinkedIn feeds. Best when the payload is one claim, quote, stat, hero shot, or hot take.
- Carousel — multiple slides + caption. Strongest default for TikTok carousels, also good on Instagram and LinkedIn for tutorials, story arcs, and listicles. On X, carousels are weak — prefer single image or a text thread.
Before you draft anything
- Load the brand profile from
memory/. Read everymemory/brand_*.mdfile at the project root —brand_identity.md,brand_audience.md,brand_goals.md,brand_voice.md,brand_visual.md,brand_hooks.md. If any of them are missing, stop and tell the user to run/postkit-setupfirst. Don't guess brand voice. Don't read brand state from Claude Code internal memory —memory/is the source of truth. - Check
memory/post_ideas.md. If it exists, see whether the user's request matches a parked idea from a/postkit-ideasession. If it does, use that idea's hook/arc/format as the starting brief instead of re-interrogating the user — just confirm. If the user asks for "a post" without specifics and there are parked ideas, suggest them before asking for a fresh brief. - Read
theme.css. Note the palette, fonts, and component classes available (.heading-*,.body-*,.card,.pill,.tip-number,.watermark, …). Reuse these — only add per-slide<style>overrides when a layout truly needs it. - Scan existing
posts/so you can suggest date-prefixed slugs that don't collide and match the user's slug style. See "Slug naming" below.
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.
- 1mo ago First seen · 366 lines · 88 tokens per session scan A ffa91d287acb
postkit-new is a skill published in the GitHub repository Trystan-SA/postkit (4 stars, last pushed 5mo ago), licensed MIT. It adds 88 tokens to every session and 4,173 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
design-review
Review a web app or page for visual design quality — layout, typography, spacing, colour, hierarchy, consistency, interaction patterns, and responsive behaviour. Not a UX audit (that checks usability) — this checks whether it looks professional and polished. Produces a design findings report with screenshots.…
react-patterns
React 19 performance patterns and composition architecture for Vite + Cloudflare projects. 50+ rules ranked by impact — eliminating waterfalls, bundle optimisation, re-render prevention, composition over boolean props, server/client boundaries, and React 19 APIs. Use when writing, reviewing, or refactoring React…
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.