postkit CLAUDE.md

A contributor guide for Postkit, a small command-line tool that creates a Claude Code workspace for making social-media posts. The workspace includes setup, creation, rendering, and review workflows.

In plain words
What is it for?
Use it when developing Postkit, updating its project templates, changing the command-line interface, or working on the browser-based rendering process.
Why use it?
It explains how the tool’s source code, templates, and rendering process fit together. This helps contributors change the scaffolder without confusing it with the generated workspace.

Instructions file

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 instructions/trystan-sa/postkit/claude-md
Clone the repo
git clone --depth 1 https://github.com/Trystan-SA/postkit
Per session 1,077 This file is loaded in full into every session.
When invoked 1,077 The same file — it is already loaded in full.
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 $0.01077 $0.01077
Opus 5 $0.00539 $0.00539
Sonnet 5 $0.00215 $0.00215
Haiku 4.5 $0.00108 $0.00108

Measured yesterday against content hash 302c8baa52c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

postkit CLAUDE.md 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 yesterday.

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.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — postkit (contributor guide)

This file tells Claude Code how to navigate and contribute to the postkit codebase itself. If you're a user who scaffolded a project with npx postkit, the CLAUDE.md in your own postkit/ folder is a different file (copied from templates/project/CLAUDE.md).

What this repo is

A tiny CLI that scaffolds a Claude-Code-native social-media post workspace into ./postkit/. All end-user workflows run through four Claude skills: /postkit-setup, /postkit-new, /postkit-render, /postkit-review.

The skills ship as plain Markdown files inside templates/project/.claude/skills/ and are refreshed every time the user re-runs npx postkit.

Rendering stays in the npm package (not copied into user projects), so users get renderer improvements for free via npx postkit@latest.

Repo map

bin/postkit.js                       CLI shebang; boots src/cli.js
src/
  cli.js                             Dispatches:  (no args) → scaffold,  `render` → renderPost
  scaffold.js                        The only command most users ever invoke
  render.js                          Puppeteer pipeline (called via `npx postkit render <post>`)
  formats.js                         Aspect-ratio → pixel dimensions
templates/project/                   Scaffolded verbatim into user's ./postkit/
  .claude/skills/
    postkit-setup/SKILL.md           Brand intake → saves memory/brand_*.md + updates theme.css
    postkit-idea/SKILL.md            Creative brainstorm + sequence plan → saves memory/post_ideas.md
    postkit-new/SKILL.md             Draft one post or a series
    postkit-render/SKILL.md          Shells out to `npx postkit render`
    postkit-review/SKILL.md          Strategy + copy + design critique
  theme.css                          Default design system
  CLAUDE.md                          Guide used by Claude inside user's workspace
  gitignore                          Renamed to .gitignore on copy
  (memory/)                          Brand profile lives here at runtime — created by scaffolder, populated by /postkit-setup
examples/
  quickstart/                        Committed reference post, smoke-test fixture

Read the full file on GitHub · 105 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. yesterday First seen · 105 lines · 1,077 tokens per session scan A 302c8baa52c4

Subscribe to this mod's changes

postkit CLAUDE.md is an instructions file published in the GitHub repository Trystan-SA/postkit (4 stars, last pushed 4mo ago), licensed MIT. It adds 1,077 tokens to every session, about $0.0054 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 2026-08-31.