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 instructions/trystan-sa/postkit/claude-mdgit clone --depth 1 https://github.com/Trystan-SA/postkitWhat 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 | $0.01077 | $0.01077 |
| Opus 5 | $0.00539 | $0.00539 |
| Sonnet 5 | $0.00215 | $0.00215 |
| Haiku 4.5 | $0.00108 | $0.00108 |
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.
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
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.
- yesterday First seen · 105 lines · 1,077 tokens per session scan A 302c8baa52c4
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.
Other instructions, from other repositories
Browser4 CLAUDE.md
Instructions for platonai/Browser4, covering browser4 — project context for claude, architecture, key dispatch chain (cli → browser), batch commands and e2e test structure.
spring-ai-agentcore AGENTS.md
Instructions for spring-ai-community/spring-ai-agentcore, covering agents.md, project overview, architecture, key components and artifact store classes.
flyto-core CLAUDE.md
Instructions for flytohub/flyto-core, covering claude notes, cross-agent handoff and shared code intelligence.
metamask-extension AGENTS.md
AGENTS.md instructions for MetaMask/metamask-extension, covering agents.md, agent instructions summary, critical rules for agents, comprehensive guidelines location and quick setup.
deckforge AGENTS.md
Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.
fast-browser CLAUDE.md
Claude Code instructions for m4ttstack/fast-browser, covering fast browser plugin, where a change belongs, fork branch: use fast-browser-runtime, releasing a new runtime and re-pinning this repo: use the script.