seedkit CLAUDE.md

Repository instructions for maintaining Seedkit, a Claude Code plugin that bootstraps Django projects. They describe the plugin layout, where reference files and test cases belong, and how related repositories exchange generated projects and source files.

In plain words
What is it for?
Use them when editing Seedkit's plugin manifest, Django setup skill, reference documents, test cases, or its linked example-project workflow.
Why use it?
They prevent plugin files, examples, tests, and website content from being mixed into the wrong repository and preserve the expected workflow.

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/viewflow/seedkit/claude-md
Clone the repo
git clone --depth 1 https://github.com/viewflow/seedkit
Per session 1,325 This file is loaded in full into every session.
When invoked 1,325 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 $0.01325 $0.01325
Opus 5 $0.00662 $0.00662
Sonnet 5 $0.00265 $0.00265
Haiku 4.5 $0.00133 $0.00133

Measured 2d ago against content hash 0467fba0a298, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

seedkit 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 2d 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.

CLAUDE.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

seedkit

Claude Code plugin: a skill for bootstrapping Django projects. The repo root is the plugin root, so everything here ships to anyone who installs it.

Layout:

  • .claude-plugin/plugin.json — the plugin manifest. .claude-plugin/marketplace.json — this repo serving as its own single-plugin marketplace.
  • skills/django-seedkit/SKILL.md + skills/django-seedkit/references/*.md — the skill itself.
  • testcases/0[1-9]-*.md — scripted runs that exercise the skill end-to-end. Specs, not scripts: the harness that runs them lives elsewhere.

Two sibling repos hold everything that is not the skill. Keep it that way — a plugin repo is downloaded in full by every user, and its whole tree is read by the marketplace review pipeline.

  • seedkit-examples — the generated projects and the train/ harness that produces them. It reads skills/ and testcases/ from here via $SEEDKIT (default ../seedkit) and is the only thing that writes back. Its CLAUDE.md holds the harness and baseline contracts.
  • viewflow-pro/seedkit/ (private) — the django-seedkit.viewflow.io landing page and blog, its deploy playbook, and the article backlog. Its CLAUDE.md holds the blog rules.

Run claude plugin validate . after touching either manifest.

Writing reference files

Each reference is a paste-ready snippet plus the minimum prose needed to use it correctly.

Show the correct sample. Imperative, specific, copyable. The agent uses snippets verbatim (SKILL.md "Snippet integrity" pitfall) — anything not in the snippet won't make it into the generated project.

Drop the matching "don't". When a positive sample shows the right way, don't follow it with "Don't write X" / "Never use Y". The correct line is the canonical answer; the redundant warning adds tokens, invites the agent to second-guess, and ages badly. Keep negative guidance only when it stands alone — a behavior rule with no positive code sample (e.g. "Don't strip the Host-header check globally", "Don't log request bodies").

Read the full file on GitHub · 82 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. 2d ago First seen · 82 lines · 1,325 tokens per session scan A 0467fba0a298

Subscribe to this mod's changes

seedkit CLAUDE.md is an instructions file published in the GitHub repository viewflow/seedkit (54 stars, last pushed 10d ago), licensed MIT. It adds 1,325 tokens to every session, about $0.0066 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 2026-08-30.

Related

Other instructions, from other repositories