simple-host: Instructions file for Claude Code

CLAUDE.md

simple-host CLAUDE.md is an instructions file for Claude Code from vineetu/simple-host. It costs 2,596 tokens per session, scanned B, original, MIT.

Repository instructions for AI coding assistants working on simple-host, a Go program that hosts static websites and provides an API, admin interface, and database-backed features.

In plain words
What is it for?
Use them when modifying simple-host so requests are routed correctly and changes fit the existing design.
Why use it?
They give an assistant the project's layout, architecture, conventions, and important implementation details before it changes code.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions .claude-plugin; mentions CLAUDE.md; mentions Claude Code.

This is vineetu/simple-host's own configuration. It tells Claude Code how to work on simple-host itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything simple-host configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vineetu/simple-host. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vineetu/simple-host/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/vineetu/simple-host

Made for: Claude Code.

Wrote 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.

agentmods badge for simple-host CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vineetu/simple-host/claude-md/github.svg)](https://agentmods.dev/instructions/vineetu/simple-host/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vineetu/simple-host/claude-md"><img src="https://agentmods.dev/badge/instructions/vineetu/simple-host/claude-md/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.

agentmods 80×15 button for simple-host CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/vineetu/simple-host/claude-md"><img src="https://agentmods.dev/badge/instructions/vineetu/simple-host/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,596 This file is loaded in full into every session.
When invoked 2,596 The same file — it is already loaded in full.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.02596 $0.02596
Opus 5.5 $0.01038 $0.01038
Sonnet 5.5 $0.00519 $0.00519
Haiku 4.5 $0.00260 $0.00260

Measured today against content hash 9dd7205a0aa6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

simple-host CLAUDE.md scanned grade B with 2 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 today.

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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

by hand: `sudo systemctl start sh-plugin-repo-sync`, or `DRY_RUN=1 bash scripts/publish-claude-plugin-repo.sh` to preview.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- `curl -s -o /dev/null -w '%{http_code}\n' https://simple-host.app/healthz` → 200
CLAUDE.md · 144 lines

How it starts

The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Working rules for any agent (Claude Code, Codex, Cursor, ...) changing this repo. Simple Host is one Go binary that hosts static sites with a small per-site JSON backend; it is live at https://simple-host.app and runs in production for real users.

Before you change anything

  1. Read INTENT.md (what it is for, non-goals, decisions with dates), then FEATURES.md (what it does today), then ARCHITECTURE.md (where it lives).
  2. git fetch and fast-forward first. Two sessions have overwritten each other in production.
  3. Map every surface a change touches before coding: routes, openapi.yaml, llms.txt, the skills, the dashboard and the showcase page, the MCP tools, the Claude and OpenAI plugins.
  4. If a request conflicts with INTENT.md, say so in one line and ask. When the owner rules on something, add it to INTENT's decisions with the date and reason.

In the same commit as a feature change

  • Update FEATURES.md and add a line to CHANGELOG.md (newest first, plain language).
  • Route changed: update internal/handler/static/openapi.yaml (the contract), regenerate openapi.json with python3 -c "import yaml,json;json.dump(yaml.safe_load(open('internal/handler/static/openapi.yaml')),open('internal/handler/static/openapi.json','w'),indent=2)", then llms.txt and the skills if it is user-facing. scripts/check-docs-sync.sh fails on drift.
  • Skills changed: bump version in simple-host-website/.claude-plugin/plugin.json (the stale-skill notice reads it from the embedded file), then run bash scripts/sync-claude-plugin.sh. Never hand-edit plugins/simple-host/skills/.
  • The plugin repos github.com/vineetu/simple-host-plugin and simple-hack-plugin are published from origin/main by the hourly sh-plugin-repo-sync.timer (it runs both scripts/publish-*claude-plugin-repo.sh); by hand: sudo systemctl start sh-plugin-repo-sync, or DRY_RUN=1 bash scripts/publish-claude-plugin-repo.sh to preview.
  • Schema changed: edit db/schema.sql AND add a file under db/migrations/ (hosted batches: <batch>-<what>.sql; lexical order is apply order). The file must be plain SQL, idempotent (ADD COLUMN IF NOT EXISTS, CREATE ... IF NOT EXISTS) and safe on a live database (additive, defaults, no long locks, no CONCURRENTLY): simple-host migrate runs every file not yet recorded in schema_migrations, including on databases built from schema.sql that already have its effect. Full rule: db/migrations/migrations.go. The historical files listed there as baseline are never run. Small boxes migrate from install.sh on every run; the server never migrates on start. Production: apply the file by hand before deploying (the binary refuses to start if a column it reads is missing), then simple-host migrate -mark <file> (or just simple-host migrate); migrate -status lists what is pending.
  • Parity with Simple Host Enterprise (PARITY.md, identical in both repos): any security fix in one repo is checked against the other the same day (note it in PARITY.md). A new or changed feature updates PARITY.md in the same commit. scripts/check-parity.sh (in check-docs-sync.sh) fails if a ## N. section of FEATURES.md has no PARITY.md row.
  • Design docs in docs/designs/ carry a status line at the top; update it when you ship or drop the thing. Finished plans go to docs/history/.

Read the full file on GitHub · 144 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. today Changed · +3 lines · +69 tokens per session 9dd7205a0aa6
  2. 6d ago Changed · +34 tokens per session 0e32690cc505
  3. 13d ago Changed · +5 lines · +89 tokens per session 5f8756dc2b46
  4. 16d ago Changed · +3 lines · +101 tokens per session e50f034617dd
  5. 20d ago Changed · +12 tokens per session 17ce6bc9176f
  6. 1mo ago Changed · +7 lines · +170 tokens per session 897633c3c69f
  7. 1mo ago Changed · +19 lines · -1,122 tokens per session scan A → B aa3c6b5c34c5
  8. 1mo ago Changed · +2 lines · +495 tokens per session ce29f1caafaf
  9. 1mo ago Changed · +1 lines · +162 tokens per session abfc8bfceb5e
  10. 1mo ago First seen · 104 lines · 2,586 tokens per session scan A 7adc46124458

Subscribe to this mod's changes

simple-host CLAUDE.md is an instructions file published in the GitHub repository vineetu/simple-host (1 stars, last pushed today), licensed MIT. It adds 2,596 tokens to every session, about $0.0104 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens