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/rewritingthecode/workshop/claude-mdgit clone --depth 1 https://github.com/RewritingTheCode/workshopWhat 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 | $0.00842 | $0.00842 |
| Opus 5 | $0.00421 | $0.00421 |
| Sonnet 5 | $0.00168 | $0.00168 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
workshop 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Portfolio Starter - Project Rules
A single-page personal portfolio. Built live during RTC's "How RTC Builds Real Software with AI" workshop, and yours to keep extending afterward.
The loop
Every change follows the same five steps. No exceptions, including for small changes.
- Context - ask what this is and who it is for, before proposing anything
- Spec - write the decision down as an ADR in
docs/adr/, before writing code - Build - implement the ADR. The ADR is the instruction.
- Validate -
npm run check. Look at it at 320px wide. - Ship -
npm run deploy. It is not done until it is on the internet.
Content
All personal content lives in src/content/profile.ts and must satisfy
src/content/schema.ts. Never add a second source of truth for content. Never hardcode a name,
a job title, or a date into a component.
That includes index.html. Its <title> and meta description are filled in from profile.ts
at build time by the plugin in vite.config.ts - see src/content/metadata.ts. Leave the
__PAGE_TITLE__ and __PAGE_DESCRIPTION__ tokens alone.
Page section order is content too: profile.sections is the order of the page and of the
anchor nav. Adding a section means adding its id to SECTION_IDS in the schema and an entry
in src/components/sections.tsx - never a hand-placed component in Page.tsx. See
docs/adr/ADR-006-section-order.md.
Never invent content. If information is not in the source the user gave you, leave the field out. This is a public portfolio - a fabricated job or project is a serious problem, not a formatting detail.
Code
- React 19 + TypeScript + Tailwind v4 + Vite. Match the existing patterns in
src/components/. - Mobile first. Start at the phone layout with no prefix, add width at
sm:andmd:. - It must work at 320px. No fixed widths in the page shell.
- Real semantics: one
<h1>, headings that do not skip levels,<nav>for the nav,<button>for buttons. Never a<div>with an onClick. - Visible focus states on everything interactive.
- Keep files under 200 lines. Split a component before it gets long.
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 · 75 lines · 842 tokens per session scan A 84b4230b7905
workshop CLAUDE.md is an instructions file published in the GitHub repository RewritingTheCode/workshop (10 stars, last pushed 5d ago), licensed MIT. It adds 842 tokens to every session, about $0.0042 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
magicui AGENTS.md
Instructions for magicuidesign/magicui, covering project context, key principles, before writing code, rules and accessibility (a11y).
core CLAUDE.md
Claude Code instructions for module-federation/core, covering claude task parallelization & development guidelines, core principles, maximum parallelization strategy, universal parallel task patterns and for any codebase task.
orval AGENTS.md
AGENTS.md instructions for orval-labs/orval, covering using vite+, the unified toolchain for the web, built-in commands vs scripts, tool versions and review checklist.
ui-components AGENTS.md
Instructions for starc007/ui-components, covering beui v2 — agent guide, commands, layout, component catalog and components (motion category — primitives).
personal-site AGENTS.md
Instructions for mldangelo/personal-site, covering agents.md, quick commands, project structure, code style and git workflow.
deepseek-pp AGENTS.md
Instructions for zhu1090093659/deepseek-pp, covering deepseek++ project agent instructions, scope, product context, truth sources and collaboration rules.