Borrowing it
Nothing to install: this file belongs to jed1978/ddd-architecture-coach. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jed1978/ddd-architecture-coach/main/CLAUDE.mdgit clone --depth 1 https://github.com/jed1978/ddd-architecture-coachWrote 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.
[](https://agentmods.dev/instructions/jed1978/ddd-architecture-coach/claude-md)<a href="https://agentmods.dev/instructions/jed1978/ddd-architecture-coach/claude-md"><img src="https://agentmods.dev/badge/instructions/jed1978/ddd-architecture-coach/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.
<a href="https://agentmods.dev/instructions/jed1978/ddd-architecture-coach/claude-md"><img src="https://agentmods.dev/badge/instructions/jed1978/ddd-architecture-coach/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01389 | $0.01389 |
| Opus 5 | $0.00694 | $0.00694 |
| Sonnet 5 | $0.00278 | $0.00278 |
| Haiku 4.5 | $0.00139 | $0.00139 |
Grade B, and why
ddd-architecture-coach CLAUDE.md scanned grade B with 1 finding 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 8d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
Most files are `chmod 444` (read-only) on disk. If an edit is needed, `chmod u+w` first; the read-only bit signals "stable surface, change deliberately." How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository Nature
This repo is a Claude Code skill, not a software project. There is no build, no test runner, no lint, no package manifest. All artifacts are Markdown — the value is in the prompt content itself.
SKILL.mdis the entry point loaded by Claude Code when the skill activates. Its YAML frontmatter (name,description) controls when the skill triggers — edits there change activation behaviour, not just docs.references/phase{1..4}-*.mdhold the detailed methods/formats for each phase. SKILL.md deliberately defers to them; phase work mustReadthe relevant reference rather than rely on memory.assets/templates/*.mdandassets/commands/*.mdare copied verbatim into a user's.claude/directory at bootstrap.assets/agents/bc-developer.mdis copied to.claude/agents/. Treat everything underassets/as user-facing — not internal coach docs (those live inreferences/).
Most files are chmod 444 (read-only) on disk. If an edit is needed, chmod u+w first; the read-only bit signals "stable surface, change deliberately."
Editing Rules Specific to This Skill
When modifying skill content, the following invariants must be preserved (violating them will break the skill in production):
- SKILL.md frontmatter
descriptionis the trigger surface. It enumerates the slash commands (/arch-coach,/phase-1..4,/arch-learn) and the topical keywords (Bounded Context, Aggregate, AI-ADR…) that Claude Code matches against user prompts. Adding capabilities means updating this description, not just the body. - Bilingual policy — instructions to Claude are written in English; user-facing output is Traditional Chinese with technical terms left in English. Chinese text inside
「...」quotation marks is verbatim output to reproduce, not paraphrasable example copy. - Decision-priority ordering in SKILL.md (Domain correctness > fallback > verifiability > team executability) is referenced by name from the phase files. Re-ordering requires updating downstream references.
- AI veto conditions (four listed in SKILL.md) are referenced by Phase 2's AI-ADR workflow. Keep wording aligned across files.
- File-structure contract —
docs/system/{domain-stories,context-map,touchpoints}.mdanddocs/{bc}/{discovery,decisions,spec}.mdare the artifact paths the skill produces in user projects. Phase files assume these exact paths. - Phase-selection state machine in SKILL.md ("State determination" section) operates on three invocation paths: (a)
/phase-N <BC>with explicit BC arg, (b)/arch-coach <BC>, (c)/arch-coachwith no arg (renders an in-flight summary derived from{coach_output_root}/and asks user to pick).arch-state.mdis gitignored at bootstrap — it is per-developer state holding onlylast_touched: { bc, phase, at }, NOT team coordination. Per-BC commands (/phase-2 <BC>,/phase-3 <BC>) require BC explicitly and do NOT fall back tolast_touched.bc; only no-arg/arch-coachreadslast_touched(as a default-suggestion hint). Phase progress is derived from filesystem (artifact existence +spec.mdfrontmatterstatusfor Phase 3 stability). Adding a phase or step requires updating the state-determination algorithm in SKILL.md and may require updatingarch-state-template.mdonly if the new step changes whatlast_touched.phasecan be.
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.
- 8d ago First seen · 45 lines · 1,389 tokens per session scan B e7339b0a7b2a
ddd-architecture-coach CLAUDE.md is an instructions file published in the GitHub repository jed1978/ddd-architecture-coach (5 stars, last pushed 4mo ago), licensed MIT. It adds 1,389 tokens to every session, about $0.0069 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.