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/langerrr/distributed-architect/claude-mdgit clone --depth 1 https://github.com/Langerrr/distributed-architectWrote 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/langerrr/distributed-architect/claude-md)<a href="https://agentmods.dev/instructions/langerrr/distributed-architect/claude-md"><img src="https://agentmods.dev/badge/instructions/langerrr/distributed-architect/claude-md.svg" alt="Measured on agentmods" 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 | $0.01025 | $0.01025 |
| Opus 5 | $0.00513 | $0.00513 |
| Sonnet 5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
distributed-architect 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
distributed-architect — Distributed Systems Reasoning Plugin
A reasoning framework that helps LLMs analyze distributed system changes for correctness. Not a documentation system — a structured thinking process.
Boundary Detector (Always Active)
When working on a distributed system (multiple processes, services, or storage systems communicating), watch for these signals before writing code:
| Signal | You are... | Module |
|---|---|---|
| Changing state/status that another actor (process, human, or AI agent) reads or reacts to | state-mutation |
modules/state-mutation.md |
| Moving data across a serialization, network, or storage boundary | data-lifecycle |
modules/data-lifecycle.md |
| Writing error/retry/timeout handling for cross-component operations | failure-mode |
modules/failure-mode.md |
| Adding a new message type, API call, or event between components | interaction |
modules/interaction.md |
Concurrency signal: Check the project topology file. If the component you're modifying is on the "1" side of a 1:N relationship, also load modules/concurrency.md.
Procedure: Detect signal → read the relevant module → walk its checklist → if topology shows 1:N, run concurrency pass → flag concerns before writing code. No overhead for single-component changes.
Skills
| Command | Phase | Purpose |
|---|---|---|
/dist-check |
Coding | Two-pass boundary + concurrency analysis on code changes |
/dist-design |
Design | Architecture trade-off analysis for distributed decisions |
/dist-debug |
Debug | Backward root-cause tracing from symptoms to cause boundary |
Architecture
Three layers, loaded incrementally to minimize context cost:
Layer 1 — Boundary Detector (above — always loaded with this file): Recognizes when a code change crosses a distributed boundary.
Layer 2 — Reasoning Modules (loaded on demand, ~50 lines each): Five modules covering two dimensions:
- Boundary correctness:
state-mutation,data-lifecycle,failure-mode,interaction - Concurrency correctness:
concurrency(triggered when topology shows 1:N)
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.
- 3d ago First seen · 98 lines · 1,025 tokens per session scan A 99750e3ed7c0
distributed-architect CLAUDE.md is an instructions file published in the GitHub repository Langerrr/distributed-architect (1 stars, last pushed 5mo ago), licensed MIT. It adds 1,025 tokens to every session, about $0.0051 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
dekko CLAUDE.md
Instructions for aahlijia/dekko, covering claude.md, what this project is, working in this repo and evaluation reports: test-repos/reports/.
code-pentester CLAUDE.md
Instructions for ch015/code-pentester, covering claude.md — ch015-pentester, reasoning discipline, project operational rules and tone.
codeweb CLAUDE.md
Claude Code instructions for GhostlyGawd/codeweb: Read CHARTER.md before changing product behavior, public copy, or claims. The charter defines the problem, user, job, non-goals, invariants, and current milestone.
DotNetAnalyzer CLAUDE.md
Claude Code instructions for CartapenaBark/DotNetAnalyzer, covering claude.md, 常用命令, 构建和测试, 打包和安装 and mcp 服务器.
river-review GEMINI.md
Gemini CLI instructions for s977043/river-review, covering gemini instructions (river-review), 必須チェック, gemini-specific tips, prompt assembly and development tips.
ship-it open-pr.instructions.md
Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…