Borrowing it
Nothing to install: this file belongs to archcore-ai/cli. 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/archcore-ai/cli/main/CLAUDE.mdgit clone --depth 1 https://github.com/archcore-ai/cliWrote 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/archcore-ai/cli/claude-md)<a href="https://agentmods.dev/instructions/archcore-ai/cli/claude-md"><img src="https://agentmods.dev/badge/instructions/archcore-ai/cli/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/archcore-ai/cli/claude-md"><img src="https://agentmods.dev/badge/instructions/archcore-ai/cli/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 | $0.03334 | $0.03334 |
| Opus 5.5 | $0.01334 | $0.01334 |
| Sonnet 5.5 | $0.00667 | $0.00667 |
| Haiku 4.5 | $0.00333 | $0.00333 |
Grade A, and why
cli 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 1mo 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 — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Read and follow AGENTS.md before creating or editing technical documentation, Archcore documents, CLI help, MCP tool descriptions, prompts, agent instructions, or user-facing Markdown.
The writing policy in AGENTS.md applies two profiles: an ASD-STE100-inspired profile constrains the sentence, and an ISO 24495-1-inspired profile constrains the structure. The document type decides which half binds. The per-type assignment — profile, line format, and metric — lives in the shared Archcore rule concepts/document-prose-canon.
Do not claim formal ASD-STE100 or ISO 24495-1 compliance.
Search Priority
When researching patterns, decisions, or conventions in this project, always search .archcore/ documents first (list_documents → get_document) before grepping the codebase or using external sources.
.archcore/architecture/ holds the structure of the system: system-overview.doc is the map,
package-dependency-direction.rule binds the import graph, process-and-concurrency-model.spec binds
shared state, and advisory-subsystem.doc describes the hook advisories. Read the map before a change
that crosses a package boundary.
.archcore/cli-ui/building-the-cli.doc.md holds the procedures. Consult it before adding a command,
document type, MCP tool, hook, or agent.
Go Code Quality — Mandatory
.archcore/code-quality/ holds the binding coding agreements for this repository. They are not
advisory.
Before you write or edit any .go file in cmd/, internal/, templates/, or main.go, load the
code-quality documents. Load them once per session and keep them in context for the rest of the
session.
- Call
list_documentswithtags: ["code-quality"]. - Call
get_documentfor each returned path. - Apply every clause to the code you write.
The documents and what each one governs:
| Document | Binds |
|---|---|
go-code-quality.rule |
Error handling, exit codes, package layout, imports, allocation, general Go conventions. |
strict-go-naming-conventions.rule |
Every identifier name. Absolute for new code. |
comments-are-the-exception.rule |
Whether a comment is written at all. The default is none. |
fail-open-or-fail-closed-reads.rule |
Every read of settings.json, a host config, the filesystem, or git. |
choosing-an-atomic-write.rule |
Every write that must not be observable half-finished. |
bounded-and-deterministic-output.rule |
Every collection or stream that leaves the process. |
cite-the-governing-document-from-code.rule |
Comments on code that exists because of a recorded decision. |
shared-guards-return-classified-sentinels.rule |
A predicate more than one surface consults. |
rendering-happens-at-the-boundary.rule |
What a domain package returns, and who formats it. |
platform-splits-are-files.rule |
Behavior that differs by GOOS or GOARCH. |
the-shape-of-an-mcp-tool-file.rule |
Every file under internal/mcp/tools/ that adds a tool. |
unit-testing-patterns.guide |
Every _test.go file. |
isolating-the-machine-from-the-test-suite.guide |
TestMain in a package whose code reaches $HOME, XDG state, a host CLI, or git. |
registry-agreement-and-test-seams.guide |
A new registry, a matcher over one, or a test seam into production code. |
in-process-mcp-integration-tests.adr |
Tests that cross MCP tool boundaries. |
e2e-testing-for-cli.idea |
End-to-end coverage layers. Historical record; read the ADR above for current state. |
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.
- 1mo ago Changed · +54 lines · +764 tokens per session 322587168e15
- 1mo ago Changed · +67 lines · +1,042 tokens per session e03131120cdb
- 1mo ago First seen · 162 lines · 1,528 tokens per session scan A 80a2f81513c7
cli CLAUDE.md is an instructions file published in the GitHub repository archcore-ai/cli (66 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 3,334 tokens to every session, about $0.0133 per session on Opus 5.5. 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.
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).
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.
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).
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.
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).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.