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/archcore-ai/cli/claude-mdgit clone --depth 1 https://github.com/archcore-ai/cliWhat 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 | $0.01528 | $0.01528 |
| Opus 5 | $0.00764 | $0.00764 |
| Sonnet 5 | $0.00306 | $0.00306 |
| Haiku 4.5 | $0.00153 | $0.00153 |
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 2d 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 — 162 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.
The canonical architecture and how-to reference is .archcore/cli-ui/building-the-cli.doc.md. Consult it before adding a command, document type, MCP tool, hook, or agent.
Archcore Operations
Use Archcore MCP tools for all .archcore/ document operations.
- Create documents with
create_document. - Update documents with
update_document. - Remove documents with
remove_document. - Read documents with
list_documents,search_documents, andget_document. - Manage document relations with
add_relation,remove_relation, andlist_relations.
Do not use direct file-writing tools to modify .archcore/ documents.
Before creating or updating an Archcore document:
- Search existing documents for relevant decisions, rules, specifications, and duplicates.
- Read the applicable document-type guidance.
- Apply the controlled technical writing policy in
AGENTS.md. - Preserve code identifiers, commands, flags, paths, MCP tool names, configuration keys, and literal values exactly.
- Mark unsupported technical claims with
[assumption].
Treat mounted global documents as read-only. Do not edit them or create relations to them.
Managed Blocks
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.
- 2d 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 (62 stars, last pushed 16d ago), licensed Apache-2.0. It adds 1,528 tokens to every session, about $0.0076 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 2026-08-30.
Other instructions, from other repositories
cocoindex AGENTS.md
AGENTS.md instructions for cocoindex-io/cocoindex, covering agents.md, build and test commands, building, testing and code formatting and linting.
apm python.instructions.md
Python development guidelines.
framework AGENTS.md
Instructions for ai-driven-dev/framework, covering agents.md, behavior, communication, action and memory management.
SwarmAI CLAUDE.md
Instructions for xg-gh-25/SwarmAI, covering claude.md, before you push — the local quality gate, commit identity, dev commands and conventions & invariants.
sruja AGENTS.md
Instructions for sruja-ai/sruja, covering ⚡ quick reference (top 5 commands), architecture setup (ai agent workflow), step 1: understand the codebase, step 2: classify the architecture and step 3: generate ide context.
openwebui-extensions CLAUDE.md
Instructions for Fu-Jie/openwebui-extensions, covering 🤖 openwebui extensions, 🤝 project standards, 📖 development guidelines, writing documentation and code standards.