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/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/archcore-ai/cli/agents-md"><img src="https://agentmods.dev/badge/instructions/archcore-ai/cli/agents-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/agents-md"><img src="https://agentmods.dev/badge/instructions/archcore-ai/cli/agents-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 | $0.03615 | $0.03615 |
| Opus 5.5 | $0.01446 | $0.01446 |
| Sonnet 5.5 | $0.00723 | $0.00723 |
| Haiku 4.5 | $0.00362 | $0.00362 |
Grade A, and why
cli AGENTS.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 — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Agent Instructions
Archcore — project context for this repo
This repo's architecture, decisions, rules, specs and patterns live in .archcore/,
reachable through the Archcore MCP tools. Consult them even on code you think you
know — a decision or rule may already constrain it.
- Touching this repo's real code or behavior → search first; read only what matches.
- A decision was made ("we'll use X", "from now on Y") → record it.
- A module / API / system has no doc — or a search comes back empty → capture it.
- Planning a feature or refactor → scope it against what's already decided.
A .archcore/ may also mount read-only global sources — shared, org-wide
context not shown in the session-start list. list_documents / search_documents
surface them alongside local docs, tagged source_kind: "global". When present,
treat them as defaults a local doc can override — never edit or relate to one.
The search is cheap — lean on it. Skip it only for turns this repo would have no opinion on: syntax trivia, throwaway snippets, pure mechanics.
Archcore + Serena
Applies when the session lists any Serena tool, including a deferred tool that shows only its name.
Session start:
- Before the first code read, search Archcore for accepted decisions, specifications, and rules on the affected area.
- Treat accepted Archcore records as constraints on the change.
- If an accepted Archcore record conflicts with the request, report the conflict to the user.
- Make no code edit until the user resolves the Archcore conflict.
- If the host shows Serena tools by name only, load their schemas through tool search before the first code read.
- Before the first code read, call Serena
initial_instructionsonce per session. - If no Serena project is active, call
activate_projectfor the current repository.
Tool choice:
- To find where a symbol is used, call
find_referencing_symbolsinstead of text search. - To find where a symbol is defined, call
find_symbolinstead of text search. - To inspect a code file, call
get_symbols_overviewbefore reading the whole file. - To read one symbol, call
find_symbolwithinclude_body. - To rename a symbol, call
rename_symbol. - To delete a symbol, call
safe_delete_symbolwhen the toolset has it. - To find a string, JSON key, configuration key, path, or prose phrase, use text search.
- To find a project decision, call Archcore
search_documentsinstead of reading Serena memory.
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 · +730 tokens per session 17d567198df1
- 1mo ago Changed · +18 lines · +201 tokens per session 16301706eb60
- 1mo ago First seen · 306 lines · 2,684 tokens per session scan A e563a15642fa
cli AGENTS.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 3,615 tokens to every session, about $0.0145 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.