What is sima_atlas CLAUDE.md?

A repository-specific instruction guide for working with Claude Code, an AI coding assistant, in the Sima Atlas project. It explains how the project connects its tools and which project documents to read first.

Use it when asking Claude Code to inspect, change, or run the Sima Atlas codebase, especially when its project tools have not loaded automatically.

It helps the coding assistant find the right project rules and navigation tools before changing code, reducing missed instructions and incorrect edits.

How neskuchny/sima_atlas configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to neskuchny/sima_atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/neskuchny/sima_atlas/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/neskuchny/sima_atlas

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/neskuchny/sima_atlas/claude-md/github.svg)](https://agentmods.dev/instructions/neskuchny/sima_atlas/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/neskuchny/sima_atlas/claude-md"><img src="https://agentmods.dev/badge/instructions/neskuchny/sima_atlas/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/neskuchny/sima_atlas/claude-md"><img src="https://agentmods.dev/badge/instructions/neskuchny/sima_atlas/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 669 This file is loaded in full into every session.

When invoked 669 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00669	$0.00669
Opus 5	$0.00334	$0.00334
Sonnet 5	$0.00134	$0.00134
Haiku 4.5	$0.00067	$0.00067

Measured 9d ago against content hash 6be28cb55376, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sima_atlas 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 9d 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.

CLAUDE.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code in this repo

Claude Code auto-loads two things when opening this repo:

.mcp.json — registers the Sima MCP server (~64 tools). On first session in this directory, Claude Code may ask permission to run node scripts/mcp_atlas_server.mjs. Approve it. Tools become available under the mcp__sima-atlas__* prefix.
.claude/skills/sima-atlas-navigator/SKILL.md — the navigation strategy (read order, MCP tool selection, skip-list, write protocol, stop-signals). Auto-activates whenever you work in a Sima Atlas codebase.

For the canonical version of the navigation strategy, see docs/agent-navigation.md. Both AGENTS.md and .claude/skills/sima-atlas-navigator/SKILL.md are adapters of that one document — keep edits in sync.

If MCP didn't auto-register

claude mcp add sima-atlas node scripts/mcp_atlas_server.mjs

Read order for any task

Start with /atlas/project.md → /atlas/rules.md → tech_stack.md, then the target block's mission.md → acceptance.md → depends_on.md. Stop at the first level that answers the question. Full strategy in docs/agent-navigation.md.

Most-useful MCP entry points

read_block / update_block / verify_block_acceptance — per-block contract operations
list_dependencies — single-hop graph walk
sync_check — drift report (orphan provides, dangling deps)
sima_fill_from_chat — turn a conversation into block proposals
sima_watch_chats — scanner for ~/.claude/projects/, picks up fresh transcripts
enqueue_ingestion / ingest_chat_distillate — queue and apply distilled chat insights into a block's decisions.log / patterns.md (memory pipeline)
accept_proposal / reject_proposal — process pending UI proposals
nightly_consolidation — run all 68 validators
generate_full_bundle — regenerate WIKI / auto_tz / roadmap
build_context_pack — deterministic per-block context for the verifier

Read the full file on GitHub · 59 lines

Changes

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.

9d ago First seen · 59 lines · 669 tokens per session scan A 6be28cb55376

Subscribe to this mod's changes

sima_atlas CLAUDE.md is an instructions file published in the GitHub repository neskuchny/sima_atlas (6 stars, last pushed 2mo ago), licensed MIT. It adds 669 tokens to every session, about $0.0033 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.

Claude Code acceptance testing agent-orchestration ai-agents claude codex

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

sima_atlas: Instructions file for Claude Code