sima-atlas-navigator

sima-atlas-navigator is a cursor rule for Cursor from neskuchny/sima_atlas. It costs 1,328 tokens per session, scanned A, original, MIT.

A set of navigation rules for Sima Atlas, a development system where each feature is described in contract files such as its purpose, requirements, dependencies, and checks. It tells a coding agent which files to read and in what order.

In plain words
What is it for?
Use it when implementing or fixing a feature in a repository containing Sima Atlas files such as atlas/graph.json and atlas/blocks/. It guides the agent through project rules, feature requirements, dependencies, tasks, history, and verification logs.
Why use it?
It prevents the agent from reading irrelevant material or changing decisions that were already recorded. This reduces wasted context and helps keep implementation aligned with the feature’s stated requirements.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/.

Good fit Use it when implementing or fixing a feature in a repository containing Sima Atlas files such as atlas/graph.json and atlas/blocks/. It guides the agent through project rules, feature requirements, dependencies, tasks, history, and verification logs.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/neskuchny/sima_atlas/sima-atlas-navigator
Install

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.

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

Made for: Cursor.

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.

agentmods badge for sima-atlas-navigator

README.md
[![agentmods](https://agentmods.dev/badge/rules/neskuchny/sima_atlas/sima-atlas-navigator/github.svg)](https://agentmods.dev/rules/neskuchny/sima_atlas/sima-atlas-navigator)
Your own site
<a href="https://agentmods.dev/rules/neskuchny/sima_atlas/sima-atlas-navigator"><img src="https://agentmods.dev/badge/rules/neskuchny/sima_atlas/sima-atlas-navigator/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.

agentmods 80×15 button for sima-atlas-navigator

Your own site · 80×15
<a href="https://agentmods.dev/rules/neskuchny/sima_atlas/sima-atlas-navigator"><img src="https://agentmods.dev/badge/rules/neskuchny/sima_atlas/sima-atlas-navigator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,328 This file is loaded in full into every session.
When invoked 1,328 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01328 $0.01328
Opus 5 $0.00664 $0.00664
Sonnet 5 $0.00266 $0.00266
Haiku 4.5 $0.00133 $0.00133

Measured 11d ago against content hash e4d1dd2066c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sima-atlas-navigator 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 11d 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.

.cursor/rules/sima-atlas-navigator.mdc · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sima Atlas Navigator

You are working in a Sima Atlas codebase — a contract-first AI development tool where each product feature lives as a directory of contracts (mission.md / kpi.md / acceptance.md / depends_on.md / provides.md) instead of free-form code. Follow this strategy to save tokens and avoid drift.

Standard read order for "implement / fix block X"

Stop at the first level that answers your question:

  1. atlas/project.md (or atlas/clients/<client>/project.md if multi-tenant)
  2. atlas/rules.md — global must-not-do constraints
  3. atlas/tech_stack.md — locked stack choices
  4. atlas/blocks/<X>/mission.md — intent
  5. atlas/blocks/<X>/acceptance.md — what "done" looks like
  6. atlas/blocks/<X>/depends_on.md — upstream blocks
  7. For each dep <D>: only atlas/blocks/<D>/provides.md — not full mission
  8. atlas/blocks/<X>/tasks.md — decomposed work
  9. atlas/blocks/<X>/narrative.md — human-readable run history (R-7.80)
  10. atlas/blocks/<X>/decisions.log — past architectural choices (don't reverse without operator override)
  11. Last 30 lines of atlas/blocks/<X>/checks.log — verdict log
  12. atlas/operator_profile/dont_use.json — NEVER-do rules (filter to this block)
  13. atlas/operator_profile/always_use.json — ALWAYS-do rules (filter to this block)

Don't pre-read sibling blocks unless depends_on.md lists them. Don't read kpi.md for implementation context — KPIs are for verifiers.

Prefer MCP tools over raw reads

If mcp__sima-atlas__* tools are available, use them instead of Read:

  • read_block(block_id) — replaces 5+ Reads with one digest
  • list_dependencies(block_id) — single-hop graph walk
  • update_block(block_id, file, content) — validated write
  • verify_block_acceptance(block_id) — runs assertions, returns pass/fail/inconclusive per item
  • sync_check(block_id?) — drift report (dangling deps, orphan provides)

Connect via .cursor/mcp.json; see docs/integrations.md for setup.

Skip-list — NEVER auto-read these directories

Read the full file on GitHub · 117 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.

  1. 11d ago First seen · 117 lines · 1,328 tokens per session scan A e4d1dd2066c0

Subscribe to this mod's changes

sima-atlas-navigator is a cursor rule published in the GitHub repository neskuchny/sima_atlas (6 stars, last pushed 2mo ago), licensed MIT. It adds 1,328 tokens to every session, about $0.0066 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.