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.
curl -O https://raw.githubusercontent.com/neskuchny/sima_atlas/main/.claude/skills/sima-atlas-navigator/SKILL.mdgit clone --depth 1 https://github.com/neskuchny/sima_atlasWrote 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/skills/neskuchny/sima_atlas/sima-atlas-navigator)<a href="https://agentmods.dev/skills/neskuchny/sima_atlas/sima-atlas-navigator"><img src="https://agentmods.dev/badge/skills/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.
<a href="https://agentmods.dev/skills/neskuchny/sima_atlas/sima-atlas-navigator"><img src="https://agentmods.dev/badge/skills/neskuchny/sima_atlas/sima-atlas-navigator.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 | $0.00084 | $0.01532 |
| Opus 5.5 | $0.00034 | $0.00613 |
| Sonnet 5.5 | $0.00017 | $0.00306 |
| Haiku 4.5 | $0.00008 | $0.00153 |
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 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 — 133 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 / etc.) instead
of free-form code.
Before reading anything else, follow this navigation strategy:
1. Standard read order — minimum context, maximum signal
For "implement / fix block X":
atlas/project.md(root) oratlas/clients/<client>/project.md(multi-tenant)atlas/rules.md— global must-not-doatlas/tech_stack.md— locked stack choicesatlas/blocks/<X>/mission.md— intentatlas/blocks/<X>/acceptance.md— how «done» is verifiedatlas/blocks/<X>/depends_on.md— upstream blocks- For each dep
<D>: onlyatlas/blocks/<D>/provides.md atlas/blocks/<X>/tasks.md— decomposed workatlas/blocks/<X>/narrative.md— human-readable run history (R-7.80)atlas/blocks/<X>/decisions.log— past architectural choices (don't reverse)- Last 30 lines of
atlas/blocks/<X>/checks.log— verdict log atlas/operator_profile/dont_use.json— NEVER-do rules (filter to this block)atlas/operator_profile/always_use.json— ALWAYS-do rules (filter to this block)
Stop at the first level that fully answers the question. Don't
pre-read sibling blocks unless depends_on.md lists them.
Note: when invoked through run_block_implementation.mjs, items
9-13 are already pre-injected into your prompt under "## ⚠ Block memory"
— don't re-fetch them.
2. Prefer MCP tools over raw file reads
Sima exposes ~64 MCP tools (prefix mcp__sima-atlas__* when registered via
.mcp.json). The 5 you'll actually need:
read_block(block_id)— full contract digest in one call (replaces 5+ Reads)list_dependencies(block_id)— single-hop graph walkupdate_block(block_id, file, content)— validated write backverify_block_acceptance(block_id)— run all assertions, returns pass/fail/inconclusive per assertionsync_check(block_id?)— drift report (dangling deps, orphan provides)
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 First seen · 133 lines · 84 tokens per session scan A 52111509a743
sima-atlas-navigator is a skill published in the GitHub repository neskuchny/sima_atlas (6 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 1,532 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
index-refresh
Use when an LLM Wiki operation issue requests an index refresh. Rebuild wiki/index.md from the actual wiki tree, reconcile missing/deleted entries, and log counts without editing page bodies.
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.