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 skills add AURORA-NEURO/aurora-agent --skill aurora-backend-setupgit clone --depth 1 https://github.com/AURORA-NEURO/aurora-agentWrote 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/aurora-neuro/aurora-agent/aurora-backend-setup)<a href="https://agentmods.dev/skills/aurora-neuro/aurora-agent/aurora-backend-setup"><img src="https://agentmods.dev/badge/skills/aurora-neuro/aurora-agent/aurora-backend-setup/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/aurora-neuro/aurora-agent/aurora-backend-setup"><img src="https://agentmods.dev/badge/skills/aurora-neuro/aurora-agent/aurora-backend-setup.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 | $0.00082 | $0.00664 |
| Opus 5 | $0.00041 | $0.00332 |
| Sonnet 5 | $0.00016 | $0.00133 |
| Haiku 4.5 | $0.00008 | $0.00066 |
Grade A, and why
aurora-backend-setup 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AURORA backend setup
The aurora-backend plugin launches bioprism-mcp, the MCP server of the
AURORA Agent workspace (259 tools; JSON-RPC 2.0 over newline-delimited stdio;
stdout is JSON-RPC only, diagnostics go to stderr).
Where the backend lives
The plugin's launcher (scripts/aurora-mcp.mjs) resolves the checkout in this
order and refuses with a precise stderr message if nothing matches:
AURORA_AGENT_ROOTenvironment variable~/aurora-agent~/bioprism
A directory qualifies when it contains Cargo.toml. Set AURORA_AGENT_ROOT
when the checkout lives anywhere else.
Build
git clone https://github.com/AURORA-NEURO/aurora-agent
cd aurora-agent
cargo build --release --offline -p bioprism-mcp
The workspace builds offline against pinned versions (.cargo/config.toml
sets net.offline = true); you cannot add external crates. A release build of
the full three-binary set is -p bioprism-cli -p bioprism-mcp -p bioprism-api
and takes a long time (codegen-units = 1, thin LTO) — the MCP server alone is
faster.
Windows gotcha: os error 4551
If a freshly linked binary reports os error 4551 ("never executed"), Windows
Application Control blocked it — the program NEVER RAN, even though cargo
reports a failure. Touch a source file to force a relink and rebuild. In test
suites this silently truncates --workspace totals; a suite that never ran
looks like a suite that failed.
What --root means
The launcher passes --root <checkout>. Root is a confinement boundary:
every path a tool receives resolves inside it — absolute paths, .. traversal,
and symlink escapes are refused. The reference fixtures
(fixtures/fiber-v0.1/radiogenomic_world.json,
fixtures/fiber-v0.1/leakage_query.json) live inside root, so tool calls can
name them by that relative path.
Known caveat: the conformance_run tool bakes a build-machine fixtures path at
compile time; it only works when the checkout has not moved since it was built.
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 · 64 lines · 82 tokens per session scan A 7fb9eadba4bc
aurora-backend-setup is a skill published in the GitHub repository AURORA-NEURO/aurora-agent (1 stars, last pushed today), licensed Apache-2.0. It adds 82 tokens to every session and 664 once invoked, about $0.0004 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.
Other skills, from other repositories
gradient
The Synthesize partner API from the terminal - every endpoint, plus a usage-push ledger, billing drift detection, and alert-to-ticket tracing no other Gradient tool has. Trigger phrases: push usage counts to gradient, sync usage to synthesize, check my synthesize integration status, find unmapped gradient accounts…
microsoft-graph
The maintained single-binary successor to the retiring mgc - every MSP-relevant Microsoft Graph surface, plus an offline store that finds wasted licenses, privileged-access risks, over-privileged third-party app consents, and stale devices no single API call can. Trigger phrases: find unused microsoft 365 licenses…
blazemeter-api-monitoring
Comprehensive guide for BlazeMeter API Monitoring, including test creation, configuration, scripting, integrations, notifications, and management. Use when working with API Monitoring tests for (1) Creating and configuring API tests, (2) Writing custom scripts (Initial, Pre-request, Post-response), (3) Integrating…
diagnose-connectivity
Work out why a 3x-ui client cannot connect, in the order that finds the cause fastest — scope the outage, check the core, the inbound, the client's own limits, routing and outbounds, then the node. Use whenever someone reports "it stopped working", a client cannot connect, a site is unreachable through the proxy, or…
roxyapi
Use RoxyAPI to build or integrate any astrology, divination, or insight feature. RoxyAPI is a multi domain API with Remote MCP under one key. Invoke when the user is building or asking about natal charts, horoscopes, Vedic kundli, panchang, synastry or compatibility, tarot readings, numerology reports, human design…
spotify-exhaustive-feature-sweep
Exhaustive feature sweep across Spotify domains — enumerate all endpoints into quantity-first tool proposals with quota flags and batched GitHub logging.