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 agentmods add skills/evanl1/aetheredge/aethernpx skills add EvanL1/AetherEdge --skill aethergit clone --depth 1 https://github.com/EvanL1/AetherEdgeWhat 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 | $0.00082 | $0.02548 |
| Opus 5 | $0.00041 | $0.01274 |
| Sonnet 5 | $0.00016 | $0.00510 |
| Haiku 4.5 | $0.00008 | $0.00255 |
Grade A, and why
aether-iot-query 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 yesterday.
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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AetherEdge Runtime Query Skill
Use aether as the primary interface for live AetherEdge runtime data. Energy
models, mappings, rules, commissioning examples, and operator-console guidance
belong to the downstream AetherEMS repository.
Core Rules
- Execute
aethercommands to answer questions about current platform state. - Do not read source code files or SQLite database files to answer live data questions.
- Do not read config YAML files to answer questions about running device data.
- Always add
--jsonwhen you need to parse or chain results. - When
--hostis needed, pass it as a global flag (before the subcommand).
Command Discovery
aether --help
aether <subcommand> --help # e.g. aether alarms --help
aether channels --help
Global Flags
| Flag | Purpose |
|---|---|
--json |
Machine-readable output (suppresses color/banner) |
--host <ip> |
Read-only direct-service diagnostics (e.g. --host 192.0.2.10) |
--verbose |
Debug-level logging |
Authentication
Read-only aether queries require no login on the local interface. Governed
mutations require a signed Admin/Engineer JWT in AETHER_ACCESS_TOKEN plus
explicit --confirmed; talking to a loopback service does not grant write
authority.
Connecting to a Remote Machine
# Option A — SSH (aether lives on the remote machine)
ssh [email protected] 'aether --json alarms list'
# Option B — local aether binary + --host flag
# read-only diagnostics only; requires explicitly protected service ingress
aether --host 192.0.2.10 --json alarms list
Prefer Option A. Browser applications and operator consoles must use the
authenticated aether-api application gateway rather than expose internal
service ports.
Command Map
Channels (io :6001)
aether channels list
aether channels list --json
aether channels status <id>
aether channels health
aether channels points list <channel_id>
aether channels points get <channel_id> <point_type> <point_id>
AETHER_ACCESS_TOKEN='<Admin/Engineer JWT>' aether channels create \
--name <name> --protocol <protocol> --params '<json>' --confirmed
AETHER_ACCESS_TOKEN='<Admin/Engineer JWT>' aether channels update <id> \
--description <text> --expected-revision <revision> --confirmed
AETHER_ACCESS_TOKEN='<Admin/Engineer JWT>' aether channels enable <id> \
--expected-revision <revision> --confirmed
AETHER_ACCESS_TOKEN='<Admin/Engineer JWT>' aether channels disable <id> --confirmed
AETHER_ACCESS_TOKEN='<Admin/Engineer JWT>' aether channels delete <id> \
--expected-revision <revision> --confirmed
What ships with it
49 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- Cargo.toml 2.4 KB
- install.sh 6.9 KB runs code
- README.md 11 KB
- src/alarms.rs 39 KB
- src/channels.rs 80 KB
- src/cloud.rs 11 KB
- src/comtrade.rs 23 KB
- src/core.rs 5.2 KB
- src/core/exporter.rs 31 KB
- src/core/file_utils.rs 14 KB
- src/core/schema.rs 122 KB
- src/core/syncer.rs 88 KB
- src/core/validator.rs 7.0 KB
- src/deploy_mode.rs 2.9 KB
- src/doctor.rs 32 KB
- src/history.rs 22 KB
- src/install_context.rs 17 KB
- src/logs_tui.rs 19 KB
- src/logs.rs 22 KB
- src/main.rs 44 KB
- src/mcp_docs.rs 18 KB
- src/mcp.rs 116 KB
- src/models.rs 8.8 KB
- src/models/client.rs 15 KB
- src/models/csv_loader.rs 1.5 KB
- src/net.rs 24 KB
- src/output.rs 14 KB
- src/pack_artifact.rs 40 KB
- src/routing.rs 29 KB
- src/rules.rs 21 KB
- src/services.rs 32 KB
- src/setup.rs 39 KB
- src/shm_dashboard.rs 11 KB
- src/shm_web.rs 20 KB
- src/shm.rs 57 KB
- src/templates.rs 13 KB
- src/top_draw.rs 13 KB
- src/top.rs 25 KB
- src/transport_security.rs 2.3 KB
- src/utils.rs 3.7 KB
- tests/cloud_enrollment.rs 19 KB
- tests/documented_environment_surface.rs 4.2 KB
- tests/pack_artifact_install.rs 12 KB
- tests/removed_instance_measurement_surface.rs 2.8 KB
- tests/setup_onboarding.rs 26 KB
- tests/sync_ownership_guard.rs 3.7 KB
- tests/test_import_export.rs 14 KB
- tests/test_json_output_is_clean.rs 10 KB
- tests/validation_scope.rs 2.7 KB
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.
- yesterday First seen · 237 lines · 0 tokens per session scan A fea8e0d058a0
aether-iot-query is a skill published in the GitHub repository EvanL1/AetherEdge (3 stars, last pushed 17d ago), licensed Apache-2.0. It adds 82 tokens to every session and 2,548 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
edge-iot
Edge computing, IoT protocols, and embedded systems integration.
ha-merge-queue
Finds open Home Assistant pull requests that are genuinely ready to merge, checking CI, the merge-gate statuses, code-owner approval, merge conflicts, requested changes and unresolved review threads. Use when looking for PRs to merge, doing merge-queue triage, or asking for "quick wins" from the open PR backlog.
bump-dependency
Bumps a Python package dependency across Home Assistant Core integrations, regenerates core requirement files, runs verification tests and prek lint, and prepares a pull request with proper release/compare links.
ha-review
Reviews Home Assistant code changes and provides constructive feedback. Should be used when a review is requested to provide a consistent review behavior and output format. This skill can be used for code reviews in general, not just for GitHub pull requests.
ha-integration-knowledge
Everything you need to know to build, test and review Home Assistant Integrations. If you're looking at an integration, you must use this as your primary reference.
ha-quality-scale-verify
Verifies that a Home Assistant integration follows a specific quality scale rule, checking whether it implements the required patterns, configurations, or code structures defined by the quality scale system. Use when asked to check a rule (e.g. "check if the peblar integration follows the config-flow rule") or to…