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 orchestra-hq/orchestra-skills --skill airflow-sensors-to-orchestragit clone --depth 1 https://github.com/orchestra-hq/orchestra-skillsWrote 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/orchestra-hq/orchestra-skills/airflow-sensors-to-orchestra)<a href="https://agentmods.dev/skills/orchestra-hq/orchestra-skills/airflow-sensors-to-orchestra"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/airflow-sensors-to-orchestra/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/orchestra-hq/orchestra-skills/airflow-sensors-to-orchestra"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/airflow-sensors-to-orchestra.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 | $0.00083 | $0.02285 |
| Opus 5.5 | $0.00033 | $0.00914 |
| Sonnet 5.5 | $0.00017 | $0.00457 |
| Haiku 4.5 | $0.00008 | $0.00229 |
Grade A, and why
airflow-sensors-to-orchestra 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 2mo 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Airflow Sensors → Orchestra Sensors Block
Overview
Airflow sensors are tasks that poll an external system until a condition is met, then allow downstream tasks to proceed. In Orchestra, sensors are pipeline triggers — they live in the sensors: block at the pipeline root (not inside pipeline:). When all sensor checks pass, the pipeline run is triggered automatically.
Key difference: Airflow sensors are inline DAG steps. Orchestra sensors are external watchers that start pipeline runs. They use a cron window + polling interval model.
Sensor checks also carry a connection: field — for mapping the sensor's aws_conn_id=/conn_id= to the right Orchestra connection type, see airflow-connections-to-orchestra.
SensorModel Structure
sensors:
<sensor-id>:
name: My Sensor # required, max 100 chars
cron: '0 8 * * ? *' # required — when the check window opens
timezone: UTC # required — IANA timezone
timeout_mins: 60 # required — max 7200; must be < cron interval
frequency_secs: 60 # optional — polling interval (60–600, default 60)
exclude: [] # optional — YYYY-MM-DD dates to skip
run_inputs: {} # optional — inputs to pass when sensor triggers
checks: # required — dict of SensorCheckModel
<check-id>:
integration: SNOWFLAKE # IntegrationsEnum
sensor_type: SNOWFLAKE_QUERY # SensorChecksEnum (see table below)
connection: my_snowflake_12345
parameters:
query: "SELECT COUNT(*) FROM daily_files WHERE date = CURRENT_DATE"
map_outputs: # optional — pipe check results to pipeline inputs
file_count: "result" # pipeline input name → check output field
alerts: # optional — sensor-level alerts
- name: sensor-timed-out
statuses: [FAILED]
destinations:
- integration: SLACK
destination: '#data-alerts'
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.
- 2mo ago First seen · 274 lines · 83 tokens per session scan A df27512d890b
airflow-sensors-to-orchestra is a skill published in the GitHub repository orchestra-hq/orchestra-skills (9 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 2,285 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.
airflow-sensors-to-orchestra compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| airflow-sensors-to-orchestraorchestra-hq/orchestra-skills | Skill | 9 | yesterday | MIT | A | 83 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |