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 dagster-branching-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/dagster-branching-to-orchestra)<a href="https://agentmods.dev/skills/orchestra-hq/orchestra-skills/dagster-branching-to-orchestra"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/dagster-branching-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/dagster-branching-to-orchestra"><img src="https://agentmods.dev/badge/skills/orchestra-hq/orchestra-skills/dagster-branching-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 | $0.00107 | $0.01713 |
| Opus 5.5 | $0.00043 | $0.00685 |
| Sonnet 5.5 | $0.00021 | $0.00343 |
| Haiku 4.5 | $0.00011 | $0.00171 |
Grade A, and why
dagster-branching-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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dagster Branching / Conditional Execution -> Orchestra Condition Expressions
Overview
Dagster expresses conditional execution through ops with multiple Out definitions (is_required=False) that conditionally yield Output(value, "branch_name"). Downstream ops wired to a branch only run when that branch is yielded. There is no trigger_rule and no dedicated branch operator — branching is data-flow driven.
Orchestra replaces this with condition: — a string expression evaluated per task or task group using ${{ expression }} syntax. The expression must be truthy for the task/stage to run. The conversion question is always: is the branch decided at trigger time (use inputs:) or at runtime (use an upstream task's OUTPUTS)?
Mapping Dagster patterns
| Dagster pattern | Orchestra equivalent |
|---|---|
Op with multiple Out(is_required=False), conditional yield Output(..., "name") |
Mutually-exclusive condition: on each downstream stage |
| Branch decided by config | condition: "${{ inputs.x == ... }}" |
| Branch decided by upstream computation | Upstream PYTHON/SQL task with set_outputs: true, downstream condition: on its OUTPUTS |
| "run regardless of upstream status" | treat_failure_as_warning: true upstream + no downstream condition |
DynamicOut fan-out |
Orchestra matrix block (parallel mapping) — not a condition |
| Asset skip when no new data (AutomationCondition) | condition: gated on an upstream output, or a sensor (see dagster-sensors-to-orchestra) |
Condition Expression Reference
Variables available
| Variable | Type | Example |
|---|---|---|
task_groups['id'].all().status |
String | == 'SUCCEEDED' |
task_groups['id'].any().status |
String | == 'FAILED' |
inputs.my_input |
Any | == 'prod' |
ORCHESTRA.CURRENT_TIME |
Timestamp | format_date(ORCHESTRA.CURRENT_TIME, '%H') == '04' |
ORCHESTRA.PIPELINE_RUN_TASKS['task_id'].OUTPUTS['key'] |
Any | == 'expected_value' |
matrix.input_name |
Any | Inside matrix task groups |
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 · 193 lines · 107 tokens per session scan A 623caf20ef97
dagster-branching-to-orchestra is a skill published in the GitHub repository orchestra-hq/orchestra-skills (9 stars, last pushed yesterday), licensed MIT. It adds 107 tokens to every session and 1,713 once invoked, about $0.0004 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.
dagster-branching-to-orchestra compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dagster-branching-to-orchestraorchestra-hq/orchestra-skills | Skill | 9 | yesterday | MIT | A | 107 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| azure-mgmt-botservice-dotnetmicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 78 | Claude Code |
| fastapi-router-pymicrosoft/skills | Skill | 3.2k | yesterday | MIT | A | 46 | Claude Code |
| dev-runtimelangwatch/langwatch | Skill | 5.0k | yesterday | Apache-2.0 | A | 172 | Claude Code |
| api-designericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 105 | Claude Code, Codex |
| migrate-segw-to-raparc-mcp/arc-1 | Skill | 252 | yesterday | MIT | A | 106 | Claude Code |