Dag Fanout
Hand-written lens-spec fanout: you author the lenses (persona + sub-angles), the engine runs them concurrently and judges. Manual gearbox of dag-council. Trigger: fanout with my own lenses / 手写 lens / 我已明确要哪几个视角 / dag-fanout. Skip: want the conductor to author lenses automatically (/dag-council, the default) / web research (/dag-research).
Install
$ agentstack add skill-abysscn-oh-my-dag-dag-fanout ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-abysscn-oh-my-dag-dag-fanout) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
/dag-fanout — hand-written lens fanout
When you already know exactly which expert perspectives you want, write them down and skip the conductor: each lens (persona + V sub-angles) runs concurrently over the same question + ground truth, then reduce → synthesis → judge.
Usage
bun run dag-fanout // spec.json
{
"question": "…",
"groundTruth": "…", // shared evidence base fed to every lens
"lenses": [
{ "key": "operator", "persona": "…", "subAngles": ["…", "…"] },
{ "key": "risk", "persona": "…", "subAngles": ["…"] }
],
"synthesisFramings": ["…"], // optional
"judgeCriteria": ["…"], // optional; default includes factual/engineering correctness
"lensModel": "provider:model", // optional (env OMD_LENS_MODEL)
"reasonModel": "provider:model" // optional (env OMD_REASON_MODEL)
}Artifact: /tmp/dag-fanout--.md.
Discipline
Diversity > volume: sub-angles must be different questions, not the same prompt resampled — resampling has diminishing returns; orthogonal angles don't.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: AbyssCN
- Source: AbyssCN/oh-my-dag
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.