workflow-standalone-schema-agent-crash-and-args-string SKILL.md skillA
workflow-standalone-schema-agent-crash-and-args-string from wan-huiyan/agent-traffic-control is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add wan-huiyan/agent-traffic-control/workflow-standalone-schema-agent-crash-and-args-string@v1.2.0Pins v1.2.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- wan-huiyan/agent-traffic-control
- Path
plugins/agent-traffic-control/skills/workflow-standalone-schema-agent-crash-and-args-string/SKILL.md- Versions recorded
- 1
- Latest version
- v1.2.0, committed Jul 8, 2026
- Size
- 9,450 bytes
- Repository stars
- 3
- License
- MIT
Two failure modes that crash an entire dynamic Workflow (the Workflow tool / multi-agent orchestration scripts) and discard all completed agents' work. Use when: (1) a workflow fails with "Error: agent({schema}): subagent completed without calling StructuredOutput (after 2 in-conversation nudges)" — caused by a STANDALONE/terminal `await agent(prompt, {schema})` that is NOT inside parallel()/pipeline(), so the throw propagates and fails the whole run even though the other agents succeeded; (2)…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Workflow: a standalone schema agent crashes the whole run; and args arrives as a string
## Problem
A dynamic Workflow (the `Workflow` tool's JS orchestration script) can run dozens of expensive
subagents and then **lose the entire run to a single late failure** — discarding all the completed
agents' work — because of two non-obvious script-level fragilities. Both cost a failed launch each;
the second can throw away a near-complete, six-figure-token run on one agent's hiccup.
## Context / Trigger Conditions
- **Mode A — terminal schema agent.** The run fails at the very end with:
`Error: agent({schema}): subagent completed without calling StructuredOutput (after 2 in-conversation nudges)`
Symptom: many agents ran (high `agent_count` / `subagent_tokens`), but `status: failed` and the
workflow returned nothing. The culprit is almost always a **standalone** `const x = await agent(prompt, {schema})`
(e.g. a final "critic"/"synthesis" step) that is NOT wrapped in `parallel()` or `pipeline()`.
- **Mode B — args is a string.** The run fails in `~10ms` at the first line touching `args`, with
…Read the whole file at its exact version.
How to install
mdr add wan-huiyan/agent-traffic-control/workflow-standalone-schema-agent-crash-and-args-string@sha256:fe52432b6fbd0ed6The line at the top of this page pins the label v1.2.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_hdo5o3mqzsnwhw5u)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Jul 8, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9450 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
wan-huiyan/agent-traffic-control · 3 stars · license MIT · pushed 2026-09-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_hdo5o3mqzsnwhw5u GET https://markdownregistry.com/api/v1/resolve?ref=wan-huiyan/agent-traffic-control/workflow-standalone-schema-agent-crash-and-args-string GET https://markdownregistry.com/api/v1/blob/fe52432b6fbd0ed6158f633be664fc62c1a75a195ad1b9f0d47e28dd10456839
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.