workflow-schema-agent-retry-cap-oversized-payload SKILL.md skillA
workflow-schema-agent-retry-cap-oversized-payload 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-schema-agent-retry-cap-oversized-payload@v1.0.0Pins v1.0.0 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-schema-agent-retry-cap-oversized-payload/SKILL.md- Versions recorded
- 1
- Latest version
- v1.0.0, committed Jul 8, 2026
- Size
- 7,797 bytes
- Repository stars
- 3
- License
- MIT
A dynamic Workflow (the Workflow tool / multi-agent orchestration) parallel()/pipeline() agent that DID all its work returns null and the run reports "StructuredOutput retry cap (5) exceeded — 5 failed calls with no valid output" — NOT because the agent found nothing or was rate-limited, but because its result OBJECT was too large / malformed to serialize in one StructuredOutput call (a big nested array of findings, long SQL/quotes per row), often compounded by a stray closing-tag / truncation…
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 schema agent hits the retry cap on an oversized output — recover its work from the transcript
## Problem
A `Workflow` `parallel()`/`pipeline()` agent forced to emit a `StructuredOutput` schema **completes its
actual work** (e.g. runs all its BQ probes, gathers every finding) but then **cannot emit the result**
because the object is **too large or malformed to serialize in one call**. It burns the retry cap
(default 5), the run logs `StructuredOutput retry cap (5) exceeded — 5 failed calls with no valid
output`, and that agent resolves to `null` inside `parallel()`. The run "completes" N-of-M and the null
looks like "this agent found nothing" — but the work is real and **recoverable**.
This is a *distinct* failure from its siblings: the args are **full, not empty** (rules out the
rate-limit empty-loop), the agent is **inside** `parallel()` so it doesn't crash the whole run (rules
out the terminal-agent throw), and it's an oversized *payload*, not CJK token density.
## Context / Trigger Conditions
- Workflow `<failures>` / result reports: `parallel[i] failed: agent({schema}): StructuredOutput retry
cap (5) exceeded — 5 failed calls with no valid output`.
…Read the whole file at its exact version.
How to install
mdr add wan-huiyan/agent-traffic-control/workflow-schema-agent-retry-cap-oversized-payload@sha256:33cd68b65826ca3cThe line at the top of this page pins the label v1.0.0, 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_2n545defho2egkmj)
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 (7797 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_2n545defho2egkmj GET https://markdownregistry.com/api/v1/resolve?ref=wan-huiyan/agent-traffic-control/workflow-schema-agent-retry-cap-oversized-payload GET https://markdownregistry.com/api/v1/blob/33cd68b65826ca3ce578ef4bdb4201f07b0866230558925c903d44410b015a60
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.