workflow-deterministic-compute-as-script-not-stall-prone-agent SKILL.md skillA
workflow-deterministic-compute-as-script-not-stall-prone-agent 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-deterministic-compute-as-script-not-stall-prone-agent@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-deterministic-compute-as-script-not-stall-prone-agent/SKILL.md- Versions recorded
- 1
- Latest version
- v1.0.0, committed Jul 8, 2026
- Size
- 5,414 bytes
- Repository stars
- 3
- License
- MIT
Use when a Workflow-tool (or background Agent) subagent doing heavy multi-step compute STALLS mid-stream and loses work. Trigger conditions: (1) a workflow agent fails with "API Error: Response stalled mid-stream. The response above may be incomplete" and returns null; (2) a subagent runs many bq/python/tool calls in one long turn and dies before writing/committing; (3) the agent must emit a LARGE structured return (big arrays/objects) and stalls while producing it; (4) recurring stalls…
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
# Move deterministic compute to a direct script; don't lose it to a stalling agent turn ## Problem A Workflow `agent()` (or `Agent(run_in_background:true)`) doing a big job — schema probes + build N tables + prove + enumerate + a large structured return — dies with **"API Error: Response stalled mid-stream. The response above may be incomplete"** and returns `null`. The longer the turn and the larger the structured output, the higher the stall rate. Naively re-running the same monolithic agent just burns the budget rediscovering the same things and stalls again. Observed on one heavy job: **3 agent turns stalled; 0 direct-Python runs stalled.** The heavy work that *needed* an agent (judgment: a binarization/thresholding design decision) was done once; everything deterministic (counting, closed-form stats) was far more reliable as a plain script. ## Context / Trigger Conditions - Workflow/subagent stalls mid-stream, returns null, after meaningful tool use (work may be partially durable). - A single agent prompt asks for build + prove + enumerate + model + write + a big structured return. …
Read the whole file at its exact version.
How to install
mdr add wan-huiyan/agent-traffic-control/workflow-deterministic-compute-as-script-not-stall-prone-agent@sha256:308fcc0a45b8ca19The 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_scjttpqd2fpx5m2m)
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 (5414 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_scjttpqd2fpx5m2m GET https://markdownregistry.com/api/v1/resolve?ref=wan-huiyan/agent-traffic-control/workflow-deterministic-compute-as-script-not-stall-prone-agent GET https://markdownregistry.com/api/v1/blob/308fcc0a45b8ca192df8bf2bd3c0c70b9eac3edadd281ec87135885721a7bccb
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.