workflow-parallel-fanout-omits-sequential-phases SKILL.md skillA
workflow-parallel-fanout-omits-sequential-phases 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-parallel-fanout-omits-sequential-phases@v1.0.1Pins v1.0.1 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-parallel-fanout-omits-sequential-phases/SKILL.md- Versions recorded
- 2
- Latest version
- v1.0.1, committed Aug 5, 2026
- First version recorded
- Jul 8, 2026
- Size
- 7,239 bytes
- Repository stars
- 3
- License
- MIT
A sequential, stateful multi-agent process (adversarial DEBATE rounds, iterative reflect-then-rebut, staged consensus where step N reads step N-1's peers) silently VANISHES when the task is run under "ultracode" or authored as a Workflow — the run collapses to a parallel find→verify→judge with no reviewer-to-reviewer cross-talk. Use when: (1) you ran "review / red-team / debate X in ultracode mode" and the workflow shows only ~3 stages (review → verify → judge)…
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
# Running a sequential multi-agent process as a Workflow silently drops its sequential phases ## Problem A multi-agent process that depends on **sequential, stateful cross-talk** — adversarial debate rounds, reflect-then-rebut, blind-final-after-debate, any "step N reads step N−1's peer outputs and responds" — **silently disappears** when the task is executed under *ultracode* or hand-authored as a `Workflow`. The result looks like a clean 3-stage **review → verify → judge** with no reviewer-to-reviewer argument, and reads as complete. The judge ends up doing alone the reconciliation the debate was supposed to surface. ## Context / Trigger Conditions - You said "review / red-team / stress-test X **in ultracode**" and the `/workflows` view shows ~3 stages at most: independent review → verify → judge. No debate / reflection / blind-final. - You invoked a multi-phase **skill** (e.g. `roundtable:agent-review-panel`, which *mandates* Phase 5 Debate / 6 Summarize / 7 Blind-Final) but the actual execution was a parallel fan-out — N independent agents, then a judge — with zero agents reading each other's output. …
Read the whole file at its exact version.
How to install
mdr add wan-huiyan/agent-traffic-control/workflow-parallel-fanout-omits-sequential-phases@sha256:53eb8167babadd8bThe line at the top of this page pins the label v1.0.1, 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_27jwq7l6m4rrljzt)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jul 8, 2026 and Aug 5, 2026, about one every 28 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.1 latest | 2026-08-05 | ef4b211 | 7,239 B | A | view · diff |
| v1.0.0 | 2026-07-08 | b0f0d02 | 7,237 B | A | view |
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 (7239 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_27jwq7l6m4rrljzt GET https://markdownregistry.com/api/v1/resolve?ref=wan-huiyan/agent-traffic-control/workflow-parallel-fanout-omits-sequential-phases GET https://markdownregistry.com/api/v1/blob/53eb8167babadd8b7114c1814c478fe21446c6883a1ead398c5b900a7312fe9f
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.