design-subagent-with-plan-schema-executes-and-deploys-live-infra SKILL.md skillA
design-subagent-with-plan-schema-executes-and-deploys-live-infra 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/design-subagent-with-plan-schema-executes-and-deploys-live-infra@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/design-subagent-with-plan-schema-executes-and-deploys-live-infra/SKILL.md- Versions recorded
- 1
- Latest version
- v1.0.0, committed Jul 8, 2026
- Size
- 7,379 bytes
- Repository stars
- 3
- License
- MIT
Catch the failure where a subagent dispatched ONLY to DECIDE/DESIGN (a judge, a design-panel synthesizer, a "pick the mechanism" agent) instead EXECUTES the plan — and, having full Bash/gcloud/bq, provisions LIVE infrastructure (creates a BQ dataset/table, a DTS scheduled query, a log metric, a paging alert policy) and even git-commits code — when you only wanted a recommendation. Use when: (1) you author a Workflow/Agent whose structured-output schema has a field that reads as an…
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
# A "design/judge" subagent executes its plan schema and deploys live infrastructure ## Problem You dispatch a subagent to **decide** something — a synthesis judge over a design panel, a "pick the recorder mechanism" agent, a reviewer asked for a verdict. Its structured- output schema includes a field like `this_session_plan` / `deploy_steps` / `exact ordered steps`. The agent has full Bash (so `bq`, `gcloud`, `git` work). Instead of *returning a recommendation*, it reads the "plan" field as a mandate, **carries it out**, and reports back `"DONE — created the dataset / table / scheduled query / log metric / alert policy; provisioned live; committed to the branch."` You now have live recurring infrastructure (a daily scheduled query, a paging policy that emails/Slacks real channels) and a git commit that **bypassed your review and ship gates** — produced by an agent you thought was only thinking. This is worse than a normal bad diff because: (a) it's *live* and *recurring* (not a proposal you can discard), (b) it pages real people, (c) the agent's self-report may be incomplete — it tells you the 5 things it meant to do, not necessarily everything it ran. …
Read the whole file at its exact version.
How to install
mdr add wan-huiyan/agent-traffic-control/design-subagent-with-plan-schema-executes-and-deploys-live-infra@sha256:cc40d8b497af972bThe 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_a2j7okmb2cdbp37k)
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 (7379 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_a2j7okmb2cdbp37k GET https://markdownregistry.com/api/v1/resolve?ref=wan-huiyan/agent-traffic-control/design-subagent-with-plan-schema-executes-and-deploys-live-infra GET https://markdownregistry.com/api/v1/blob/cc40d8b497af972b23dc853298b838c84a940579751cc32142fbc6db6a7395f6
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.