Borrowing it
Nothing to install: this file belongs to warpdotdev-demos/cloud-factory-demo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/warpdotdev-demos/cloud-factory-demo/main/.agents/skills/oz-cloud-factory-demo/SKILL.mdgit clone --depth 1 https://github.com/warpdotdev-demos/cloud-factory-demoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/warpdotdev-demos/cloud-factory-demo/oz-cloud-factory-demo)<a href="https://agentmods.dev/skills/warpdotdev-demos/cloud-factory-demo/oz-cloud-factory-demo"><img src="https://agentmods.dev/badge/skills/warpdotdev-demos/cloud-factory-demo/oz-cloud-factory-demo/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/warpdotdev-demos/cloud-factory-demo/oz-cloud-factory-demo"><img src="https://agentmods.dev/badge/skills/warpdotdev-demos/cloud-factory-demo/oz-cloud-factory-demo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 22 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 68 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 214 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 236 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 69 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 215 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 310 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 70 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 216 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 310 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 71 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 217 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 310 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 72 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 218 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 310 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 73 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 219 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 237 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 74 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 220 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00079 | $0.05847 |
| Opus 5 | $0.00039 | $0.02923 |
| Sonnet 5 | $0.00016 | $0.01169 |
| Haiku 4.5 | $0.00008 | $0.00585 |
Grade A, and why
oz-cloud-factory-demo scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `curl` How it starts
The opening of the file, as written. The whole thing — 384 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oz Cloud Factory Demo
Guide a user who is new to Oz through setting up this flow in a GitHub repository:
new issue -> Oz triage (+ optional verify-behavior reproduce) -> Ready to spec label -> Oz spec -> PRODUCT.md + TECH.md PR -> Oz implementation (+ optional verify-behavior verify, with parallel story fan-out for features) -> pull request -> Oz review (+ optional verify-behavior)
Use the canonical installer and workflows from warpdotdev-demos/cloud-factory-demo. Explain each action before taking it, keep secrets out of output and files, and stop at explicit activation checkpoints.
Success criteria
The setup is complete when:
- The target repository contains the
triage,spec,write-product-spec,write-tech-spec,validate-changes-match-specs,implementation, andverify-behaviorskills. - The target repository contains the three Cloud Factory GitHub workflows.
- The repository has an Oz API key stored as the
WARP_API_KEYActions secret. A team key is preferred for shared automation, but a personal key is supported and may be necessary when creating keys through the Oz CLI. - If using a team key, the Warp team has team GitHub authorization configured so implementation runs can push branches and open pull requests. If using a personal key, runs authenticate as that user and use that user's GitHub permissions.
- The setup is committed and pushed to the repository's default branch.
- A newly opened test issue triggers triage and receives exactly one triage-state label.
- Applying
Ready to spectriggers spec work and, for a suitable issue, opens a PR containingPRODUCT.mdandTECH.md. - Applying
Ready to implementtriggers implementation and, for a suitable issue, produces a pull request.
Important concepts to explain
- Oz runs agents and records their runs. Each run consumes Warp credits.
- Skills are reusable agent instructions checked into
.agents/skills/. - GitHub Actions provides the event triggers and repository checkout for this demo.
- Triage classifies each new issue as
Ready to implement,Ready to spec,Needs info, orWait to implement. - The triage workflow runs the agent read-only: a first job grants the agent only
contents: readandissues: readand has it emit a structured JSON result, and a second deterministicapplyjob (issues: write) applies the label and comment to the triggering issue only. The agent never holds issue-write access, so it cannot modify other issues. - Verification (
verify-behavior) is a shared skill other stages invoke as Oz cloud subagent work. It chooses browser use (Chrome + Puppeteer MCP) for most web flows or computer use for native apps and multi-surface journeys. Triage can use it inreproducemode for UI bugs; implementation and review can use it inverifymode for greenfield features and fixes. WhenPRODUCT.mddefines multiple user stories, feature verification defaults to parallel story fan-out with computer-use-capable workers. Default evidence is video of each critical path, with screenshots as keyframes or fallbacks. - Spec runs when the issue receives a ready-to-spec label, delegates spec content to the common
write-product-specandwrite-tech-specskills, and opens a specs PR containingPRODUCT.mdandTECH.md. - Implementation runs only when the issue receives a ready-to-implement label. If
PRODUCT.mdandTECH.mdspecs exist, it reads them first and usesvalidate-changes-match-specsto check the completed diff against the specs before opening a PR. For visible UI features or fixes it should also invokeverify-behaviorinverifymode when cloud verification is available. - The implementation workflow has permission to create branches and pull requests. It does not merge them.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 384 lines · 79 tokens per session scan A aa0fd67f777c
oz-cloud-factory-demo is a skill published in the GitHub repository warpdotdev-demos/cloud-factory-demo (122 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 5,847 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
import-prom-rule
Bulk import of a Prometheus alert rule YAML file (create a whole set of rules at once). Dedicated to handling a remote URL or local YAML text, automatically parsing the three formats groups / a plain rules array / a single rule. ⚠️ Do not use this skill for single-rule creation — when the user describes a single alert…
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
configure-env-variables
Configures environment variables for Power Pages site settings to support ALM across environments. Creates environment variable definitions in Dataverse, guides the user through linking site settings to those variables via the Power Pages Management app, adds the variables to the solution, and generates a…
atmos-profiles
Atmos profiles: profile directories, --profile and ATMOSPROFILE activation, profile merge behavior, environment switching, and routing profile-specific auth/toolchain/config overrides.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.