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/triage/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/triage)<a href="https://agentmods.dev/skills/warpdotdev-demos/cloud-factory-demo/triage"><img src="https://agentmods.dev/badge/skills/warpdotdev-demos/cloud-factory-demo/triage/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/triage"><img src="https://agentmods.dev/badge/skills/warpdotdev-demos/cloud-factory-demo/triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 Excessive Agency · line 147 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00110 | $0.01785 |
| Opus 5 | $0.00055 | $0.00892 |
| Sonnet 5 | $0.00022 | $0.00357 |
| Haiku 4.5 | $0.00011 | $0.00178 |
Grade A, and why
triage scanned grade A with 0 findings 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 9d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triage
Assess the issue passed in the user's prompt and decide exactly one implementation-readiness state:
Ready to implementReady to specNeeds infoWait to implement
The goal is to route work honestly, not to make every issue appear actionable. Base the decision on evidence from the issue tracker, current checkout, and related open issues.
This is a read-only analysis: inspect the issue and codebase but do not mutate the tracker. Return the structured decision described in step 6; the caller applies the label and comment.
Workflow
1. Identify the issue and tracker
Extract the issue URL, key, or number from the prompt. Determine whether it belongs to GitHub Issues, Jira, Linear, or another tracker.
If the prompt does not identify one issue unambiguously, ask the user for the issue rather than guessing.
2. Fetch tracker context
Read the issue using the best available integration, in this order:
- A relevant MCP server or native tracker tool
- The tracker's authenticated CLI, such as
gh - The tracker's API or web page
Fetch:
- Full issue title and description
- Comments and discussion
- Existing labels, status, assignee, project, and linked issues
- Attachments or screenshots when they materially affect understanding
- The tracker's available labels
- Related open issues, including likely duplicates, dependencies, and nearby product work
Do not classify solely from the title. Do not expose credentials or secrets while fetching tracker data.
3. Inspect the current codebase
Confirm the current checkout is the relevant repository. Search the codebase for the affected feature, behavior, terminology, and likely implementation area.
If roadmap.md or vision.md exist at the repository root, read them first. Use them to determine whether the issue aligns with the stated product direction before choosing a state.
Assess:
- Whether the described behavior exists today
- Likely files, services, and systems involved
- Whether the issue has a bounded implementation path
- Dependencies, migrations, platform differences, and testing requirements
- Existing abstractions that make the change cohesive or indicate it does not fit
- Whether the issue aligns with the roadmap and vision (if those documents exist)
- Whether related open issues or active work change the recommendation
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 151 lines · 110 tokens per session scan A 53150703019d
triage is a skill published in the GitHub repository warpdotdev-demos/cloud-factory-demo (122 stars, last pushed 27d ago), licensed MIT. It adds 110 tokens to every session and 1,785 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.