EdgeOne Makers Tools is a collection of AI-agent skills and related workflow files for developing and deploying projects on EdgeOne Makers. It covers agent development, deployment, edge and cloud functions, storage, middleware, command-line usage, and project templates. The catalogue entries package these capabilities as skills, rules, instructions, a hook, and a plugin for coding agents.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/TencentEdgeOne/edgeone-makers-toolsnpx agentmods add rules/tencentedgeone/edgeone-makers-tools/makers-cliWrote 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/rules/tencentedgeone/edgeone-makers-tools/makers-cli)<a href="https://agentmods.dev/rules/tencentedgeone/edgeone-makers-tools/makers-cli"><img src="https://agentmods.dev/badge/rules/tencentedgeone/edgeone-makers-tools/makers-cli/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/rules/tencentedgeone/edgeone-makers-tools/makers-cli"><img src="https://agentmods.dev/badge/rules/tencentedgeone/edgeone-makers-tools/makers-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00024 | $0.00765 |
| Opus 5.5 | $0.00010 | $0.00306 |
| Sonnet 5.5 | $0.00005 | $0.00153 |
| Haiku 4.5 | $0.00002 | $0.00076 |
Grade A, and why
edgeone-makers-cli 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 1mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EdgeOne Makers CLI Reference
Install
npm install -g edgeone
Verify: edgeone -v
Commands
| Command | Description |
|---|---|
edgeone makers dev |
Start local dev server (agent runtime + frontend) |
edgeone makers build |
Build agents + frontend into .edgeone/ |
edgeone makers deploy |
Build and deploy to EdgeOne Makers |
edgeone makers deploy -n <name> |
Deploy as a new project |
edgeone makers deploy -t <token> |
Deploy with API token (CI/headless) |
edgeone makers deploy -e preview |
Deploy to preview environment |
edgeone makers deploy --anonymous --json |
Deploy without login; claim later (CLI ≥ 1.6.29) |
edgeone makers deploy --anonymous --site china|global --json |
Anonymous deploy to a specific site (omit --site to auto-detect by IP) |
edgeone makers claim --sid <token> |
Claim an anonymously-deployed project (requires login) |
edgeone makers link |
Link local project to remote EdgeOne project |
edgeone makers env pull |
Pull remote env vars to local .env |
edgeone makers env set <KEY> <VALUE> |
Set a remote environment variable |
edgeone makers env ls |
List remote environment variables |
edgeone makers env rm <KEY> |
Remove a remote environment variable |
edgeone login |
Login (browser-based) |
edgeone login --site china |
Login to China site |
edgeone login --site global |
Login to Global site |
edgeone login --claim --local --json |
Background listener: prints the login+claim link for an anonymous deploy, then auto-links the claimed project |
edgeone whoami |
Check current login status |
Anonymous deploy and
claimrequire CLI>= 1.6.29(the general CLI floor is1.6.0). The claim parameter is--sid(the anonymous token);-tis the account API token — they are different credentials. Tell the user the link expires in 60 minutes; never show the rawexpiresAt. The claim link you present comes fromedgeone login --claim(claimLoginUrl), not the bareclaimUrlin the deploy JSON. Details: makers-deploy/references/anonymous-deploy.md.
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.
- 1mo ago Changed · +6 lines c436b3147e80
- 1mo ago First seen · 72 lines · 24 tokens per session scan A 36fd9954357b
edgeone-makers-cli is a cursor rule published in the GitHub repository TencentEdgeOne/edgeone-makers-tools (1,851 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 765 once invoked, about $0.0001 per session on Opus 5.5. 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 cursor rules, from other repositories
beanstalk-deploy
Robust deployment patterns for Elastic Beanstalk with GitHub Actions, Pulumi, and edge case handling.
aws-ecs
Definitive guidelines for building, deploying, and operating applications on AWS ECS, emphasizing immutable containers, secure secrets management, and robust operational patterns.
aws-rds-best-practices
AWS RDS PostgreSQL best practices - database configuration, connection management, authentication, backup, and performance optimization standards.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.