- Home
- Skills
- Agents & Orchestration
- Agents Workflow
More screenshots
Works with the AI Agents you already use
Agents Workflow
Coordinate coding and independent review with the Agents CLI: durable task state, scoped handoffs, recorded checks, and a final human decision.
$5
Agents Workflow
Example session with this skill installed
Check Agents v0.5.1 with race-enabled regression tests and static analysis. Keep the results with the task so I can review them.
- Read your context and instructions
- Compiled the agents workflow
Agents v0.5.1 checks
Regression tests and static analysis passed. The results are recorded with the task for review.
| Check | Result |
|---|---|
| Regression tests with race detection | Passed |
| Static analysis | Passed |
Regression tests
go test -race -count=1 ./...
ok github.com/mekilis/agents
ok github.com/mekilis/agents/cmd/agents
ok github.com/mekilis/agents/internal/app
Static analysis
go vet ./...
Exit code: 0
Review the task
The task keeps the verification commands, output, and exit results together. Review these records before accepting the work.
Connects securely to your tools. The creator never sees your data.
About this skill
Agents Workflow helps your coding assistant use the open-source Agents CLI to keep implementation, review, and verification organized. Define a task, hand work between roles, record findings and test results, and review the outcome before accepting it.
What's included
- Installation and setup instructions for Agents v0.5.1.
- Configuration templates for inspection-only use and Codex/Claude workflows.
- Examples for starting tasks, recording checks, and continuing work across sessions.
Keep work traceable
Agents stores task scope, handoffs, findings, and verification in .agents/. Checks can include the command, output, and exit code, so you can inspect the evidence alongside the changes.
Requirements
Use a local POSIX shell on macOS or Linux, Git, and Agents v0.5.1. Automated roles also require separately installed and authenticated coding providers. Provider subscriptions and API usage are separate from this free skill.
Review your provider's permissions before running it. A limit on role launches does not cap token usage or spending.
Get started
Requires local shell access and separately configured coding providers. Provider permissions determine which files and commands a role can access. Role-launch limits do not enforce a token or spending cap. Use the macOS/Linux setup described in the package.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 12 days ago
Requires
Permissions
File Scopes
Uses the shell to run agreed project checks and read/write access for task records and authorized project changes. Network access supports CLI downloads and configured providers. Provider prompts may include project content. Environment variables support task attribution and provider configuration. File access should match the scope of the task.