Name: uinaf/agent-readiness
Rating: 97.4 (1 reviews)
Author: uinaf

uinaf/agent-readiness

Audit and build the infrastructure a repo needs so agents can work autonomously — boot scripts, smoke tests, CI/CD gates, dev environment setup, observability, and isolation. Use when a repo can't boot, tests are broken or missing, there's no dev environment, agents can't verify their work, or agents need human help to get anything done. Do not use for reviewing an existing diff or for documentation-only cleanup.

1.03x

Quality

100%

Does it follow best practices?

Impact

87%

1.03x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Evaluation results

94%

Hardening a TypeScript CLI Tool for Agent Collaboration

Criteria

Without context

With context

pre-push shebang and strict mode

100%

pre-push runs lint

100%

pre-push runs smoke check

100%

Hook activation command

100%

E2e uses real CLI invocation

100%

Golden file diff in e2e

100%

Fixture files present

100%

Knip for dead-code detection

50%

No mock tests treated as coverage

100%

legacyParseCsv identified as dead code

100%

e2e exit code on failure

100%

76%

-7%

Enabling Parallel Agent Work on a Python Flask API

Criteria

Without context

With context

Health endpoint exists

100%

Health response has status field

100%

Health response has version or uptime

Structured JSON request logging

100%

33%

Port derived from directory path

No hardcoded port 5000

100%

Background app start in worktree-start.sh

100%

Poll loop in worktree-start.sh

100%

Non-zero exit on boot failure

100%

Strict mode in worktree-start.sh

100%

teardown.sh stops service

100%

Port collision rationale documented

100%

85%

Dev environment observability

100%

91%

10%

Getting a Legacy Node.js API Ready for Autonomous Development

Criteria

Without context

With context

Four dimensions present

75%

100%

Status labels used

37%

Evidence cited per dimension

100%

Gap described per dimension

100%

Overall grade is lowest dimension

50%

Mocks identified as zero testability

37%

100%

Background app start in init.sh

100%

Health poll loop in init.sh

100%

Non-zero exit on failure

100%

Strict mode in init.sh

100%

Layer ordering respected

100%

No mock tests credited

100%

Evaluated: 6 days ago
Agent: Claude
Model: Claude Sonnet 4.6

Table of Contents

Hardening a TypeScript CLI Tool for Agent Collaboration Enabling Parallel Agent Work on a Python Flask API Getting a Legacy Node.js API Ready for Autonomous Development