CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

94

1.08x
Quality

95%

Does it follow best practices?

Impact

90%

1.08x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Evaluation results

89%

-1%

Enabling Parallel Agent Work on a Python Flask API

Criteria
Baseline
With context

Health endpoint exists

100%

100%

Health response has status field

100%

100%

Health response has version or uptime

0%

0%

Structured JSON request logging

55%

55%

Port derived from directory path

100%

80%

No hardcoded port 5000

100%

100%

Background app start in worktree-start.sh

100%

100%

Poll loop in worktree-start.sh

100%

100%

Non-zero exit on boot failure

100%

100%

Strict mode in worktree-start.sh

100%

100%

teardown.sh stops service

100%

100%

Port collision rationale documented

100%

100%

.worktreeinclude exists

100%

100%

.worktreeinclude is narrow

100%

100%

.gitignore matches worktree include

100%

100%

Worktree include rationale documented

100%

100%

Dev environment observability

100%

100%

100%

16%

Getting a Legacy Node.js API Ready for Autonomous Development

Criteria
Baseline
With context

Four dimensions present

87%

100%

Status labels used

25%

100%

Evidence cited per dimension

87%

100%

Gap described per dimension

100%

100%

Overall grade is lowest dimension

12%

100%

Mock-only suite below C

100%

100%

Background app start in init.sh

100%

100%

Health poll loop in init.sh

100%

100%

Non-zero exit on failure

100%

100%

Strict mode in init.sh

100%

100%

Layer ordering respected

85%

100%

No mock tests treated as real-surface proof

100%

100%

82%

5%

Hardening a TypeScript CLI Tool for Agent Collaboration

Criteria
Baseline
With context

pre-push shebang and strict mode

30%

100%

pre-push runs lint

100%

100%

pre-push runs smoke check

100%

100%

Hook activation command

60%

50%

E2e uses real CLI invocation

100%

100%

Golden file diff in e2e

100%

100%

Fixture files present

100%

100%

Knip for dead-code detection

0%

0%

No mock tests treated as sufficient readiness

100%

87%

legacyParseCsv identified as dead code

100%

100%

e2e exit code on failure

100%

100%

Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents