Evaluation report

• Repository is reachable

  https://github.com/cheddarfox/safe-agentic-workflow @ adb3670 — ★ 3 · MIT · last push 6 months ago

• Manifest detected

  kind=agent slug=bsa · path=.claude/agents/bsa.md · source=.claude/agents/bsa.md

• Slug is URL-safe

  "bsa" matches /^[a-z0-9][a-z0-9-]{0,62}$/

• Slug is unique within kind

  No collision found for agent/bsa

• Version is semver

  0.1.0

• Description quality

  11 words · 91 chars — OK but more detail helps

• README is present and substantial

  65,604 chars · 18 sections · 24 code blocks

• Tags / topics declared

  7 total — read, write, edit, bash, grep, glob (+1)

• README has usage / example sections

  found: Quick Start · Getting Started · Installation

• Homepage / docs URL declared

  https://jscottgraham.us

• LICENSE file at repo root

  LICENSE

• No sensitive files in the repo

  scanned for .env, credentials.json, *.pem, .ssh/, AWS / GCP configs — none found

• Agent: prompt definition

  Prompt-based agent — instructions found in the markdown body

• Agent: tools declared

  7 declared: Read, Write, Edit, Bash, Grep

• Agent: model preference

  model: opus

• Recent activitywarn

  last push 6 months ago — looks slowing down

  Consumers prefer artifacts that are actively maintained (threshold: 90 days, configurable via EVAL_RECENCY_PASS_DAYS).

• Tests detectedwarn

  no test/tests/__tests__/spec/t/ dirs, no JVM src/test/, and no JS/TS/Python/Go/Ruby/Elixir test files

  Add tests (even a smoke test). Consumers gauge maintenance quality by their presence.

• CI configuration detected

  GitHub Actions (3 workflows)

Behavioral results aren't published for this artifact. The publisher sees the full report on their own dashboard.