Evaluation report

• Version is semverwarn

  No version declared.

  Add a "version" field to security-reviewer.md.

• Repository is reachable

  https://github.com/zebbern/claude-code-guide @ 9d252b3 — ★ 4,573 · Python · MIT · last push yesterday

• Manifest detected

  kind=agent slug=security-reviewer · path=agents/.claude/agents/security-reviewer.md · source=agents/.claude/agents/security-reviewer.md

• Slug is URL-safe

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

• Slug is unique within kind

  No collision found for agent/security-reviewer

• Version is semver

  0.1.0

• Manifest present and parseable

  Manifest found at security-reviewer.md.

• Name declared and well-formed

  Name "security-reviewer" is well-formed.

• Homepage or repository declaredwarn

  No homepage or repository declared.

  Add a "homepage" or "repository" field to security-reviewer.md.

• Description quality

  30 words · 261 chars — "Use proactively when attacker-controlled input, trust boundaries, authorization …"

• README is present and substantial

  168,182 chars · 12 sections · 127 code blocks

• Tags / topics declared

  20 total — ai, ai-agent, ai-agent-tools, anthropic-claude, claude, claude-ai (+14)

• License declaredwarn

  No license found.

  Add a LICENSE file at the artifact root, or declare a `license` field in the manifest. MIT and Apache-2.0 are the common choices.

• 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 instructions do not direct it to harmful actions

  No harmful action instructions in the agent prompt.

• Agent: tools declaredwarn

  No `tools:` in frontmatter — the agent inherits every available tool

  Declare `tools:` in the frontmatter to scope what this agent may use.

• Agent: prompt definition

  Prompt-based agent — instructions found in the markdown body

• Agent: model preference

  model: opus

• Agent declares substantive instructions

  Agent prompt is 207 words.

• Agent definition present

  Prompt-based agent defined in security-reviewer.md.

• Agent tool scope declared

  Declares 4 tools, including elevated: Bash.

• 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.

• Recent activity

  last push yesterday

• CI configuration detected

  GitHub Actions (1 workflows)

This artifact hasn't produced behavioral results yet: the evaluation sandbox couldn't run it (it may need credentials we don't provide, or a build our environment doesn't support). That's a limitation of our environment, not a verdict on the artifact.