0
/ 100
Good shape overall. A few tweaks would push it into the top tier.
Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI agents to continuously learn from real user interactions.
Top fixes
Highest-impact changes first, ranked by point weight
- 1Tests18pt
Wire your tests to a documented command (e.g. a test script in your build config) so the suite is reproducible.
- 2CI/CD14pt
If your CI lives elsewhere (a private repo that builds this one) or this project is itself a CI/CD tool, mark this check Not Applicable. Otherwise add a GitHub Actions workflow that runs tests on each push. It takes 15 minutes and reassures contributors their changes won't break things.
- 3Reproducibility6pt
Add .github/dependabot.yml with at least one package-ecosystem entry so dependencies are updated automatically.
- 4Issue and PR templates6pt
Add .github/ISSUE_TEMPLATE/ with bug_report.md and feature_request.md to guide contributors. It dramatically improves issue quality.
Working through the fixes? Let every push regrade itself.
The free GitHub App rescans this repo on every push and posts the grade as a commit check, so the score climbs without coming back to rescan by hand.
Scorecard
Every check, grouped by category and sorted worst-first
Documentation
88
Contributing guidance is in the README, not a dedicated CONTRIBUTING.md (−20 pts).
→ Moving it to a CONTRIBUTING.md makes it easier to find and keeps the README focused. A dedicated file earns +47 pts base.
README is present.
README documents how to install the project.
Licensed under Apache-2.0.
Engineering
49
No CI configuration detected in this repository.
→ If your CI lives elsewhere (a private repo that builds this one) or this project is itself a CI/CD tool, mark this check Not Applicable. Otherwise add a GitHub Actions workflow that runs tests on each push. It takes 15 minutes and reassures contributors their changes won't break things.
No issue or PR templates found (−100 pts).
→ Add .github/ISSUE_TEMPLATE/ with bug_report.md and feature_request.md to guide contributors. It dramatically improves issue quality.
Test files detected (benchmark/gdpval/tests).
Lockfile present (uv.lock). Installs are reproducible.
Linter or formatter configured (docs/eslint.config.mjs).
Project health
100
Dependency manifest found (pyproject.toml).
Repository has a description.
Actively maintained (pushed within the last month).
.gitignore present.
Repository health signals
Activity, community, and responsiveness at scan time
Activity
- -Commits (30d / 90d)
- 44Forks
- 0Releases
Community
- -Community health
- -authors own >50% of commits
- 313Watchers
Responsiveness
- -Median issue response
- <1hMedian PR merge time
- 2Open issues
Repository files27 root entries
- .agents
- .claude
- .superpowers
- benchmarkGood: Test files detected (benchmark/gdpval/tests).
- client_dist
- docsGood: Linter or formatter configured (docs/eslint.config.mjs).
- notebooks
- reflexio
- scripts
- tests
- .coderabbit.yaml
- .env.example
- .gitignoreGood: .gitignore present.
- .python-versionGood: Environment pinned via .python-version.
- AGENTS.md
- AI_AGENT_INTEGRATION.md
- CLAUDE.md
- developer.md
- how_to_write_readme.mdGood: README is present.Good: README is well structured with multiple sections.Good: README includes screenshots or visuals. Great for first impressions.Good: README has code examples.Good: README links to a live demo or deployed app.Good: README includes status badges.Good: README documents how to install the project.Good: README documents how to run the project.
- LICENSEGood: Licensed under Apache-2.0.
- Makefile
- pyproject.tomlGood: Dependency manifest found (pyproject.toml).
- pyrightconfig.json
- README.md
- run_services.sh
- stop_services.sh
- uv.lockGood: Lockfile present (uv.lock). Installs are reproducible.
Add this badge to your README
It updates automatically each time the repo is re-graded.
[](https://www.repo-grade.com/report/reflexioai/reflexio)