Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add vasilyu1983/AI-Agents-public --skill dev-contribution-quality-analysisgit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/vasilyu1983/ai-agents-public/dev-contribution-quality-analysis)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/dev-contribution-quality-analysis"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/dev-contribution-quality-analysis/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/dev-contribution-quality-analysis"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/dev-contribution-quality-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.03180 |
| Opus 5 | $0.00018 | $0.01590 |
| Sonnet 5 | $0.00007 | $0.00636 |
| Haiku 4.5 | $0.00004 | $0.00318 |
Grade A, and why
dev-contribution-quality-analysis scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developer Contribution Quality Analysis
Objective, multi-dimensional analysis of code contribution quality from git data. Produces individual deep-dive reports and team calibration comparisons.
Modern Best Practices
- Measure contribution quality through outcomes (churn, duplication, test coverage), not presence metrics
- AI-assisted code is normal; score the output, not the authorship
- GitClear Diff Delta and CodeScene Code Health are the established commit-level quality benchmarks
- Stanford ghost engineering research claims commit content analysis predicts expert quality judgments (r=0.82); study is not peer-reviewed — apply with caution
- Agent Trace (Cursor RFC) is an emerging vendor-neutral standard for AI attribution
- DX Core 4 framework consolidates DORA/SPACE into a unified set of four oppositional dimensions
- DORA 2025 itself reports AI adoption now correlates with higher throughput and a "mirror and multiplier" pattern (seven team archetypes replace prior elite/high/medium/low clusters); do not confuse it with vendor telemetry reports
- Faros AI's 2026 "Acceleration Whiplash" telemetry report (4,000+ teams, distinct from DORA) found bugs per developer up 54% and incidents per PR up 242.7% where AI adoption outran test/review discipline — cite it as Faros, not DORA
- GitClear Jan 2026 (2,172 developer-weeks): power AI users produced 4.2x more durable code than non-users but also showed 9x more churn — AI widened an existing performance gap and its downside, not evidence of uniform uplift
- GitClear "The Maintainability Gap" 2026 (623M code changes) extends this: refactor/moved-code share collapsed to 3.8% YTD 2026 (13% in 2023), copy/paste 15.7% in H1 2026, error-masking constructs +47%, cross-file reuse -35% — use these as the current structural-quality benchmarks
- Treat commits and PRs authored end-to-end by an autonomous coding agent (not just AI-assisted) as a distinct evidence class — see Known Traps
Quick Reference
| Task | Tool / Reference | Command / Path | When |
|---|---|---|---|
| Extract contribution profiles | extract-contribution-profile.py |
python scripts/extract-contribution-profile.py --config config.json |
First step after CSV extraction |
| Sample code quality | sample-code-quality.py |
python scripts/sample-code-quality.py --config config.json |
When repo checkouts available |
| Generate quality report | generate-quality-report.py |
python scripts/generate-quality-report.py --config config.json --mode person |
After profile extraction |
| Understand scoring model | scoring-model.md |
references/scoring-model.md |
Before interpreting results |
| Map findings to CC-* rules | code-quality-sampling-rubric.md |
references/code-quality-sampling-rubric.md |
During code sampling |
| Calibrate against industry | industry-benchmarks.md |
references/industry-benchmarks.md |
When comparing to external norms |
What ships with it
20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 398 B
- assets/person-quality-report-template.md 2.2 KB
- assets/quality-scorecard-template.md 516 B
- assets/team-calibration-template.md 1.1 KB
- data/sources.json 13 KB
- learnings.consolidated.md 609 B
- learnings.md 923 B
- references/ai-attribution-patterns.md 8.7 KB
- references/code-quality-sampling-rubric.md 5.6 KB
- references/contribution-signals-catalog.md 11 KB
- references/industry-benchmarks.md 12 KB
- references/mr-pr-quality-signals.md 4.2 KB
- references/scoring-model.md 13 KB
- scripts/compute-code-rating.py 12 KB runs code
- scripts/config-example.json 4.2 KB
- scripts/extract-contribution-profile.py 39 KB runs code
- scripts/generate-quality-report.py 16 KB runs code
- scripts/README.md 6.1 KB
- scripts/sample-code-quality.py 21 KB runs code
- scripts/test_rating_sync.py 3.4 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 204 lines · 36 tokens per session scan A c92f5ca6099c
dev-contribution-quality-analysis is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (87 stars, last pushed 7d ago), licensed MIT. It adds 36 tokens to every session and 3,180 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
block-no-verify-hook
Configure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-verify and other bypass flags. Use when setting up Claude Code projects that enforce commit quality gates.
turborepo-caching
Configure Turborepo for efficient monorepo builds with local and remote caching. Use when setting up Turborepo, optimizing build pipelines, or implementing distributed caching.
babysit
Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
make-pr-easy-to-review
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".