Review economics
muratcankoylan/Agent-Skills-for-Context-Engineering
Read from the 49 most recently merged pull requests ·
Pull requests with attributed agent authorship took 2.6× the time to merge of the rest.
≥49%
Attributed
a floor
11
Attributed PRs
38
Other PRs
49
Read
Attributed — the latest 5
#103 Release Long-Horizon Prompting with guide, prompt lab, references, and Pages site
1 reviews · 0h to merge
#102 Release Long-Horizon Prompting with guide, prompt lab, references, and Pages site
0 reviews · 2.2d to merge
#101 Add long-horizon-prompting skill (v2.5.0): pseudo-formal task briefs for long-running and parallel agents
0 reviews · 4h to merge
#98 Add self-improvement-loops skill: RSI, meta-harnesses, and evolutionary scaffold search (v2.4.0)
0 reviews · 1h to merge
#97 chore: polish repo-wide production readiness
0 reviews · 0h to merge
The rest — the latest 5
#115 Update retired Sonnet 4 model id in pipeline template
0 reviews · 12h to merge
#53 fix interleaved-thinking install path
0 reviews · 4.3d to merge
#77 Add latent briefing skill for KV-based agent memory sharing
0 reviews · 0h to merge
#75 fix: score structured ground truth in compression evaluator
2 reviews · 13h to merge
#73 Add DeepWiki link to README
0 reviews · 0h to merge
How this was measured
49% of merged commits carry agent attribution — a floor, not the share; tools that only complete code inline leave no commit trail, so the unattributed side includes AI-assisted work.
Detected: Cursor agent, Claude Code.
“Attributed” means a commit carried an agent’s signature — a co-author trailer, an agent commit identity, or an agent bot account. Tools that only complete code inline leave no such mark, so the other column is “rest”, not “human-written”. Full method and its limits
The badge reads this repo’s current report, so it follows the number.
Tell me when this moves
We re-read muratcankoylan/Agent-Skills-for-Context-Engineering weekly and email only when the number changes materially.
Read your own repos
This one is public. For a private repo, run the same read locally through your own GitHub credentials — nothing is installed and nothing is sent to us.
npx @ambera/review-taxWant this continuously on muratcankoylan/Agent-Skills-for-Context-Engineering — each pull request paired to the task it came from, and the work graded from its review loop rather than its diff size? Claim this repo in Forge
Browse every repo people have read · Read a different repository