JavaScript · MIT
clawplays/ospec
Spec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable specs and evidence in your repo. Works with Claude Code, Codex, Gemini, OpenCode, and plain CLI.
★ 452
Stars
25 forks · 0 open issues
—
Growth · stale
We stopped seeing this repository in its topic's top results, so its star count is frozen at the date it was last read. Subtracting from a frozen number would read as zero growth, which would be false, so no rate is shown.
16.8
Momentum / 100
see the breakdown below
7mo ago
Created
last push 2mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | — — no measurable rate |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 9.1 | last push 2mo ago; decays to zero at 180 days |
| Scale | 15 | 7.7 | 452 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 16.8 | capped at 35 because growth is unmeasured |
Detail
| Topics | agentic-aiagentic-codingaiai-agentsai-coding-assistantai-workflowclaude-codeclicodexcoding-agentdeveloper-toolsllmloop-engineeringmcpmodel-context-protocolprompt-engineeringsddspec-driven-development |
| Matched on | Agent Skills & MCP (model-context-protocol) |
| Short window | no snapshot 5–10 days old yet |
| Long window | +0 stars over 26 days = 0.0/day |
| Lifetime average | 2.06 stars/day over 219 days |
| First seen here | 2026-10-11 |
| Last read | 27d ago |