✓It Still Works
  • Home
  • Search
  • Discover
  • Catalogue
  • Categories
  • What changed
  • Developer repos
  • How we check
  • Coding and upskilling
  • Developer utilities
  • Draw and diagram
  • Everyday tools
  • Games and play
  • Images and photos
  • Music and audio
  • Save and convert media
  • Testin category
  • Writing and publishing
  • Cloudflare (4)
  • Vercel (3)
  • GitHub Pages (2)
  • Google Cloud (2)
  • nginx (self-hosted) (2)
  • Google (1)
  • Netlify (1)
712 checks loggedEvery listing, every sweepSign in
Theme
✓It Still Works
Sign in

Every listing is checked on a schedule. No numbers we cannot measure.

How we checkGraveyardSubmit something
  • Discover
  • Catalogue
  • Changes
  • Repos

I understood

verify unfinished agent work before calling it done

Not what you meant?

  • record governance evidence from an AI coding agent
  • review AI-assisted work before trusting it
  • budget agent runs
  • verify agent patches

Tools(5)

verify unfinished agent work before calling it done · stop an agent from signing off on its own work · let agents pass work between themselves instead of routing it yourself · require observable evidence before marking work done

5 listings shown. Every result was live at its last check.

  1. When AI builds the wrong thing, make it recover.

    Why this one

    • verify unfinished agent work before calling it done
    • recover after an AI builds the wrong thing

    On the record

    • Free
    • No signup

    Last checked 2 days ago

    Open↗
  2. A supervised agentic build loop that cannot approve its own work

    Why this one

    • stop an agent from signing off on its own work
    • put a spec through implementation and review without babysitting it
    • get an independent check on a change before it lands

    On the record

    • Free
    • No signup

    Last checked 2 days ago

    Open↗
  3. Agents handle tasks, message each other, and review each other's code

    Why this one

    • let agents pass work between themselves instead of routing it yourself
    • have one agent review another's code before you see it
    • track what a group of agents is doing on a kanban board

    On the record

    • Free
    • No signup

    Last checked 2 days ago

    Open↗
  4. Frontier-style execution discipline for AI coding agents

    Why this one

    • require observable evidence before marking work done
    • keep agent task state across a chat

    On the record

    • Free
    • No signup

    Last checked 2 days ago

    Open↗
  5. Give your lead agent the machinery to run the others

    Why this one

    • gate when work is done
    • orchestrate agent tasks

    On the record

    • Free
    • No signup

    Last checked 2 days ago

    Open↗