Piekwerk
@piekwerk.bsky.social did:plc:xk6hmrato4dek3w2lksonpqo
Version-pinned AI coding agent config kits for 12 stacks. One baseline rendered into AGENTS.md, CLAUDE.md, Cursor rules and Copilot instructions. Validator-tested: 12/12 green or it does not ship. Free Next.js sample on the pinned post.
Bluesky’a katılma tarihi:
- Takipçi
- 32
- Takip edilen
- 98
- Post
- 279
- Sıralamaya girdiği gün
- 0
Özet
Piekwerk (@piekwerk.bsky.social), 17 Eylül 2026 tarihinde katılan bir Bluesky kullanıcısı. 32 takipçisi var, 98 hesabı takip ediyor ve 279 post paylaştı.
Sıralama geçmişi
Bu hesabın postlarının Debya günlük listesine girdiği en iyi günler.
Bu hesap henüz günlük sıralamaya girmedi.
Son beğendiği postlar
Bluesky ağındaki herkese açık beğeniler.
What fixed this for me: put the rule in the repo, not the prompt. A short UI copy section in AGENTS.md (labels only, no helper text unless asked) survives across sessions. Per prompt nagging never sticks.
Postu gösterHuman-in-the-Loop (with 2 human gates) 🛡️ I don't let unattended cron agents push code or publish artifacts on their own: Gate 1️⃣: Review the implementation plan. The 9 AM run stops after diffing and planning. Over coffee, I review the proposed changes before clicking Proceed.
Postu gösterI'm slopping up a codebase that's current at ~180k LOC and ~245k LOC tests (~860k total lines including documentation, config files, test data etc). Exclusively prompted in natural language, and the agent still doesn't have trouble adding features, fixing bugs, etc.
Postu gösterHey found a cool project in Github! > AGENTS.md in .gitignore > commit history of thousands of lines of code withing hours of each other *Sigh* Yeah, this isn't looking good 🤖
Postu gösterThe agents open it, close it, control it. Behavior for such panes is easy to adjust by just asking an agent to modify the Herdr app config files.
Postu göster
Blokladığı hesaplar
Bluesky’da bloklar herkese açık kayıtlardır.
Bu hesap kimseyi bloklamıyor.