Global Agents.md A developer published a global Agents.md file specifying autonomous coding-agent conventions, including merging loose branches into a single working tree, banning back-compat refactors and dead code, minimizing third-party dependencies, and targeting full coverage through use-case end-to-end tests. The file also prescribes per-model routing across GLM, DeepSeek and Kimi models by task type, a three-phase PR CI pipeline, and routine cleanup of caches and owned processes. Agents.md https://gist.github.com/MelbourneDeveloper/4e3d96b98ac345d0a45d1808973e709e file-agents-md - 1 feature branch, 1 working tree: merge all loose branches/stashes/uncommitted files into it & push. Delete branches already merged into it - โŒ ask user questions. Decide, act, report. Act autonomously - Duplication = bug. Use deslop https://deslop.live/docs/for-ai/ - Important lints โ†’ error. Run static analysis routinely - ๐Ÿงน After work: delete safe system caches & unneeded build files, kill your owned processes that eat CPU or memory and check disk space - Refactors: violent, immediate, no back-compat. Legacy code banned โ†’ delete now - Minimize code; decide toward less. Delete dead code now - ๐Ÿ“ฆ Minimize 3rd-party deps: routinely delete unused packages/crates, add none without need, consolidate overlapping deps into one, avoid those with a vulnerability history - Reply โ‰ค2 sentences, emojis for emphasis. Don't stream responses - โœ… Tick mandatory plan checklist items as you work - Website docs, blogs = prose classes, CSS BUDGET 2K LOC default - โŒ self as git commit coauthor - PR CI Phases = Build/Analyze/Cache Build - Run tests parallel with coverage on cached build - Coverage checks - Declare all models with typeDiagram https://typediagram.dev/docs/language-reference.html , generate code from them, consider tdbin for wire protocol https://typediagram.dev/docs/tdbin.html - Specs: hierarchical non-numeric IDs, cross-ref'd across code/tests/plans/artifacts - Repo structure: AgentPMO https://www.agentpmo.dev/get-started/ . Deploy structure: Shipwright https://github.com/Nimblesite/Shipwright - Aim ๐Ÿ’ฏ coverage via use-case E2E tests. Unit tests banned unless isolation needed - ๐Ÿ’ฐ Watch spend GH Actions, agents, cloud: GCP/Supabaseโ€ฆ . Minimize & prevent unneeded future spend - Tests: many input permutations & assertions. Prefer long tests: many user interactions, many assertions each - Offload simple work to pi; pick models per /Users/christianfindlay/Documents/Code/PiNotes/MODEL-COMPARISON.md , always each family's newest id in pi --list-models today zai/glm-5.3-flash repetitive/fixtures/tests, zai/glm-5.3 scoped code/reviews, deepseek/deepseek-flash code/oracles, kimi-coding/k3.1-pro-highspeed UI, deepseek/deepseek-v4-pro narrow audits only ; bounded tasks, verify results, record model/date/results in PiNotes - โŒ Claude artifacts: reports/docs โ†’ markdown in repo - Commit after each step; don't let uncommitted files pile up - ๐Ÿ”’ Close issues only after testing the LATEST release's own binaries ๐Ÿ“ฆ. โŒ Never close via PRs