← all publishers

brandhaug

@brandhaug source repo

Report this profile Claim this profile

• 4 skills
• 0 followers
• 9 hours ago last updated

1. ▌
   Deslop · brandhaug bundle

   Deslop a codebase — launch 7 parallel cleanup agents that sweep the scope for slop, from duplicated and dead code to weak types and AI-generation tells, then consolidate findings and apply approved fixes. Use when the user wants to deslop, strip AI slop, run a cleanup or quality sweep, or prep a PR, branch, or directory for review.
   0
   installs
2. ▌
   Write Agents Md · brandhaug

   Write and maintain AGENTS.md (or CLAUDE.md) files as an Intent Layer — a hierarchy of small, dense context files at semantic boundaries that auto-load as architectural context for agents. Use when the user wants to write, create, generate, scaffold, seed, sync, trim, or prune AGENTS.md / CLAUDE.md files, agent context files, intent nodes, intent layer, or architectural memory for agents; or mentions "AGENTS.md hierarchy", "intent layer", "intent nodes", "agent context", "T-shaped context", "dark room problem". Two workflows — `build` (initial capture, leaf-first with SME interview) and `sync` (reconcile affected nodes after code changes — additions, modifications, AND removals). Both end by cutting every touched node to a hard word budget; everything must earn its place.
   0
   installs
3. ▌
   Write Like A Human · brandhaug

   Strip AI writing tropes from prose — negative parallelism ("It's not X, it's Y"), em-dash addiction, "delve"-family vocabulary, punchy fragments, false suspense, signposted conclusions, and ~30 other tells. Use when writing or editing prose meant for humans (blog posts, docs, READMEs, announcements, marketing copy, emails), when the user says text "sounds like AI" or asks to humanize it, or mentions "write like a human".
   0
   installs
4. ▌
   Remove Tautological Tests · brandhaug

   Find and remove tautological tests — change-detector tests that mirror the code under test and break on any refactor without catching defects. Patterns include checksum assertions, mock-theater interaction tests, echo assertions, duplicate-algorithm tests, and snapshots with no oracle. Use when writing or reviewing tests, after a behavior-preserving refactor broke tests, or when the user says tests are tautological, circular, or "just testing the implementation".
   0
   installs