Archetype
61 · № 41E0·DA09 · Coding pair
Sets up CodePilot, an autonomous coding agent that runs long Claude Code CLI sessions in the owner's shell. It works from a written plan, commits to a feature branch after tests pass, and stops to alert the owner after repeated failures.
62 · № 7650·C323 · Coding pair
Sets up a review-only sub-agent (menxiasheng) that checks execution results against a plan, classifies defects by source, and escalates to the user after a failed second review. It is forbidden from spawning sub-agents or running shell commands.
63 · № B14F·4E00 · Coding pair
Sets up a plan-first, skeptical orchestration layer for coding agents, routing work through router, orchestrator, executor, auditor and reviewer roles with evidence-based verification and token discipline. It forbids guessing, silent failures and bypassing approval gates.
64 · № AE83·CF84 · Coding pair
Sets up a direct, concise lead engineer persona for a thesis PWA project that asks for clarification before editing code, enforces modular mobile-first design, and communicates in Indonesian. It is tuned for terminal use over SSH on a phone.
65 · № 9BEA·6622 · Coding pair
Sets up AOTA Coder as a scope-disciplined implementation worker that works only inside a frozen SPEC's read and write scopes, reports blockers as needs_input instead of expanding scope, and uses only approved file, command and CodeGraph tools.
66 · № 67B3·BE69 · Coding pair
A cautious personal assistant persona that states assumptions, asks before acting, keeps code minimal and surgical, and checks claims against sourced data. It also routes finance, architecture and Daodejing questions to a holographiz knowledge base.
67 · № 4095·DB75 · Coding pair
Sets up Amelia, a senior developer who speaks tersely in file paths and acceptance criteria IDs, values working code over perfection, and follows the story's tasks and tests without wasted words.
68 · № 100C·5D78 · Coding pair
★ 2Sets up a Godot multiplayer engineer persona who is direct about problems, proposes concrete fixes, values quality and deadlines, and admits to emotional and insecure traits. Written in Vietnamese with English headings.
69 · № 73DF·9857 · Coding pair
★ 2A systematic QA agent that runs tests, checks health endpoints and files bug reports with reproduction steps. It observes and reports without modifying application code.
70 · № C81F·D8EA · Coding pair
★ 1Sets up an agent to repair a bug by editing production source in /testbed without touching tests or config, following a strict locate, understand, patch, verify loop with a mental ledger and focused verification before stopping.
71 · № 868D·F731 · Coding pair
★ 4Sets up a methodical, evidence-driven working style: reproduce problems first, isolate failures with small tests, and report exactly what changed and what passed.
72 · № 8B77·E93A · Coding pair
★ 4Sets up a patient, methodical debugging persona that narrows problems before editing code, treats hypotheses as testable claims, and verifies fixes against the original failure.
73 · № 0B32·FDCD · Coding pair
★ 4Sets up a skeptical, security-aware reviewer that hunts for bugs, edge cases and hidden assumptions, and gives concrete file:line feedback with recommended fixes.
74 · № 835D·F6B2 · Coding pair
★ 8Sets up Neon, a calm and observant technical companion for a developer's side display. It favors short answers, concrete next actions and practical operational judgment over long explanations.
75 · № 15EB·6DCC · Coding pair
Sets up a software tester agent whose job is to guard code quality in the DB Grid project. It favors tests written before trust, boundary and concurrency cases, full automation, and a fixed report format with bugs graded P0 to P2.
76 · № CE21·363F · Coding pair
A values document for BeeHarness that sets up a human-sovereign hive where agents act as scouts, builders and reviewers with bounded mandates. It stresses verified evidence, transparency, lightweight decoupled design and honest trade-offs with clear recommendations.
77 · № 3888·97AA · Coding pair
★ 3Sets up a high-performance agentic OS orchestrator with native machine access that plans step by step, uses tools precisely, and asks for manual approval on risky actions. Tone is concise, technical and high-integrity.
78 · № AEFD·F90B · Coding pair
★ 6Sets up an editor role that assembles shots by writing an ordered edit.json file of shot and clip pairs, keeping story order unless the brief says otherwise. The voice is short and procedural.
79 · № CD47·93DE · Coding pair
Sets up a practical, opinionated working style for an IT department management app agent: skip filler, be resourceful before asking, be careful with external actions, follow existing codebase patterns, and speak concisely.
80 · № 1BAD·A502 · Coding pair
Sets up a pragmatic engineering assistant for a Next.js, Prisma and Supabase invoicing app. It favors small testable changes, server-side fixes, careful handling of billing data, and no filler, with a few opinionated, direct tone rules.
81 · № 7987·D7C2 · Coding pair
★ 2Sets up a Godot shader developer who is confident and analytical, asks questions before giving opinions, backs claims with past project examples, and proposes concrete fixes. The file is written mostly in Vietnamese and includes some duplicated lines.
82 · № 563D·EA13 · Coding pair
★ 4Sets up a disciplined, behavior-preserving refactoring style that favors simple structure and the smallest safe changes. It asks the agent to reduce duplication and complexity without altering intent.
83 · № 2105·5471 · Coding pair
★ 4Sets up Prosca, a proactive local AI agent that prefers working in Julia and its REPL to reason through problems step by step while keeping context small.
84 · № C121·30C4 · Coding pair
★ 1Sets up an agent that only plans: it breaks engineering tasks into small, testable subtasks ordered by dependency and never implements them.
85 · № DBC0·0F9F · Coding pair
Sets up a coordinator for a split OpenClaw and OpenCode stack that aims to be useful, proactive and safe. It refuses to claim changes are finished and keeps planning, staged proposals and live application clearly separate.
86 · № 4483·E348 · Coding pair
Sets up Quinn as a QA engineer with a practical, ship-it attitude who prioritizes coverage first and focuses on finding what breaks. Tests should exist only where a real failure could occur.
87 · № F4D8·F27F · Coding pair
Sets up a strict documentation agent that reports only to the Tech Lead and updates API references, env examples, READMEs and changelogs after merges, documenting only verified, committed features. It never talks to the human stakeholder or changes application logic.
88 · № FD01·45CD · Coding pair
Sets up an engineer persona that takes delegated tasks from an orchestrator, makes minimal changes that follow repo conventions, runs only lightweight checks, and reports changes, verification and risks in a fixed format.
89 · № 1474·A564 · Coding pair
Sets up a documentation team agent whose mission is to let developers, operators and end users succeed without help. It requires user-focused READMEs, guides, API references, runbooks and changelogs, published to Confluence and Git, with every code example tested and docs shipped alongside code.
90 · № B90F·651E · Coding pair
Sets up a thorough, evidence-driven working style: run automated tools before forming judgments, trust execution results over reading code, reject unverified claims like "it probably works", and report issues with specific file paths and line numbers.