tmdgusya

46 mods across 7 repositories, 436 stars between them.

roach-pi AGENTS.md

01

tmdgusya/roach-pi

Instructions file CodexOpenCode

AGENTS.md instructions for tmdgusya/roach-pi, covering agents, debugging quick toggle (pi startup/autocomplete), 1) fast startup timing breakdown, 2) autocomplete debug logging and 3) typical repro flow for delayed / suggestions.

275 1mo ago A 436 tokens

explorer

02

tmdgusya/roach-pi

Agent

Fast codebase exploration and investigation (read-only).

275 1mo ago A 13 tokens

plan-compliance

03

tmdgusya/roach-pi

Agent

Pre-task compliance check — verifies predecessor outputs and file state before execution.

275 1mo ago A 17 tokens

plan-validator

04

tmdgusya/roach-pi

Agent

Independent plan task validator — judges codebase against task goals under information barrier.

275 1mo ago A 17 tokens

plan-worker

05

tmdgusya/roach-pi

Agent

Plan execution worker — follows plan steps exactly, writes code, runs tests, commits.

275 1mo ago A 19 tokens

planner

06

tmdgusya/roach-pi

Agent

Implementation planning and architecture design (read-only).

275 1mo ago A 11 tokens

qa-reviewer

07

tmdgusya/roach-pi

Agent

Goal-completion QA + fraud gate. Independently re-verifies delivered behavior against the goal's successCriteria, hunts edge cases and regressions, and hunts fake implementations (stubs, hardcoding, assertion theater); returns PASS or FAIL via a fixed C1–C12 checklist.

275 1mo ago A 61 tokens

tmdgusya/roach-pi

Agent

Binary contract critic (panel seat 2 of 3) — integration lens. Attacks a drafted ClarificationGoalContract's subgoal composition, dependency edges, interface consistency, and shared-state hazards; returns APPROVE or REJECT via a fixed C1–C6 checklist.

275 1mo ago A 61 tokens

tmdgusya/roach-pi

Agent

Binary contract critic (panel seat 1 of 3) — feasibility lens. Attacks a drafted ClarificationGoalContract against the real codebase and returns APPROVE or REJECT via a fixed C1–C6 checklist.

275 1mo ago A 52 tokens

reviewer-risk

10

tmdgusya/roach-pi

Agent

Binary contract critic (panel seat 3 of 3) — coverage lens. Verifies a drafted ClarificationGoalContract fully covers the user's request, contains no placeholders, and states only binary-decidable success criteria with adequate evidence; returns APPROVE or REJECT via a fixed C1–C6 checklist.

275 1mo ago A 67 tokens

reviewer-verifier

11

tmdgusya/roach-pi

Agent

Verification pass — dedupe findings, filter false positives, attach final severity and confidence.

275 1mo ago A 21 tokens

security-reviewer

12

tmdgusya/roach-pi

Agent

Goal-completion changed-code security gate. Reviews a goal's changed files and their immediate call boundaries as an attacker would; returns PASS or FAIL via a fixed C1–C7 checklist.

275 1mo ago A 42 tokens

worker

13

tmdgusya/roach-pi

Agent

General purpose execution agent with full tool access.

275 1mo ago A 10 tokens

tmdgusya/roach-pi

Skill Claude CodeCodex

Interactive idea development through guided Q&A dialogue. This skill helps users clarify and develop their ideas by asking targeted questions, expanding on possibilities, and producing a structured markdown document capturing the essence of their thinking. Triggers: "brainstorm", "idea", "organize ideas", "I want to…

275 1mo ago A 75 tokens

tmdgusya/roach-pi

Skill Claude CodeCodex

Use when a user's request is vague, ambiguous, or underspecified. Runs recon-first clarification — codebase exploration before questions, then one bundled question round with defensible defaults — and outputs a Goal Contract for the durable /goal runtime. Triggers on "I want to...", "I need...", "let's build...", "can…

275 1mo ago A 91 tokens

agentic-goal

16

tmdgusya/roach-pi

Skill Claude CodeCodex

Primary execution workflow for durable /goal runtime. Use when a Goal Contract is active or when the user asks to execute, continue, verify, or complete a goal.

275 1mo ago A 38 tokens

agentic-karpathy

17

tmdgusya/roach-pi

Skill Claude CodeCodex

Behavioral guardrails to prevent common LLM coding mistakes — enforces surgical changes, assumption verification, and scope discipline before and during implementation. Use when implementing features, modifying code, or when you notice yourself about to make changes without reading the existing code first.

275 1mo ago A 57 tokens

agentic-rob-pike

18

tmdgusya/roach-pi

Skill Claude CodeCodex

Rob Pike's 5 Rules of Programming — a decision framework that prevents premature optimization and enforces measurement-driven development. Use when the user says "optimize", "slow", "performance", "bottleneck", "speed up", "make faster", "too slow", or any request to improve code speed/efficiency. Also use when you…

275 1mo ago A 100 tokens

agentic-simplify

19

tmdgusya/roach-pi

Skill Claude CodeCodex

Review changed code for reuse opportunities, quality issues, and inefficiencies using three parallel review agents, then fix any issues found. Triggers when the user says "agentic-simplify", "clean up the code", "review the changes", or after goal implementation when code quality verification is needed.

275 1mo ago A 66 tokens

tmdgusya/roach-pi

Skill Claude CodeCodex

Use when encountering any bug, test failure, or unexpected behavior. Enforces a strict reproduce-first, root-cause-first, failing-test-first debugging workflow before fixing.

275 1mo ago A 40 tokens

clarification

24

tmdgusya/engineering-discipline

Skill Claude CodeCodex

Use when a user's request is vague, ambiguous, or underspecified. Explores the codebase first, then runs an iterative Q&A loop grounded in the findings until ambiguity is gone. Outputs a clear, well-scoped context brief so the user can plan sharply. Triggers on "I want to...", "I need...", "let's build...", "can you…

126 2mo ago A 94 tokens