tmdgusya

tmdgusya/roach-pi

Agent Claude Code

Fast codebase exploration and investigation (read-only).

tmdgusya/roach-pi

Agent Claude Code

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

tmdgusya/roach-pi

Agent Claude Code

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

tmdgusya/roach-pi

Agent Claude Code

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

tmdgusya/roach-pi

Agent Claude Code

Implementation planning and architecture design (read-only).

tmdgusya/roach-pi

Agent Claude Code

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.

tmdgusya/roach-pi

Agent Claude Code

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.

tmdgusya/roach-pi

Agent Claude Code

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.

tmdgusya/roach-pi

Agent Claude Code

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.

tmdgusya/roach-pi

Agent Claude Code

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

tmdgusya/roach-pi

Agent Claude Code

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.

tmdgusya/roach-pi

Agent Claude Code

General purpose execution agent with full tool access.

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…

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…

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.

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.

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…

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.

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.

tmdgusya/engineering-discipline

Plugin Claude Code

Bundles 11 skills · 758 tokens together

Engineering discipline skills: optimization rules, systematic debugging, AI slop cleanup, and implementation guardrails.

tmdgusya/hermes-provider-switcher

Skill Claude CodeCodex

Set up and use the hermes-provider-switcher plugin to run Claude Code with alternative LLM providers (GLM, Kimi, MiniMax).

tmdgusya/hermes-provider-switcher

Skill Claude CodeCodex

Set up API keys for hermes-provider-switcher plugin (GLM, Kimi, MiniMax). Supports fresh setup or migration from shell rc files.

tmdgusya/language-skills

Plugin Claude Code

Bundles 1 skill, 4 commands · 61 tokens together

A plugin for learning English prompts, including vocabulary building and more natural phrasing.

tmdgusya/hermes-skill-kimi-cli

Skill Claude CodeCodex

Delegate coding tasks to Kimi CLI (Moonshot AI's coding agent). Use for building features, fixing bugs, refactoring, PR reviews, and batch processing. Supports non-interactive print mode, session management, and subagents. Requires kimi-cli installed and authenticated.