Instructions file CodexOpenCode
Instructions for brenbuilds1/copilot-ralph, covering agent instructions, project structure, skills, prd-generator (skills/prd/skill.md) and commands.
50 7mo ago A 589 tokens
original MIT
Skill Claude CodeCodex
Generate a Product Requirements Document (prd.json) for the Ralph autonomous agent loop. Use when planning a feature, starting a new project, or preparing work for Ralph to implement. Triggers on: create a prd, write prd for, plan this feature, generate user stories, set up ralph for, spec out.
50 7mo ago A 69 tokens
original MIT
cutweight
03Plugin Claude Code
Plugin marketplace listing 1 plugin: cutweight.
2 1mo ago A
tokens not measured
original MIT
cutweight
04Plugin Claude Code
Cut your agent's token weight: weigh in, read the bill, cut the output, cap the thinking, keep sessions lean.
2 1mo ago A
tokens not measured
original MIT
session-cut
05Skill Claude CodeCodex
Session-weight hygiene. Use when sessions run long, when an agent gets slower or starts forgetting mid-session, when deciding between /clear, /compact, or a fresh session, or when every message feels heavier than the work in it. Calls the moment a session has blown the weight limit: cut it right and start the next one…
2 1mo ago A 71 tokens
original MIT
skill-diet
06Skill Claude CodeCodex
Audit the always-on context cost of an agent setup: installed skills, memory files (CLAUDE.md, AGENTS.md), and MCP tool schemas. Use when asked to audit, trim, shrink, or cut skills or context, when an agent picks the wrong skill or feels dumber after the setup grew, when MCP servers eat the context window, or when…
2 1mo ago A 105 tokens
original MIT
think-light
07Skill Claude CodeCodex
Cut reasoning-token weight. Use when thinking or reasoning tokens dominate the bill, when asked to cap a thinking budget, lower effort, or stop simple tasks from burning extended thinking. Light tasks get light thinking: matches thinking budget to task weight, then verifies accuracy held before keeping any cap. Never…
2 1mo ago A 64 tokens
original MIT
weigh-in
08Skill Claude CodeCodex
Weigh an agent setup and print a fight-card receipt. Use when asked to weigh in, weigh my agent, check my agent's weight or token overhead, or compare before and after a cut. Measures the always-on context bill (installed skills, memory files, MCP tool schemas), assigns a weight class, prints a shareable card, and…
2 1mo ago A 92 tokens
original MIT
word-diet
09Skill Claude CodeCodex
Puts the agent's replies on a word diet. Compressed output that cuts reply tokens by roughly a third to half, more on ultra, while keeping full technical accuracy. Answers like a cornerman between rounds: only what changes the next round. Adds source discipline: verify current-year, recent, latest, changing, risky, or…
2 1mo ago A 124 tokens
original MIT