florianbuetow/codebasescout
Scout a codebase to identify high-value work, plan the fixes (point and architectural), and produce a ranked map from codebase to tasks -- each tagged with a recommended model -- without ever implementing the fix. Cheap-model agents sweep and score every file by Impact x Opportunity (1-5); the router then runs meta-level pattern analysis, plans point and architectural fixes, and recommends a model per task. Team: target guard, skip gate, formula, profile, parallel scorers, ranker, pattern-grouper (meta-level analysis + architectural fix planning), task-writer (point-fix planning), model-recommender. Objectives: bugs, security, tech debt, dead code, performance, conversion.
- name
- codebasescout
- version
- 0.1.0
- description
- Scout a codebase to identify high-value work, plan the fixes (point and architectural), and produce a ranked map from codebase to tasks -- each tagged with a recommended model -- without ever implementing the fix. Cheap-model agents sweep and score every file by Impact x Opportunity (1-5); the router then runs meta-level pattern analysis, plans point and architectural fixes, and recommends a model per task. Team: target guard, skip gate, formula, profile, parallel scorers, ranker, pattern-grouper (meta-level analysis + architectural fix planning), task-writer (point-fix planning), model-recommender. Objectives: bugs, security, tech debt, dead code, performance, conversion.
- author
- Florian Buetow2320560+florianbuetow@users.noreply.github.com
- license
- MIT
- keywords
- codebase-scanningtask-mappingmodel-recommendationprioritizationimpact-opportunitytriageagent-orchestration
- extensions
- com.openai
{
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
"name": "codebasescout",
"version": "0.1.0",
"description": "Scout a codebase to identify high-value work, plan the fixes (point and architectural), and produce a ranked map from codebase to tasks -- each tagged with a recommended model -- without ever implementing the fix. Cheap-model agents sweep and score every file by Impact x Opportunity (1-5); the router then runs meta-level pattern analysis, plans point and architectural fixes, and recommends a model per task. Team: target guard, skip gate, formula, profile, parallel scorers, ranker, pattern-grouper (meta-level analysis + architectural fix planning), task-writer (point-fix planning), model-recommender. Objectives: bugs, security, tech debt, dead code, performance, conversion.",
"author": {
"name": "Florian Buetow",
"email": "2320560+florianbuetow@users.noreply.github.com"
},
"repository": "https://github.com/florianbuetow/codex-plugins",
"license": "MIT",
"keywords": [
"codebase-scanning",
"task-mapping",
"model-recommendation",
"prioritization",
"impact-opportunity",
"triage",
"agent-orchestration"
],
"extensions": {
"com.openai": {
"interface": {
"displayName": "Codebasescout",
"shortDescription": "Scout a codebase to identify high-value work, plan the fixes (point and architectural), and pro…",
"longDescription": "Scout a codebase to identify high-value work, plan the fixes (point and architectural), and produce a ranked map from codebase to tasks -- each tagged with a recommended model -- without ever implementing the fix. Cheap-model agents sweep and score every file by Impact x Opportunity (1-5); the router then runs meta-level pattern analysis, plans point and architectural fixes, and recommends a model per task. Team: target guard, skip gate, formula, profile, parallel scorers, ranker, pattern-grouper (meta-level analysis + architectural fix planning), task-writer (point-fix planning), model-recommender. Objectives: bugs, security, tech debt, dead code, performance, conversion.",
"developerName": "Florian Buetow",
"category": "Development",
"capabilities": [
"Skills"
],
"defaultPrompt": [
"Use Codebasescout to Scout a codebase to identify high-value work, plan the fixes (point and architectural), and produce a rank…"
]
}
}
}
}
Client extensions
Data this package carries for particular clients. The directory lists the clients named and never reads what is addressed to them.
- com.openai