sightglass
por davidgeorgehope
Coding Agents & IDEsResumo
Your AI coding agent just added 47 dependencies to your project.
Descrição
O que esta skill faz
Sightglass monitors AI coding agent sessions to track how dependencies get selected, classifying each one by how the agent discovered it — training recall, context inheritance, search, or user direction. It surfaces dependency risks, missed alternatives, and bias patterns after each session. Data syncs to sightglass.dev when authenticated.
Unlike manual post-hoc dependency review, Sightglass captures the discovery method at session time, making it possible to distinguish reasoned choices from autopilot training recall.
Quando usá-la
- Auditing which packages an AI agent added without explicit instruction
- Checking training recall percentage after a large agent-driven refactor
- Comparing what alternatives the agent ignored when picking a library
- Flagging unmaintained or vulnerable packages introduced by an agent session
- Reviewing dependency history across multiple agent sessions on a project
Exemplo de fluxo de trabalho
User asks: analyze what my agent just did in the last hour
- 1
Run pre-spawn.sh before starting the coding agent session to record start time and ensure watcher is running
- 2
Agent completes its work, installing dependencies and making architectural choices
- 3
Run post-session.sh to trigger analysis of the completed session
- 4
Review the summary output showing dependencies added, risk count, training recall percentage, and missed alternatives
- 5
Run sightglass analyze --since '1 hour ago' --format json for full detail
Session report listing 12 dependencies added, 3 risks, 67% training recall, and 5 alternatives the agent never considered
Requisitos
- sightglass.dev account (for cloud analysis, history, and --push sync)
Instalação
clawhub install davidgeorgehope/sightglassExecute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.