prompt-evaluation-runn…
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost…
Use when connecting to a managed codebase-context MCP/session service, checking stale maps, or safely using MCP-provided repository context.
Claude Code
$ npx -y skills add yeaight7/agent-powerups --skill managed-codebase-context --agent claude-code
Codex
$ npx skills add yeaight7/agent-powerups --skill managed-codebase-context -a codex -y
Cursor
$ npx skills add yeaight7/agent-powerups --skill managed-codebase-context -a cursor -y
Gemini CLI
$ npx skills add yeaight7/agent-powerups --skill managed-codebase-context -a gemini-cli -y
GitHub Copilot
$ npx skills add yeaight7/agent-powerups --skill managed-codebase-context -a github-copilot -y
OpenCode
$ npx skills add yeaight7/agent-powerups --skill managed-codebase-context -a opencode -y
Windsurf
$ npx skills add yeaight7/agent-powerups --skill managed-codebase-context -a windsurf -y
name: managed-codebase-context description: Use when connecting to a managed codebase-context MCP/session service, checking stale maps, or safely using MCP-provided repository context.
Use when a persistent codebase-context MCP server is available and the task requires broad architectural context, symbol inventory, or cross-file navigation that would be expensive to reconstruct from scratch on each turn.
1. **Select transport**:
2. **Connect with timeout** — set a connection timeout; do not let the agent hang indefinitely if the server never initializes.
3. **Retrieve context** — fetch the current codebase map, symbol index, or architectural summary as available.
4. **Validate freshness** — a map is stale if any of the following are true:
5. **Refresh when stale** — trigger a context refresh only when the map is demonstrably stale. Do not refresh on every request — refreshes are expensive.
6. **Use context, then close** — read what you need, then close the session. Ensure the client and transport close cleanly. If the server was spawned as a stdio process, kill the process tree if it does not exit within a few seconds.
| Signal | Check | |---|---| | Map timestamp | Compare to `git log --format="%ci" -1` for recently changed files | | Missing files | Cross-reference map file list with `git ls-files` | | Stale symbols | Check if key function/class names in the map exist in current source | | User-reported | Accept the user's word; trigger refresh without verification |
Curated power-ups for coding agents: skills, slash commands, MCP configs, hooks, AGENTS.md templates, and workflows for serious software engineering. Claude Code, Codex, Antigravity CLI, Cursor and more
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost…
Use when creating or reviewing red-team eval plugins, attack templates, grader rubrics, safety fixtures, or model-risk test…
Use when designing, running, debugging, or hardening deterministic eval suites for agent skills, prompts, tool workflows, or…
Use when designing tool definitions for a new agent or subagent, an agent shows high retry rates, ambiguous tool invocations, or…
Use when routing a prompt to a local provider CLI for a second opinion, review, or plan -- you are about to call a provider…
Use when starting work in an unfamiliar area of a codebase, spawning a subagent that needs targeted file context, a first search…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.