Reground
adamlinscott/claude-skillsHalt a drifting agent and re-anchor it to codebase evidence for the current task, clearing speculative context without a full compaction. Use when the agent has gone off course, hallucinated files/APIs/behavior, or started over-building beyond what was asked — or when the user types /reground or says "stop", "re-ground", "re-crown", "I don't see evidence for that", or "you're building something we don't need".
At a glance
This skill is for Coding and helps you reset an agent to current codebase, verify code exists before building, and stop hallucinated implementations.
/plugin marketplace add adamlinscott/claude-skills
/plugin install reground
Setup, runtime and requirements describe adamlinscott/claude-skills, the repo this skill ships in.
agent-controlHallucination PreventionCodebase Groundingcontext-managementCode Verificationdebugging
Also in adamlinscott/claude-skills
View the repoSurface and confirm the load-bearing assumptions behind a task before a long or expensive run — goal, root, what may be edited, what is off-...
Audits a repository's Claude context-injection setup — CLAUDE.md, CONTEXT.md, docs/, .claude/agents/, and the per-project memory directory....
BETA / under development. Mine the current project's Claude Code sessions for recurring corrections, then interrogate them — consolidate clu...
Fresh-context audit of a finished diff against the conversation's stated intent. A subagent with zero conversation history reviews the diff...
Run a settled implementation goal as a bounded autonomous build loop — lock the goal from the conversation and any docs written this session...
Audit Claude's per-user memory for this project and produce a report. Asks at the start whether the user wants a non-technical summary or a...
Sets up the security foundation that lets you run Claude Code fast — auto mode, custom tools, minimal interruptions — without it doing somet...
Alias for the seatbelt skill. Sets up the security foundation that lets you run Claude Code fast — auto mode, custom tools, minimal interrup...
Alias for the ttp skill. Shape user-facing output to be brief and direct — lead with the substance, keep the default answer short, and expan...
Shape user-facing output to be brief and direct — lead with the substance, keep the default answer short, and expand only when the user asks...
Other Coding skills
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make...
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI be...
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-design...
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model...
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS,...
Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor...