ln-015-hex-line-uninstaller
Use when removing Claude-side hex-line integration surfaces such as MCP registration, permissions, hooks, and output style.
What this skill does
> **Paths:** File paths are relative to skills repo root. Locate this SKILL.md directory and go up one level for repo root. # Hex-Line Uninstaller **Type:** L3 Worker **Category:** 0XX Shared Removes Claude-side hex-line integration surfaces. This worker is standalone-capable but also supports managed `ln-010` family transport. **MANDATORY READ:** Load `references/coordinator_summary_contract.md`, `references/environment_worker_runtime_contract.md`, and `references/worker_runtime_contract.md` This worker cleans Claude-side state directly from config files and CLI state. Missing MCP connectivity is not a blocker; continue with local cleanup and verification wherever possible. ## Input / Output | Direction | Content | |-----------|---------| | **Input** | optional `dry_run`, optional `runId`, optional `summaryArtifactPath` | | **Output** | Structured summary envelope with `summary_kind = env-cleanup`, `payload.status` = `completed` / `skipped` / `error`, plus cleanup outcomes in `changes` / `detail` | Transport inputs: - standalone: omit `runId` and `summaryArtifactPath` - managed: pass both `runId` and `summaryArtifactPath` ## Runtime Runtime family: `environment-worker-runtime` Phase profile: 1. `PHASE_0_CONFIG` 2. `PHASE_1_RESOLVE_CLAUDE_STATE` 3. `PHASE_2_REMOVE_HEXLINE_REGISTRATION` 4. `PHASE_3_REMOVE_HEXLINE_ARTIFACTS` 5. `PHASE_4_VERIFY_CLEANUP` 6. `PHASE_5_WRITE_SUMMARY` 7. `PHASE_6_SELF_CHECK` Runtime rules: - emit `summary_kind=env-cleanup` - standalone runs generate their own `run_id` and write the default worker-family artifact path - managed runs require both `runId` and `summaryArtifactPath` and must write the summary to the exact provided path - always write the validated summary artifact before terminal outcome ## Output Contract Always build a structured `env-cleanup` summary envelope per: - `references/coordinator_summary_contract.md` - `references/environment_worker_runtime_contract.md` Payload fields: - `mcp_removed` - `permissions_cleaned` - `hooks_removed` - `output_style_removed` - `verification` - `status` ## What It Removes | Surface | Location | Action | |---------|----------|--------| | MCP registration | `claude mcp list` / user scope | Remove `hex-line` registration via `claude mcp remove -s user hex-line` when present | | Permission entries | `~/.claude/settings.json` and `~/.claude/settings.local.json` | Remove `permissions.allow` entries that target `mcp__hex-line__*` | | Hook entries | `~/.claude/settings.json` and `~/.claude/settings.local.json` | Remove hook entries matching the current hex-line hook signature | | Output style file | `~/.claude/output-styles/hex-line.md` | Delete file | | Output style setting | `~/.claude/settings.json` and `~/.claude/settings.local.json` | Clear only if value is `"hex-line"` | | Hook directory | `~/.claude/hex-line/` | Delete only if empty after artifact cleanup | ## Workflow ### Phase 1: Resolve Claude State 1. Read `~/.claude/settings.json` if present 2. Read `~/.claude/settings.local.json` if present 3. Detect: - `hex-line` MCP registration in user scope - `permissions.allow` entries for `mcp__hex-line__*` - hook entries whose command points to the installed hex-line hook - `outputStyle = "hex-line"` - installed style file and hook directory 4. Record exactly which owned surfaces exist before mutating anything ### Phase 2: Remove Hex-Line Registration 1. If user-scope `hex-line` registration exists, run: ```text claude mcp remove -s user hex-line ``` 2. If registration is already absent, report `already removed` 3. Do not uninstall the npm package here. This worker owns Claude-side integration surfaces only ### Phase 3: Remove Hex-Line Artifacts 1. Update Claude settings surfaces: - remove `permissions.allow` entries for `mcp__hex-line__*` - remove hook entries whose command contains the active hex-line hook path - remove empty hook event arrays and remove `hooks` only when empty - clear `outputStyle` only when it is exactly `"hex-line"` 2. Delete `~/.claude/output-styles/hex-line.md` if present 3. Delete `~/.claude/hex-line/hook.mjs` if present 4. Delete `~/.claude/hex-line/` only when it is empty after file removal Rules: - preserve all non-hex-line settings - never claim cache cleanup unless a concrete cache deletion step exists - do not touch unrelated MCP registrations or permission entries ### Phase 4: Verify Cleanup Confirm: - no user-scope `hex-line` MCP registration remains - no `permissions.allow` entry targets `mcp__hex-line__*` - no hex-line hook entry remains in managed Claude settings files - `outputStyle` is not `"hex-line"` - `~/.claude/output-styles/hex-line.md` does not exist - `~/.claude/hex-line/hook.mjs` does not exist ## Notes - This worker removes Claude-side hex-line integration only - It does not remove the npm package itself - It is safe to run multiple times ## Definition of Done - [ ] Claude user-scope `hex-line` MCP registration removed or confirmed absent - [ ] `permissions.allow` no longer contains `mcp__hex-line__*` - [ ] No hex-line hook entries remain in managed Claude settings files - [ ] `outputStyle: "hex-line"` cleared where owned - [ ] Installed style and hook artifacts removed - [ ] Structured summary returned - [ ] Summary artifact written to the managed or standalone runtime path **Version:** 1.0.0 **Last Updated:** 2026-03-27
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.