auto-coder
Autonomous multi-session feature development framework. Use when the user wants to systematically implement features from a specification, track progress across sessions, and ensure all tests pass before marking features complete. Activated by the /lynyx-agent-kit:auto-coder command or when working with feature_list.json files in an .auto-coder directory.
What this skill does
# Auto-Coder Skill
A framework for orchestrating autonomous feature development across multiple Claude Code sessions.
## Overview
Auto-coder operates in two phases:
1. **Initializer Phase** (Session 1): Analyzes a project specification and generates a comprehensive `feature_list.json` with test cases ordered by priority and dependency
2. **Coding Phase** (Sessions 2+): Implements features one-by-one, running tests, making git commits, and tracking progress until all features are complete
## State Files
All auto-coder state is persisted in the `.auto-coder/` directory:
| File | Purpose |
|------|---------|
| `feature_list.json` | Source of truth for features, test cases, and completion status |
| `progress.md` | Human-readable log of session activity |
See [FEATURE_SCHEMA.md](FEATURE_SCHEMA.md) for the complete JSON schema.
## Locating Skill Files
To quickly locate the auto-coder skill instruction files (CODER.md, INITIALIZER.md, etc.), use the `skill-file-locator.py` script:
```bash
python ~/.claude/plugins/cache/lynyx-claude/lynyx-agent-kit/<version>/skills/auto-coder/scripts/skill-file-locator.py
```
The script outputs the full path to the skill directory and a tree view of all skill files:
```
~/.claude/plugins/cache/lynyx-claude/lynyx-agent-kit/1.2.1/skills/auto-coder
├── scripts
│ ├── continue.sh
│ └── skill-file-locator.py
├── CODER.md
├── FEATURE_SCHEMA.md
├── INITIALIZER.md
└── SKILL.md
```
**Usage:**
- Default skill: `python skill-file-locator.py` (locates auto-coder skill)
- Custom skill: `python skill-file-locator.py <skill-name>`
Use this script at the start of each coding session to locate and read the appropriate instruction files (CODER.md for coding phase, INITIALIZER.md for initialization phase).
## Phases
### Phase 1: Initialization
Run with `/lynyx-agent-kit:auto-coder init [spec_file]`
For detailed instructions, see [INITIALIZER.md](INITIALIZER.md).
**Summary:**
- Read and analyze the project specification
- Generate `feature_list.json` with features ordered by critical path
- Auto-generate project prefix for task IDs (present to user for approval)
- Initialize project structure and git repository
- Create initial commit
- Rename session: `auto-coder: initialize {PROJECT_NAME}`
### Phase 2: Coding
Run with `/lynyx-agent-kit:auto-coder code`
For detailed instructions, see [CODER.md](CODER.md).
**Summary:**
- Orient to project state (read files, git log)
- Run regression tests on high-priority passing features
- Select next incomplete feature
- Implement and test the feature
- Update `feature_list.json` and commit
- Rename session: `auto-coder: {PROJECT_NAME} | {TASK_ID}`
## Session Management
### Fresh Sessions vs Resume
- **Fresh sessions**: Recommended for starting work on each new feature
- **Resume sessions**: Use `claude --resume <name>` for interrupted work mid-feature
### Session Naming
Sessions are automatically named for easy identification:
- Initializer: `auto-coder: initialize {PROJECT_NAME}`
- Coder: `auto-coder: {PROJECT_NAME} | {TASK_ID}`
### Pause/Resume
1. **To pause**: Exit session with Ctrl+C or Ctrl+D (context preserved)
2. **To resume**: `claude --resume "auto-coder: {PROJECT_NAME} | {TASK_ID}"`
3. **To start fresh**: `claude -p "/lynyx-agent-kit:auto-coder code"` (new session)
## Auto-Continuation
For fully autonomous operation, use a shell loop:
```bash
while true; do claude -p "/lynyx-agent-kit:auto-coder code" || break; sleep 3; done
```
Or use the helper script:
```bash
./plugins/lynyx-agent-kit/skills/auto-coder/scripts/continue.sh
```
## Security Guidance
The following commands are recommended for use during implementation:
**Allowed:**
- File operations: `ls`, `cat`, `head`, `tail`, `wc`, `grep`
- Runtime: `npm`, `node`, `bun`, `python`, `pytest`
- Version control: `git`
- Process management: `ps`, `lsof`, `sleep`, `pkill` (dev processes only)
**Avoid:**
- System modification commands
- Network commands without clear purpose
- Commands affecting files outside the project directory
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.