{"id":42776490,"url":"https://github.com/goca-se/dotcontext","last_synced_at":"2026-07-07T22:00:30.754Z","repository":{"id":335357989,"uuid":"1145431651","full_name":"goca-se/dotcontext","owner":"goca-se","description":"AI context toolkit for Claude Code — commands, decisions, skills, and feature planning for your codebase","archived":false,"fork":false,"pushed_at":"2026-07-01T16:42:52.000Z","size":59740,"stargazers_count":7,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-07-01T18:25:06.428Z","etag":null,"topics":["ai-assistant","ai-coding","ai-context","claude","claude-code","cli","context-management","developer-tools","toolkit"],"latest_commit_sha":null,"homepage":"https://github.com/goca-se/dotcontext#readme","language":"Shell","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/goca-se.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-01-29T19:52:30.000Z","updated_at":"2026-07-01T16:42:54.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/goca-se/dotcontext","commit_stats":null,"previous_names":["goca-se/dotcontext"],"tags_count":25,"template":false,"template_full_name":null,"purl":"pkg:github/goca-se/dotcontext","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/goca-se%2Fdotcontext","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/goca-se%2Fdotcontext/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/goca-se%2Fdotcontext/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/goca-se%2Fdotcontext/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/goca-se","download_url":"https://codeload.github.com/goca-se/dotcontext/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/goca-se%2Fdotcontext/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35243953,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-07T02:00:07.222Z","response_time":90,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-assistant","ai-coding","ai-context","claude","claude-code","cli","context-management","developer-tools","toolkit"],"created_at":"2026-01-29T22:08:46.032Z","updated_at":"2026-07-07T22:00:30.747Z","avatar_url":"https://github.com/goca-se.png","language":"Shell","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/dotcontext.svg\" alt=\"dotcontext logo\" width=\"150\"\u003e\n\u003c/p\u003e\n\n\u003ch1 align=\"center\"\u003edotcontext\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cem\u003eAI context toolkit for coding agents — Claude Code, Codex, opencode, Gemini, Copilot \u0026 Cursor\u003c/em\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/goca-se/dotcontext/releases/latest\"\u003e\u003cimg src=\"https://img.shields.io/github/v/release/goca-se/dotcontext\" alt=\"Release\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/goca-se/dotcontext/blob/main/LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/github/license/goca-se/dotcontext\" alt=\"License\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n`dotcontext` is an AI context toolkit for coding agents — Claude Code, OpenAI Codex, opencode, Gemini CLI, GitHub Copilot, and Cursor. It provides commands, decisions, skills, and feature planning workflows that help AI assistants understand and work with your codebase.\n\n\u003cdetails\u003e\n\u003csummary\u003eSee it in action\u003c/summary\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/demo-quickstart.gif\" alt=\"dotcontext quick start demo\" width=\"700\"\u003e\n\u003c/p\u003e\n\n\u003c/details\u003e\n\n## Installation\n\n```bash\ncurl -sSL https://raw.githubusercontent.com/goca-se/dotcontext/main/install.sh | bash\n```\n\nOr manually:\n\n```bash\ncurl -sSL https://raw.githubusercontent.com/goca-se/dotcontext/main/dotcontext -o /usr/local/bin/dotcontext\nchmod +x /usr/local/bin/dotcontext\n```\n\n## Usage\n\n### Initialize a project\n\n```bash\ncd your-project\ndotcontext init\n```\n\nThis creates the context structure and downloads templates for the harness(es) you select. When **Claude Code** is among them, it **automatically opens Claude running `/setup-context`** to analyze and populate your project's context files; otherwise, edit `AGENTS.md` and `.context/CONTEXT.md` to describe your project.\n\n**Options:**\n\n```bash\ndotcontext init --name \"My Project\"  # Set project name\ndotcontext init --yes                # Skip prompts, use defaults\ndotcontext init --no-setup           # Skip automatic /setup-context execution\n```\n\n### Update\n\n```bash\ndotcontext update                  # Update CLI + templates (if in a project)\ndotcontext update --cli            # Only update CLI\ndotcontext update --templates      # Only update templates\ndotcontext update --dry-run        # Preview template changes only\ndotcontext update --yes            # Update templates without prompting\n```\n\n**Terraform-style preview for templates:**\n\n```\nChecking templates...\n\n  + .claude/commands/fix-bug.md (new)\n  ~ .claude/commands/code-review.md (modified)\n  = .claude/commands/setup-context.md (unchanged)\n  • .claude/skills/bug-reproduction/SKILL.md (user-managed — skipped)\n\nSummary: 1 to add, 1 to update, 8 unchanged, 1 user-managed\n\nUpdate 1 existing file(s)? [y/N/d] (y=yes, N=no, d=show diffs)\n```\n\n**Safe by default:**\n\n- CLI downloads from the release tag (not main branch) — no unreleased code\n- Templates show exactly what will change before doing anything\n- Default action (`N`) only adds new files, never overwrites\n- Press `d` to see diffs before deciding\n- **User-managed files** (skills, READMEs) are never overwritten — they're created once during init and then owned by you\n- Never touches user content (`CONTEXT.md`, `CLAUDE.md`, your ADRs, bug reports, discoveries)\n\n### Run the setup command\n\nThe setup command runs automatically after `dotcontext init`. To run it manually (e.g., after code changes):\n\n```bash\nclaude\n\u003e /setup-context\n```\n\n\u003cdetails\u003e\n\u003csummary\u003eSee it in action\u003c/summary\u003e\n\n\u003cimg src=\"assets/demo-setup-context.gif\" alt=\"setup-context demo\" width=\"600\"\u003e\n\n\u003c/details\u003e\n\n## Decision Compliance\n\nThe generated `AGENTS.md` (the canonical instructions file) includes instructions for AI assistants to **respect architectural decisions**.\n\nWhen you ask Claude Code to make a change that conflicts with an existing ADR, it will:\n\n1. **Stop and inform you** which decision(s) would be affected\n2. **Ask explicitly** if you want to:\n   - Proceed and update the decision\n   - Modify the approach to comply\n   - Cancel the change\n3. **If updating**, create a versioned ADR (marking old one as `Superseded`)\n\nThis ensures your architectural decisions stay synchronized with your code.\n\n## What It Creates\n\n```\nyour-project/\n├── AGENTS.md                    # Canonical project instructions (read by Codex, opencode, Copilot, Cursor…)\n├── CLAUDE.md                    # Thin @AGENTS.md import for Claude Code (always added for compatibility)\n├── GEMINI.md                    # Thin @AGENTS.md import for Gemini CLI (added when Gemini is detected)\n├── .context/\n│   ├── CONTEXT.md               # Domain knowledge\n│   ├── decisions/               # ADRs (versioned)\n│   ├── discoveries/             # Deep context analysis outputs\n│   ├── bugs/                    # Bug fix reports\n│   ├── specs/                   # Behavior specs — the WHAT (/spec-dc)\n│   └── plans/                   # Implementation plans — the HOW (/plan-dc)\n├── .mcp.json                    # MCP server config (Context7, Atlassian)\n└── .claude/\n    ├── commands/\n    │   ├── setup-context.md          # Auto-setup command\n    │   ├── code-review.md            # Code review command\n    │   ├── commit.md                 # Smart commit command\n    │   ├── spec-dc.md                # Write a behavior spec (the WHAT)\n    │   ├── plan-dc.md                # Turn a spec into a plan (the HOW)\n    │   ├── execute-dc.md             # Implement a plan in waves (the DO)\n    │   ├── create-pr.md              # Create PRs with diagrams\n    │   ├── pr-comment.md             # Comment on PRs\n    │   ├── add-decision.md           # Add ADR interactively\n    │   ├── add-skill.md              # Add skill interactively\n    │   ├── add-command.md            # Add custom command\n    │   ├── deep-context.md           # Structured codebase exploration\n    │   └── fix-bug.md               # Test-driven bug fixing\n    ├── agents/                       # Extracted agent prompts\n    │   ├── code-review/              # 3 review agents\n    │   ├── deep-context/             # 4 exploration agents\n    │   ├── fix-bug/                  # 5 bug-fix agents\n    │   ├── spec-dc/                  # 2 spec reviewers (pro + fast)\n    │   ├── plan-dc/                  # 2 plan reviewers (pro + fast)\n    │   └── execute-dc/               # 2 implementation reviewers (pro + fast)\n    ├── skills/                       # Step-by-step guides (SKILL.md w/ name+description frontmatter)\n    │   ├── bug-reproduction/         # Reproduce-before-fixing patterns\n    │   ├── batch-operations/         # Safe multi-file changes\n    │   ├── git-platform/             # Detect GitHub/GitLab/… before git CLI\n    │   └── update-api-documentation/ # OpenAPI SSOT docs\n    └── scripts/\n        └── statusline.sh            # StatusLine: model, dir, git, ctx-usage bar, cost/time/lines\n```\n\n\u003e Files are emitted per chosen harness (see [Multi-Agent Support](#multi-agent-support)): `AGENTS.md` and `.context/` are always written; the full `.claude/` tree and `CLAUDE.md` appear only when **Claude** is selected, `GEMINI.md` only for **Gemini**, and `.agents/skills/` only when a non-Claude agent is selected.\n\nAdditionally, `dotcontext init` configures:\n\n- **MCP servers** in `.mcp.json` (optional, prompted during init):\n  - [Context7](https://github.com/upstash/context7-mcp) — up-to-date library docs for LLMs\n  - [Atlassian](https://mcp.atlassian.com) — Jira + Confluence via OAuth\n\n- **Native OS notifications** in `.claude/` (project-local):\n\n```\n.claude/\n├── scripts/\n│   └── notify.sh          # Cross-platform notification script\n└── settings.json          # Hooks for Notification and Stop events\n```\n\n## Multi-Agent Support\n\ndotcontext works with six harnesses: **Claude Code, OpenAI Codex, opencode, Gemini CLI, GitHub Copilot, and Cursor** (IDE and `cursor-agent`). `init` only writes files for the harnesses you pick, so a Codex-only project never ends up with a stray `.claude/`:\n\n```bash\ndotcontext init                       # interactive: confirm each detected agent\ndotcontext init --agents codex,cursor # explicit, non-interactive\ndotcontext init --yes                 # all detected agents\n```\n\nWhat's shared vs per-harness (ADR-016, ADR-017):\n\n| Layer | Coverage |\n| --- | --- |\n| Instructions (`AGENTS.md`) | Codex, opencode, Copilot, and Cursor read it natively; Claude (`CLAUDE.md`) and Gemini (`GEMINI.md`) import it with `@AGENTS.md` |\n| Skills (`SKILL.md`) | `.agents/skills/` for Codex/opencode/Gemini/Copilot/Cursor, mirrored to `.claude/skills/` for Claude |\n| Hooks (finish notification) | native config per harness (`.codex/`, `.gemini/`, `.github/hooks/`, `.cursor/`, opencode plugin); Claude also gets the tool-failure guard |\n| Commands / workflows | Claude `.claude/commands/`, opencode `.opencode/command/`, Copilot `.github/prompts/`; Gemini, Cursor, and Codex use the `## Workflows` section of `AGENTS.md` |\n\n`dotcontext update` migrates an existing single-file `CLAUDE.md` into the shared `AGENTS.md` (Claude keeps working via the import). Check `dotcontext --version --json` for the live capability/agent list.\n\n## Commands Reference\n\n### CLI Commands\n\n| Command                                | Description                                    |\n| -------------------------------------- | ---------------------------------------------- |\n| `dotcontext init`                      | Initialize + auto-run /setup-context           |\n| `dotcontext init --no-setup`           | Initialize without running setup               |\n| `dotcontext update`                    | Update CLI + templates (if in a project)       |\n| `dotcontext update --cli`              | Only update CLI                                |\n| `dotcontext update --templates`        | Only update templates                          |\n| `dotcontext update --yes`              | Update templates without prompting             |\n| `dotcontext update --dry-run`          | Preview template changes only                  |\n| `dotcontext doctor`                    | Check project setup health (+ flags available updates) |\n| `dotcontext completion [bash\\|zsh]`    | Generate shell tab completions                 |\n| `dotcontext --help`                    | Show help                                      |\n| `dotcontext --version [--features\\|--json]` | Show version; `--features`/`--json` expose the capability handshake |\n\n### Claude Code Commands\n\n| Command                      | Description                                    |\n| ---------------------------- | ---------------------------------------------- |\n| `/setup-context`             | Analyze codebase and populate context          |\n| `/spec-dc [feature]`         | Write a behavior spec — the WHAT (step 1)      |\n| `/plan-dc [spec-path]`       | Turn a spec into a plan with ADR review — the HOW (step 2) |\n| `/execute-dc [plan-path]`    | Implement a plan in parallel waves — the DO (step 3) |\n| `/code-review [--comment]`   | Multi-agent code review with confidence scoring |\n| `/commit [--amend]`          | Smart commit with style-aware message generation |\n| `/create-pr`                 | Create PR with auto-detected architecture diagrams |\n| `/pr-comment [PR] [message]` | Add comments to PRs with optional diagrams     |\n| `/deep-context [query]`      | Structured 4-step codebase exploration            |\n| `/fix-bug [description]`    | Test-driven bug fixing with parallel agents    |\n| `/add-decision`              | Add and populate an ADR interactively          |\n| `/add-skill`                 | Add and populate a skill guide                 |\n| `/add-command`               | Create a custom slash command                  |\n| `/release`                   | Version bump and release                       |\n\n## Built-in Slash Commands\n\n### `/setup-context`\n\nAnalyzes your codebase and populates context files:\n\n- Fills `CLAUDE.md` with stack, commands, rules\n- Documents domain in `.context/CONTEXT.md`\n- **Generates Architecture section** — system overview, directory structure, key dependencies, data flow\n- **Detects coding conventions** — adaptive sampling (5-20 files based on project size) across 6 categories: naming patterns, error handling, testing style, import organization, state management, API response format\n- Creates ADRs for existing architectural decisions\n- Sets up skills for recurring patterns\n\n### `/code-review [--comment]`\n\nMulti-agent code review inspired by [Claude Code's official plugin](https://github.com/anthropics/claude-code/tree/main/plugins/code-review):\n\n**Architecture:**\n- Launches **4 parallel agents** for independent analysis:\n  - 2x CLAUDE.md compliance checkers (redundancy)\n  - 1x Bug detector (logic errors, edge cases, type mismatches)\n  - 1x Security \u0026 history analyzer (vulnerabilities + git blame patterns)\n- **Confidence scoring** (0-100) filters false positives (threshold ≥80)\n- Automatic context gathering (CLAUDE.md files + PR diff)\n\n**Usage:**\n```bash\n/code-review           # Review to terminal\n/code-review --comment # Post review as PR comment\n```\n\n**Pre-flight checks** (auto-skips):\n- Closed or merged PRs\n- Draft PRs\n- PRs already reviewed by this tool\n- Trivial changes (whitespace only)\n\n**Review categories:**\n- Correctness and edge cases\n- Security vulnerabilities (OWASP top 10)\n- Performance issues\n- Code quality and patterns\n- CLAUDE.md rule violations\n\n### Feature development: spec → plan → execute\n\nFeature work runs as a three-command pipeline. Each step produces a durable, versioned\nartifact that the next step consumes — the spec is the source of truth the plan is measured\nagainst, and the plan is the contract the implementation is measured against.\n\n```text\n/spec-dc  (the WHAT)  →  /plan-dc  (the HOW)  →  /execute-dc  (the DO)\n   spec file               plan file              implemented + reviewed\n```\n\n#### `/spec-dc \u003cfeature description\u003e`\n\nWrites a **behavior specification** — the WHAT — into `.context/specs/spec-\u003cunix-ts\u003e-\u003cslug\u003e.md`:\n\n- **Runs a clarity assessment** and asks only the targeted questions that genuinely unblock ambiguity\n- Researches the real codebase (delegates broad sweeps to parallel `Explore` subagents)\n- Produces seven mandatory sections (user stories, success criteria, functional \u0026 non-functional\n  requirements, constraints/out-of-scope, technical context, acceptance tests)\n- Describes observable behavior only — **no code, no implementation plan, no ADR review**\n- Closes with a **dual reviewer loop** (`spec-dc/reviewer-pro` + `reviewer-fast`) that checks well-formedness, testability, scope, grounding, and fidelity to the request — **not** product merit (that stays your call)\n\n```text\n\u003e /spec-dc user authentication with OAuth\n```\n\n#### `/plan-dc \u003cspec-path\u003e`\n\nTurns a spec into a precise **implementation plan** — the HOW — in `.context/plans/plan-\u003cunix-ts\u003e-\u003cslug\u003e.md`:\n\n- Reads the spec (source of truth) and the actual code\n- **Owns the ADR review** for the whole flow — checks `.context/decisions/`, records impact, flags conflicts\n- Lists exact files to create/modify, tests, verification/regression, and a **100% Traceability table**\n  proving every spec item is covered\n- Runs a **dual adversarial review loop** (Reviewer Pro + Reviewer Fast, in parallel) until double-`APPROVED`\n\n```text\n\u003e /plan-dc .context/specs/spec-1746500000-user-auth.md\n```\n\n#### `/execute-dc \u003cplan-path\u003e`\n\nImplements an approved plan — the DO — treating the plan as an **immutable contract**:\n\n- Git hygiene: branches from the repo's detected base branch; **offers worktree isolation**\n- Decomposes the plan into **parallel waves** (disjoint files per wave, up to 3 subagents at a time)\n- Runs the project's tests after each wave; stops and fixes before advancing\n- Closes with a **dual review** of the `git diff` against the plan\n- Knowledge reconciliation back into `CONTEXT.md`/ADRs/skills is a deferred final step (ADR-019)\n\nBranch types are auto-detected from the plan: `feature/`, `bugfix/`, `hotfix/`, `chore/`, `experiment/`.\n\n```text\n\u003e /execute-dc .context/plans/plan-1746500123-user-auth.md\n\n# Optionally creates: ../your-project-user-auth (branch: feature/user-auth)\n```\n\n### `/create-pr`\n\nCreate well-structured pull requests with automatic architecture diagram detection:\n\n- Analyzes all commits since branching from main\n- Generates appropriate PR title and description\n- **Auto-detects architectural changes** and suggests Mermaid diagrams:\n  - New services/components → flowchart\n  - API changes → sequence diagram\n  - Data flow changes → flowchart\n  - Database changes → ER diagram\n- Pushes branch with confirmation if not on remote\n- Respects existing PR templates (`.github/PULL_REQUEST_TEMPLATE.md`)\n\nExample:\n\n```\n\u003e /create-pr\n\n# Analyzes changes, detects new API endpoint\n# Generates PR with sequence diagram showing request flow\n```\n\n### `/pr-comment [PR] [message]`\n\nAdd comments to existing pull requests:\n\n- **Comment types:**\n  - General comment - conversation thread\n  - Review comment - formal review\n  - Diagram explanation - architecture with Mermaid\n  - Status update - progress tracking\n\n- Auto-detects PR from current branch if not specified\n- Generates Mermaid diagrams when discussing architecture\n- Integrates with `/code-review` for follow-up\n\nExample:\n\n```\n\u003e /pr-comment add diagram explaining the new auth flow\n\u003e /pr-comment 123 LGTM, tested locally\n\u003e /pr-comment update status - frontend complete\n```\n\n### `/deep-context [query]`\n\nStructured 4-step codebase exploration with specialized agents:\n\n**Architecture:**\n- Follows a **structured progression** from high-level to detailed:\n  - Step 1: **Overview Agent** — architecture summary, key files, entry points\n  - Step 2: **Subsystem Agent** — module map, interdependencies, boundaries\n  - Step 3: **Drill Agent** — targeted deep-dive into relevant areas\n  - Step 4: **Data Flow Agent** — trace information movement through the system\n- **Phased execution**: Steps 1+2 run in parallel, Steps 3+4 run sequentially (each builds on prior outputs)\n- **Confidence filtering**: findings below 50% are auto-removed\n\n**Features:**\n- Auto-detects related repos from `.context/CONTEXT.md` external integrations\n- `--repo` flag for manual repo specification (local path or git URL)\n- `--cache` flag to reference previous discoveries\n- Every finding backed by `file:line` references (no fabrication)\n- Output saved to `.context/discoveries/`\n\n**Usage:**\n```\n\u003e /deep-context \"checkout flow\"\n\u003e /deep-context \"payment rules\" --repo ~/path/to/api\n\u003e /deep-context \"order processing\" --cache\n```\n\n### `/fix-bug [description]`\n\nTest-driven bug fixing with parallel subagents:\n\n**Architecture:**\n- **Phase 1 — Investigation**: Agent analyzes the bug, identifies root cause, writes a failing test\n- **Phase 2 — Parallel Fixes**: N agents (default 3) attempt fixes with diverse strategies:\n  - Conservative (minimal diff)\n  - Minimal change (surgical, exact lines)\n  - Refactor (fix + improve surrounding code)\n- **Phase 3 — Review**: Reviewer agent selects best fix or combines multiple successful fixes\n- All agents run to completion (best fix, not just first fix)\n\n**Features:**\n- Zero questions — goes straight from description to investigation\n- Test-first: writes a failing test before any fix attempt\n- `--issue N` to include GitHub issue context\n- `--pr N` to include PR context\n- `--agents N` to configure parallel fix agents\n- Bug report saved to `.context/bugs/`\n- Includes `bug-reproduction` skill template for project-specific patterns\n\n**Usage:**\n```\n\u003e /fix-bug \"login fails with empty password\"\n\u003e /fix-bug \"checkout timeout\" --issue 42\n\u003e /fix-bug \"regression in search\" --pr 123 --agents 5\n```\n\n### `/add-decision [title]`\n\nInteractively create and populate an Architectural Decision Record:\n\n- Asks clarifying questions about context and alternatives\n- Auto-numbers the ADR (001, 002, ...)\n- Populates with structured content\n- Updates the decisions index\n\n### `/add-skill [name]`\n\nInteractively create and populate a skill guide:\n\n- Analyzes codebase for existing patterns\n- Asks about use cases and anti-patterns\n- Includes real code examples from your project\n- Creates step-by-step documentation\n\n### `/add-command [name]`\n\nCreate a custom Claude Code slash command:\n\n- Asks about command purpose and behavior\n- Generates command file with proper structure\n- Immediately available as `/your-command`\n\n## Notifications\n\n`dotcontext init` automatically configures native OS notifications for each selected harness in its own hook config (`.claude/settings.json`, `.codex/hooks.json`, `.gemini/settings.json`, `.github/hooks/`, `.cursor/hooks.json`, or an opencode plugin). For Claude:\n\n| Event | When | Sound (macOS) |\n|-------|------|---------------|\n| **Notification** | Claude needs attention (question, permission) | Purr |\n| **Stop** | Claude finished processing | Funk |\n\n**Supported platforms:**\n\n- **macOS**: Native notifications via `osascript`\n- **Linux**: `notify-send` + `paplay`/`aplay`\n- **Windows/WSL**: PowerShell toast notifications\n\nNo additional dependencies required.\n\n## Shell Completion\n\n`dotcontext init` offers to wire this into your shell profile automatically. To set it up manually instead:\n\n```bash\n# Bash (add to ~/.bashrc)\neval \"$(dotcontext completion bash)\"\n\n# Zsh (add to ~/.zshrc)\neval \"$(dotcontext completion zsh)\"\n```\n\nCompletes subcommands (`init`, `update`, `doctor`, `completion`) and per-command options.\n\n## Requirements\n\n- Bash 3.2+\n- `curl` or `wget`\n\n## Uninstall\n\n```bash\nrm /usr/local/bin/dotcontext\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgoca-se%2Fdotcontext","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgoca-se%2Fdotcontext","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgoca-se%2Fdotcontext/lists"}