Cass
Keep git-native, CLI-first issue tracking in the repo so solo builders and coding agents can create, update, and sync work items without leaving the terminal.
Overview
cass (Beads-style tracking in this skill doc) is an agent skill most often used in Build (also Ship review, Operate iterate) that teaches git-native CLI issue tracking synced with your repo for AI-assisted workflows.
Install
npx skills add https://github.com/dicklesworthstone/coding_agent_session_search --skill cassWhat is this skill?
- Git-native issues stored in `.beads/issues.jsonl` and synced like source code
- CLI-first commands: create, list, show, update status, and bd sync with remote
- Designed for AI coding agents—no web UI context switching
- Branch-aware issue workflow that stays aligned with commits
- Offline-capable local tracking with sync on push
- 5 essential bd command groups: create, list, show, update, sync
Adoption & trust: 1.8k installs on skills.sh; 868 GitHub stars; 0/3 security scanners passed (skills.sh audits).
What problem does it solve?
You are juggling tasks in chat or a separate tracker while your agent works in the repo, so status and scope drift away from the code you are actually shipping.
Who is it for?
Solo builders who want lightweight, agent-friendly issue tracking committed alongside code in a monorepo or small service.
Skip if: Teams that need Jira-level workflows, cross-project portfolio views, or rich web dashboards without adopting the CLI model.
When should I use this skill?
You adopt or teach Beads-style in-repo issue tracking for AI-assisted development workflows.
What do I get? / Deliverables
You maintain a single in-repo issue list the agent can list and update via bd commands, then sync with git so backlog state matches what ships.
- Updated .beads/issues.jsonl backlog
- Synced issue state with git remote after bd sync
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Issue tracking is canonically shelved under Build → pm because that is where backlog and execution state live for day-to-day product work. Beads-style workflows map directly to project management: bd create/list/show/update/sync mirrors how indie teams run sprints beside the codebase.
Where it fits
Break a feature into bd create items before the agent implements each slice in order.
Mark release checklist issues done with bd update --status done before tagging a version.
File production follow-ups in .beads/issues.jsonl and bd sync after hotfix branches merge.
How it compares
Use instead of ad-hoc TODO markdown or a disconnected SaaS board when you want issues versioned with the same git history as the product.
Common Questions / FAQ
Who is cass for?
Indie and solo developers using AI coding agents who want issue state stored in the repository and operated through a small bd CLI rather than a separate product UI.
When should I use cass?
During Build pm when breaking work into issues, during Ship launch prep when closing release tasks, and during Operate iterate when triaging follow-ups—anytime you want agents to bd create, list, or update without leaving the repo.
Is cass safe to install?
Review the Security Audits panel on this Prism page and treat third-party skill content like any CLI workflow; the documented flow is local git and bd sync without prescribing secret handling beyond your normal repo practices.
SKILL.md
READMESKILL.md - Cass
# Beads - AI-Native Issue Tracking Welcome to Beads! This repository uses **Beads** for issue tracking - a modern, AI-native tool designed to live directly in your codebase alongside your code. ## What is Beads? Beads is issue tracking that lives in your repo, making it perfect for AI coding agents and developers who want their issues close to their code. No web UI required - everything works through the CLI and integrates seamlessly with git. **Learn more:** [github.com/steveyegge/beads](https://github.com/steveyegge/beads) ## Quick Start ### Essential Commands ```bash # Create new issues bd create "Add user authentication" # View all issues bd list # View issue details bd show <issue-id> # Update issue status bd update <issue-id> --status in_progress bd update <issue-id> --status done # Sync with git remote bd sync ``` ### Working with Issues Issues in Beads are: - **Git-native**: Stored in `.beads/issues.jsonl` and synced like code - **AI-friendly**: CLI-first design works perfectly with AI coding agents - **Branch-aware**: Issues can follow your branch workflow - **Always in sync**: Auto-syncs with your commits ## Why Beads? ✨ **AI-Native Design** - Built specifically for AI-assisted development workflows - CLI-first interface works seamlessly with AI coding agents - No context switching to web UIs 🚀 **Developer Focused** - Issues live in your repo, right next to your code - Works offline, syncs when you push - Fast, lightweight, and stays out of your way 🔧 **Git Integration** - Automatic sync with git commits - Branch-aware issue tracking - Intelligent JSONL merge resolution ## Get Started with Beads Try Beads in your own projects: ```bash # Install Beads curl -sSL https://raw.githubusercontent.com/steveyegge/beads/main/scripts/install.sh | bash # Initialize in your repo bd init # Create your first issue bd create "Try out Beads" ``` ## Learn More - **Documentation**: [github.com/steveyegge/beads/docs](https://github.com/steveyegge/beads/tree/main/docs) - **Quick Start Guide**: Run `bd quickstart` - **Examples**: [github.com/steveyegge/beads/examples](https://github.com/steveyegge/beads/tree/main/examples) ## Repo-Specific Agent Defaults This repository has legacy historical issue IDs mixed with current `coding_agent_session_search-*` IDs. To keep agent workflows stable: 1. Start triage with `bv --robot-triage` or `bv --robot-next`. 2. Use `br ready --json` to confirm actionable work. 3. Prefer explicit stale-safe flags on `br` commands in multi-agent sessions. Workspace config (`.beads/config.yaml`) sets: - `issue_prefix: coding_agent_session_search` - `allow_legacy_ids: true` - `no-auto-import: true` Runtime note: even with `no-auto-import: true`, some `br` invocations can still hit prefix-mismatch checks in this mixed-ID workspace. Use explicit flags for reliable operation: - `br ready --json --no-auto-import --allow-stale` - `br show <id> --json --no-auto-import --allow-stale` - `br list --status=open --json --no-auto-import --allow-stale` This preserves access to legacy records while avoiding auto-import validation paths that can fail in shared sessions. --- *Beads: Issue tracking that moves at the speed of thought* ⚡ # SQLite databases *.db *.db?* *.db-journal *.db-wal *.db-shm # Daemon runtime files daemon.lock daemon.log daemon.pid bd.sock sync-state.json .sync.lock # Local version tracking (prevents upgrade notification spam after git ops) .local_version # Legacy database files db.sqlite bd.db # Merge artifacts (temporary files from 3-way merge) beads.base.jsonl beads.base.meta.json beads.left.jsonl beads.left.meta.json beads.right.jsonl beads.right.meta.json # Keep JSONL exports and config (source of truth for git) !issues.jsonl !metadata.json !config.json # Local history backups .br_history/ # bv (beads viewer) lock file .bv.lock sync-branch: beads-sync allow_legacy_ids: true issue_prefix: coding_agent_session_search no-auto-import: 'true' coding_agent_session_se