Cheatsheets

Quick reference commands for all ACFS tools. Click any command to copy.

Showing 7 of 7 tools

brBeads Issue Tracker

Git-native issue tracker. All state lives in .beads/ and is committed with code.

Issue Tracking
br ready --json

Show unblocked open beads

br create "title" -t bug -p 1

Create issue (type: bug/feature/task/epic/chore, priority: 0-4)

br update br-42 --claim

Claim a bead (set in_progress + assignee)

br close br-42 --reason "Done"

Close a bead with reason

br list -s open --json

List beads by status

br show br-42 --json

Show bead details

br update br-42 -p 0

Set priority (0=critical, 4=backlog)

br sync --flush-only

Export to .beads/issues.jsonl without git ops

Tips
  • "ready" is a query, not a status -- it means open + unblocked by dependencies.
  • Always commit .beads/ in the same commit as code changes.
  • Priority 0 = critical (security, data loss). Default is 2.
bvBeads Viewer

Graph-aware triage engine for Beads. Computes PageRank, critical paths, cycles, and parallel tracks.

Issue Tracking
bv --robot-triage

THE mega-command: full triage with ranked recommendations

bv --robot-next

Single top pick + claim command

bv --robot-plan

Parallel execution tracks with unblocks lists

bv --robot-insights

Full graph metrics: PageRank, betweenness, HITS, cycles

bv --robot-alerts

Stale issues, blocking cascades, priority mismatches

bv --robot-suggest

Hygiene: duplicates, missing deps, label suggestions

bv --robot-triage --label backend

Scope triage to a label's subgraph

bv --robot-forecast all

ETA predictions with dependency-aware scheduling

Tips
  • NEVER run bare `bv` -- it launches an interactive TUI that blocks your session.
  • Always use --robot-* flags for deterministic JSON output.
  • Phase 1 metrics are instant; Phase 2 (PageRank, etc.) has a 500ms timeout.
cmCass Memory System

Procedural memory for agents. Extracts lessons from past sessions and retrieves them for new tasks.

Search & Memory
cm context "task description" --json

Get relevant rules, anti-patterns, and history for a task

cm playbook list

List all playbook rules

cm playbook add "rule" --category "debugging"

Add a new rule to the playbook

cm reflect --days 7

Extract rules from recent sessions

cm doctor --fix

Health check and auto-repair

cm onboard status

Check onboarding progress

cm onboard sample --fill-gaps

Get sessions to analyze (filtered by playbook gaps)

Tips
  • Run `cm context` before every non-trivial task.
  • Context returns: relevantBullets, antiPatterns, historySnippets, suggestedCassQueries.
  • Leave inline feedback: // [cass: helpful b-xyz] or // [cass: harmful b-xyz].
cassCross-Agent Session Search

Indexes conversations from Claude Code, Codex, Cursor, Gemini, ChatGPT, etc. so solved problems can be reused.

Search & Memory
cass search "query" --robot --limit 5

Search past agent sessions

cass health

Check indexing status

cass view /path -n 42 --json

View specific message in a session

cass expand /path -n 42 -C 3 --json

View message with 3 lines of context

cass capabilities --json

List available search capabilities

cass robot-docs guide

Full robot-mode documentation

Tips
  • Never run bare `cass` -- it launches a TUI. Always use --robot or --json.
  • stdout is data-only, stderr is diagnostics. Exit 0 = success.
  • Use --fields minimal for lean output. Filter by agent with --agent.
ubsUltimate Bug Scanner

Static analysis tool that flags likely bugs before commit. Exit 0 = safe, exit >0 = fix and re-run.

Dev Tools
ubs file.ts

Scan specific file (<1 second)

ubs $(git diff --name-only)

Scan all changed files

ubs $(git diff --name-only --cached)

Scan staged files (pre-commit)

ubs .

Full project scan (auto-ignores .venv, node_modules)

ubs --ci --fail-on-warning .

CI mode -- strict, fails on warnings

ubs --only=js,python src/

Language filter (3-5x faster)

Tips
  • Golden rule: `ubs <changed-files>` before every commit.
  • Scope to changed files for speed. `ubs src/file.ts` (<1s) vs `ubs .` (30s).
  • Output format: file:line:col -- location, bulb icon = fix suggestion.
ntmNamed Tmux Manager

Agent cockpit for managing tmux sessions with multiple coding agents (Claude, Codex, Gemini).

Infrastructure
ntm ls

List all sessions

ntm new "name"

Create a new session

ntm attach "name"

Attach to an existing session

ntm send "name" "cmd"

Send a command to a session

ntm kill "name"

Kill a session

ntm health

Check tool and daemon health

ntm quota

Check agent quota usage

Tips
  • Sessions persist across SSH disconnects.
  • Use `ntm send` to dispatch prompts to agents without attaching.
  • Health check verifies all dependencies (tmux, claude, codex, gemini CLIs).
ruRepo Updater

Multi-repo sync tool with AI-driven commit automation. Manages cloning, pulling, and automated commits across all repositories.

Infrastructure
ru sync

Clone missing + pull updates for all repos

ru sync --parallel 4

Parallel sync with 4 workers

ru status --fetch

Fetch + show ahead/behind for each repo

ru agent-sweep --dry-run

Preview dirty repos to process

ru agent-sweep --parallel 4

AI-driven commits in parallel

ru list --paths

List all managed repo paths

Tips
  • Exit codes: 0=success, 1=partial failure, 2=conflicts, 5=interrupted (use --resume).
  • Always `ru status` before `ru sync` to preview changes.
  • Use --repos=pattern to scope operations to matching repos.