Help us improve
Share bugs, ideas, or general feedback.
From agentops
Persistent graph-based issue tracker that survives conversation compaction. Track issues with bd/br CLI, triage with bv, and export to git-friendly JSONL.
npx claudepluginhub boshu2/agentops --plugin agentopsHow this skill is triggered — by the user, by Claude, or both
Slash command
/agentops:beadsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Graph-based issue tracker that survives conversation compaction.
references/ANTI_PATTERNS.mdreferences/BOUNDARIES.mdreferences/BR_REFERENCE.mdreferences/BV_TRIAGE.mdreferences/CLI_REFERENCE.mdreferences/DEPENDENCIES.mdreferences/INTEGRATION_PATTERNS.mdreferences/ISSUE_CREATION.mdreferences/MIGRATION.mdreferences/MOLECULES.mdreferences/PATTERNS.mdreferences/PLAN_TO_BEADS.mdreferences/RESUMABILITY.mdreferences/ROUTING.mdreferences/STATIC_DATA.mdreferences/TROUBLESHOOTING.mdreferences/WORKFLOWS.mdreferences/beads.featurereferences/composition-over-invention.mdreferences/tracker-migration-and-triage.mdGuides technical evaluation of code review feedback: read fully, restate for understanding, verify against codebase, respond with reasoning or pushback before implementing.
Share bugs, ideas, or general feedback.
Graph-based issue tracker that survives conversation compaction.
bd and br (beads_rust) replace markdown task lists with a dependency-aware graph stored in git. bv adds graph-aware triage using PageRank and betweenness centrality.
Key Distinction:
Decision Rule: If resuming in 2 weeks would be hard without bd, use bd.
br vs bd: br is the Rust rewrite. Commands are the same except: br never auto-commits (git is your job), and bd sync becomes br sync --flush-only. Use whichever is installed.
bv safety: NEVER run bare bv — it launches interactive TUI and blocks the terminal. Always use --robot-* flags.
Don't re-learn the command surface here. bd --help / br --help (and per-subcommand --help) self-describe every command and flag — run them before specifying enforcement commands; compose primitives, don't invent (composition-over-invention.md). Full catalogs ship in CLI_REFERENCE.md (bd), BR_REFERENCE.md (br), and BV_TRIAGE.md (bv robot flags). This skill carries the operating doctrine.
bd reads as authoritative. Use bd show, bd ready, bd list, and bd export to inspect current tracker state. Do not treat .beads/issues.jsonl as the primary decision source when live bd data is available.ao reconcile --json when available. Treat bd ready as planning input only after high-severity main/release/bead evidence findings are resolved or explicitly superseded..beads/issues.jsonl as a git-friendly export artifact. If the repo tracks .beads/issues.jsonl and you mutate tracker state, refresh it explicitly with bd export -o .beads/issues.jsonl.bd close --reason text.
Name the touched files or explicit no-file evidence artifact, validation command(s), and parent
reconciliation outcome. Do not use generic closure reasons such as "done" or "implemented" for child beads.bd ready returns a broad umbrella issue, do not implement directly against vague parent wording. First narrow the remaining gap into an execution-ready child issue, then land the child and reconcile the parent.bd ... # mutate tracker state
bd export -o .beads/issues.jsonl # if tracked in git
bd vc status
bd dolt commit -m "..." # if tracker changes are pending
bd dolt push # only if a Dolt remote is configured
Session ending pattern (br — sync is EXPLICIT, never automatic):
git pull --rebase
br sync --flush-only # DB → JSONL (reverse: --import-only after pull)
git add .beads/ && git commit -m "Update issues"
git push
bd init run once (humans do this, not agents)User says: /vibe
This skill loads via dependency: the agent reads issue metadata with bd show <id>, links validation findings to the issue under check, and cites the issue ID in the validation report — no manual bd lookups.
User says: /implement ag-xyz-123
This skill loads to manage the issue lifecycle: bd show ag-xyz-123 for the body, check dependencies, and bd close ag-xyz-123 (with scoped closure proof) after completion.
NEVER run bare bv. Always use --robot-* flags (--robot-triage, --robot-next, --robot-plan, --robot-insights, --robot-priority, --robot-alerts — selection guide in BV_TRIAGE.md).
Key metrics: PageRank = everything depends on this (fix first). Betweenness = bottleneck (blocks multiple paths). High both = critical bottleneck, drop everything.
Convert a markdown plan into fully dependency-wired beads:
br create for each issue, including full context in the description.gherkin
block or link to a filled intent issue. Mechanical chores may omit Gherkin
only when their acceptance criteria are fully command/file based.hexagon: boundary block from
docs/architecture/intent-to-loop-hexagon.md for substantial beads:
inbound port, bounded context, adapters, context packet, and done state.br dep add / bd dep add. Do not hand-edit JSONL or
database files.br dep cycles must be empty; run bv --robot-insights for graph
health; use bv --robot-next for the first bead. Never run bare bv.br sync --flush-only, then git add .beads/
and commit tracker changes when appropriate.Beads should be so detailed that a fresh agent can implement without consulting the original plan. Ready-to-implement beads have clear scope, explicit dependencies, BDD or mechanical acceptance, unit/e2e test expectations, detailed logging expectations, a named done state, and no dependency cycles.
Symptom → fix table (command not found, not-a-git-repo, init missing, ID prefix errors, bv hangs, dependency cycles, sync direction confusion): TROUBLESHOOTING.md. The two most common: a hung bv means a robot flag was omitted; br sync confusion means the direction (--flush-only vs --import-only) wasn't specified.
references/beads.feature — Executable spec: bd-mandatory tracker, create-before-code, ready-detection, discovered-from links, live-reads-authoritative (soc-qk4b)
references/composition-over-invention.md — Run bd <subcmd> --help before specifying enforcement commands; compose primitives, don't invent