agentic development commands

181 tagged agentic development, measured the same way as everything else here.

Browse within: Multi-Agent 41llm-judge 41prompt-engineering 41agentic-workflow 36ai-coding-agents 34brownfield 34ci-cd 34code-quality 34agent-framework 30agents-md 30ai-governance 30ai-guardrails 30agentic-design-patterns 25ai-developer-tools 25

app-init

03

KbWen/agentic-os

Command Claude Code

Execute the canonical workflow: .agent/workflows/app-init.md.

149 7d ago A 0 tokens original MIT

bootstrap

04

KbWen/agentic-os

Command Claude Code

Execute the canonical workflow: .agent/workflows/bootstrap.md.

149 7d ago A 0 tokens original MIT

spec-intake

05

KbWen/agentic-os

Command Claude Code

Execute the canonical workflow: .agent/workflows/spec-intake.md.

149 7d ago A 0 tokens original MIT

status

06

Dowwie/tasker

Command

Display executor status dashboard with task progress and recent activity.

19 1mo ago A 10 tokens original Apache-2.0

tasker-to-beads

07

Dowwie/tasker

Command

Transform Tasker task definitions into rich, self-contained Beads issues.

19 1mo ago A 0 tokens original Apache-2.0

tui

08

Dowwie/tasker

Command

Launch the TUI status dashboard in a tmux split pane.

19 1mo ago A 12 tokens original Apache-2.0

allowlist

12

vyuh-labs/dxkit

Command

Per-finding suppression with a typed-category audit trail. The allowlist is dxkit's deliberate escape hatch for findings you can't fix today: false positives, intentional test-fixture patterns, real risks mitigated externally, or work you're deferring with an explicit deadline.

10 3d ago A 0 tokens original MIT

guardrail

13

vyuh-labs/dxkit

Command

Diff a current scan against a committed baseline and classify each finding as added / relocated / toolingdrift / configdrift / persisted / removed / fixed. Block on net-new regressions per the brownfield policy; exit non-zero so a pre-commit hook, pre-push hook, or CI workflow can stop the commit/push/merge.

10 3d ago A 0 tokens original MIT

remediate

14

vyuh-labs/dxkit

Command

Close the debt the deterministic lanes cannot version-bump away: the grandfathered broken build, advisories with no direct upgrade path, the lint backlog, missing tests, missing docs. Each run plans that debt as finite work orders and works them in two tiers: deterministic recipes execute first at $0 (lockfile resync…

10 3d ago A 0 tokens original MIT

auto-mode

17

ShaheerKhawaja/ProductionOS

Command Claude Code

Idea-to-running-code lifecycle orchestration. 10-phase pipeline with 5 hard decision gates, wave-based parallelism, and STATE.json resumability. Composes /deep-research, /auto-swarm-nth, /production-upgrade, /security-audit, and /ship into a single end-to-end flow.

8 4mo ago A 68 tokens original MIT

max-research

18

ShaheerKhawaja/ProductionOS

Command Claude Code

Nuclear-scale autonomous research — deploys 500-1000 agents in ONE massive simultaneous wave for exhaustive topic saturation. Deep-research methodology × auto-swarm scale = maximum parallel intelligence. WARNING: Extreme resource consumption.

8 4mo ago A 48 tokens original MIT

omni-plan

19

ShaheerKhawaja/ProductionOS

Command Claude Code

ProductionOS flagship — 13-step orchestrative pipeline with tri-tiered evaluation, recursive convergence, CEO/Eng/Design review chain, CLEAR framework evaluation, multi-model judge tribunal, and autonomous PIVOT/REFINE/PROCEED decisions. Targets 100% production-ready output.

8 4mo ago A 62 tokens original MIT