boshu2/agentops

1

ms meta_skill (ms) — the skill-search/load engine over both corpora (agentops + jsm). Find a skill for a task, search sk…

boshu2/agentops

29

2

postmortem Optionally test a retrospective causal question against durable verdict evidence. Triggers: "postmortem", "causal ret…

boshu2/agentops

28

3

curate Mine transcripts, .agents, br, and git for skill diffs, br updates, or rare wiki entries. Triggers: "curate skills fr…

boshu2/agentops

27

4

skill-auditor Audit SKILL.md files against the AgentOps template and readiness checks. Use for quality reviews or template complian…

boshu2/agentops

26

5

system-tuning Restore system responsiveness via safe, ordered process cleanup and agent-swarm hygiene.

boshu2/agentops

22

6

craft-goal Compile or lint a persistent Mayor-style goal prompt that ratchets a bead graph through bounded RPI experiments towar…

boshu2/agentops

19

7

hooks-authoring Author AgentOps runtime hooks.

boshu2/agentops

19

8

fitness Measure declared project fitness goals without recommending or applying work. Triggers: "fitness", "check project fit…

boshu2/agentops

15

9

using-flywheel Operate the Agentic Coding Flywheel as a caller-selected software factory; keep its runtime state out of AgentOps ver…

boshu2/agentops

13

10

beads-br Local-first issue tracker (beads_rust) for AI agents — track tasks, manage dependencies, find ready work, sync via gi…

boshu2/agentops

11

11

beads-bv Graph-aware task triage with bv and br — prioritize work, find bottlenecks, track dependencies across projects. Trigg…

boshu2/agentops

11

12

eval-outcomes Grade agent or model output against Outcomes for holdout-safe evals and runtime comparisons. Fold target for scenario…

boshu2/agentops

11

13

session-bootstrap Universal init prompt — every agent spawned into an AgentOps repo runs `ao session bootstrap` first.

boshu2/agentops

11

14

ship-loop Bot-paired fast-lane cycle for coherent-arc internal PRs (one closable bead or small-epic slice): claim → test → impl…

boshu2/agentops

11

15

converge Drive a fix -> re-run-judge-panel loop to terminal agreement or a hard BLOCK via the Go ao converge command. Triggers…

boshu2/agentops

10

16

judge DEPRECATED: Use /council instead. Multi-model validation council.

boshu2/agentops

10

17

pre-land-refuters Dispatch fresh-context refuters (model-agnostic; multi-model opt-in) to attack a completion claim at the shared-trunk…

boshu2/agentops

10

18

agy-headless-evidence Run AGY headlessly via scheduled ticks or `agy -p`, capture agentapi JSONL evidence, and validate automated AGY loops…

boshu2/agentops

8

19

beads-workflow Use when converting markdown plans into br beads with dependencies for implementation or swarm execution. Triggers: "…

boshu2/agentops

8

20

using-atm Use ATM as the out-of-session substrate: spawn Claude/Codex panes running /rpi and /evolve over a bead queue, then te…

boshu2/agentops

8

21

vibing-with-ntm Use when tending NTM agent swarms, unsticking panes, handling rate limits, or coordinating convergence.

boshu2/agentops

8

22

anti-ceremony Guard outcome work against process overhead. Triggers: RPI pre-Plan guard; explicit "full anti-ceremony audit" reques…

boshu2/agentops

7

23

behavior-first-planning Behavior-first planning discipline — intent → Gherkin behaviors → EXECUTED-red acceptance tests → spec → acceptance-g…

boshu2/agentops

7

24

codex-approval Use when Codex needs Fable approval through an ATM/NTM validator pane. Triggers: - codex approval - ask fable - fable…

boshu2/agentops

7

25

continuity-loop Own the unattended renewal spine: renewal ticks, the two-tick stall rule, escalation for NTM panes over MCP Agent Mai…

boshu2/agentops

7

26

expert-council Alias for /council --mode=debate — adversarial named-persona debate. Triggers: "expert council", "dueling council", "…

boshu2/agentops

7

27

dual-pane-atm Repeatable mixed-model ATM duel — Opus (Claude) + Codex (+AGY) panes, or an in-session variant for a one-shot one-way…

boshu2/agentops

5

28

human-only-skills Name the skills reserved for people to invoke — where the runtime honors disable-model-invocation — and when to reach…

boshu2/agentops

4

29

one-way-door Classify a pending decision as reversible or irreversible before it is acted on, and route irreversible ones to the c…

boshu2/agentops

4

30

operating-loop-workflow Install and run the operating-loop multi-agent Workflow (the seven-move loop) for AgentOps plugin users.

boshu2/agentops

4

31

orchestrate Out-of-session orchestration instrument lane: route, preflight, verify before human atm/am procedure. Triggers: "orch…

boshu2/agentops

4

32

route Pick the one AgentOps skill that owns a request, or answer that none does. Triggers: "which skill covers this", "rout…

boshu2/agentops

4

33

skill-eval Author and tier behavioral probes for a skill, including seeded-defect probes that escape ceiling saturation. Trigger…

boshu2/agentops

4

34

burndown Drive a finite epic set to all-merged, then stop.

boshu2/agentops

3

35

dueling-idea-genies Challenge a consequential idea with sealed independent perspectives, cross-review, and preserved dissent. Triggers: "…

boshu2/agentops

3

36

bd-first-memory-migration Consolidate fragmented agent-memory layers into one bd-canonical store, then GC/retire the rest. Triggers: "memory mi…

boshu2/agentops

2

37

gc-membrane The agentops-membrane pack: fail-closed cross-family verdict-bound close door on stock gc — close gate, finalize, paw…

boshu2/agentops

2

38

goal-design Create validated goal-design packets. Triggers: "goal prompt", "goal-design packet", "turn this goal into loop-ready …

boshu2/agentops

2

39

known-bad A test fixture that intentionally fails Pass-2 checks.

boshu2/agentops

2

40

known-good Test fixture skill that satisfies all 15 auditor checks (Pass 1 + Pass 2). **Use when:** - The auditor integration t…

boshu2/agentops

2

41

pawl-review Run one fresh, read-only, nonce-bound reviewer lane and hand its evidence to ao pawl without deciding the panel verdi…

boshu2/agentops

2

42

project-readme-craft Use when writing READMEs that help users install, run, test, troubleshoot, and adopt a project. Triggers:

boshu2/agentops

2

43

using-ntm Use NTM as the out-of-session substrate: spawn Claude/Codex panes running /rpi and /evolve over a bead queue, then te…

boshu2/agentops

2

44

agy-mcp-plugins Wire MCP servers and AgentOps plugin bundles into the AGY image with least-privilege tool access and rollback evidenc…

boshu2/agentops

1

45

agy-rules-workflows Install AGY rules, workflow, goal, and schedule controls for AgentOps loop law. Triggers: AGY rules, agy-loop, AGY sc…

boshu2/agentops

1

46

artifact-clarity-pass Use when removing generic filler from code, docs, or handoffs while preserving every load-bearing fact. Triggers:

boshu2/agentops

1

47

automation-loop-hardening Use when turning repeated manual operations into safer, observable, reusable automation loops. Triggers:

boshu2/agentops

1

48

bead-completion-audit Use when auditing closed beads for real shipped evidence, acceptance proof, and truthful closeout. Triggers:

boshu2/agentops

1

49

bead-tracker-migration Use when migrating an issue tracker workspace from bd to br with loss-free verification. Triggers:

boshu2/agentops

1

50

behavior-preserving-simplification Use when simplifying code, reducing duplication, or clarifying flow while preserving behavior with tests. Triggers:

boshu2/agentops

1