macros

Plugin macros from marketplace isnbh0 in isnbh0/shared. Commands read from the repo's manifest — 4 days ago.

Skills (20)

• anytime

  Explicit-request macro. Activate only when the user directly requests this macro; never infer activation from task characteristics. Skill — Run bulk work so partial results are usable at any moment and more time yields more results, with the stop condition set in conversation

• askme

  Explicit-request macro. Activate only when the user directly requests this macro; never infer activation from task characteristics. Skill — Shorthand that tells the agent to ask clarifying questions instead of making decisions on its own

• calibrate

  Explicit-request macro. Activate only when the user directly requests this macro; never infer activation from task characteristics. Skill — Iteratively align a mental model or state through purpose-driven passes that move from broad structure to consequential finer distinctions.

• chunked

  Explicit-request macro. Activate only when the user directly requests this macro; never infer activation from task characteristics. Skill — Sequence a task as ordered parts that add up to the whole. Each iteration may read prior iterations' outputs.

• consensus

  Explicit-request macro. Activate only when the user directly requests this macro; never infer activation from task characteristics. Skill — Run N blind agents on the same job in parallel, then merge findings into consensus/unique/conflicts. Agents report only — no edits for concurrent safety.

• delegate

  Explicit-request macro. Activate only when the user directly requests this macro; never infer activation from task characteristics. Skill — Use subagents to save context space and/or parallelize subtasks where possible

• doubt

  Explicit-request macro. Activate only when the user directly requests this macro; never infer activation from task characteristics. Skill — Spawns an independent subagent to critique recent work with web research. Use when the user wants a second opinion, says "doubt this", or wants to verify code a

• dredge

  Explicit-request macro. Activate only when the user directly requests this macro; never infer activation from task characteristics. Skill — Search prior coding-agent transcripts and prompt histories for past requests. Use when the user explicitly activates this skill or asks to recall or dig up some

• dry-run

  Explicit-request macro. Activate only when the user directly requests this macro; never infer activation from task characteristics. Skill — One-shot failsafe — describe what you would do for the current request instead of doing it, then wait for confirmation

• landscaping

  Explicit-request macro, active only when directly requested. Skill — Shaping the information environment so capable agents arrive at intended behavior through ordinary judgment.

• leeway

  Explicit-request macro, active only when directly requested. Skill — Interpretive latitude that uses enough precision to help without needless rigidity or literalism.

• mapreduce

  Explicit-request macro. Activate only when the user directly requests this macro; never infer activation from task characteristics. Skill — Split a task into parallel chunks, dispatch subagents, and consolidate results

• new

  Explicit-request macro. Activate only when the user directly requests this macro; never infer activation from task characteristics. Skill — Scaffold a custom macro for a project or user and selected agent hosts, with one source directory and the macros composition line.

• orchestrate

  Explicit-request macro. Activate only when the user directly requests this macro; never infer activation from task characteristics. Skill — Activate Orchestrator Mode — delegate execution to subagents by default and operate at the high level, conserving your own context for direction and synthesis

• packet

  Explicit-request macro. Activate only when the user directly requests this macro; never infer activation from task characteristics. Skill — Package work for completion outside the current agent loop at a durable filesystem boundary, then validate returned artifacts and resume dependent work.

• rigor

  Explicit-request macro. Activate only when the user directly requests this macro; never infer activation from task characteristics. Skill — Activate Rigor Mode — prioritize correctness, thoroughness, and web-grounded verification over minimalism while active

• seq

  Explicit-request macro. Activate only when the user directly requests this macro; never infer activation from task characteristics. Skill — Run N serial blind passes on the same job with commits between. Each pass works on the current code state with fresh eyes. Requires a clean worktree.

• timeless

  Explicit-request macro. Activate only when the user directly requests this macro; never infer activation from task characteristics. Skill — Shorthand that tells the agent to avoid time estimates — hours, days, calendar dates, or size buckets that map to time. Describe complexity and scope instead.

• timestamp

  Explicit-request macro. Resolve the timestamp value the user refers to with the `date` CLI.

• tmi

  Explicit-request macro. Activate only when the user directly requests this macro; never infer activation from task characteristics. Skill — Flag content a future reader doesn't need — session residue, defensive justifications, phantom counterarguments, unsolicited caveats, backstory, speculation