Build with agents.
Keep your judgment.

Practical reference for building, reviewing and teaching with agents. Find the reasoning, the tradeoffs and the exact text.

Reference library

22 references

  • Agent Markers debugging workflows: team walkthrough

    Marker-centered debugging using createAgentMarkers, browser-global marking and export, nearby-event association, privacy boundaries, cleanup, and project verification. Preserves the bounded debug-packet model, downstream work-unit bridge, failure recovery,…

    Team practiceagent-markersdebuggingprivacy
  • Context packing with Oracle and PackX: team walkthrough

    Skill-backed context packing and Oracle review: scope and evidence selection, preview and bundling, compact evidence, follow-up state tracking, CLAUDE.md exclusion, saved-log inspection, and locally authored project artifacts.

    Team practiceoraclepackxteam-guide
  • Controlled variation workflows: team walkthrough

    Controlled software variations using one variable, a shared prompt seed, isolated candidates, common verification, comparison records, and explicit Pick/Combine/Refine/Expand/Reject decisions, including billing-webhook examples and convergence failure…

    Team practicevariationsverificationcomparison
  • Fusion council decisions and evidence: team walkthrough

    Decision-focused multi-model council workflow: frame a billing-webhook tradeoff, write a prompt file, inspect providers, dry-run, execute the configured panel, and review final artifacts, disagreement, and verification before acting. Distinguishes local…

    Team practicefusioncouncilreview
  • Interview for judgment and build for agency

    Agent-heavy work eventually comes back to the human side of software practice.

    Team practicejudgmentagencyethics
  • Narrow Imp agents and routing: team walkthrough

    Bounded one-tool agent workflow covering routing, direct execution, foreground versus forked dash-prefix prompts, fleet health, warm-mode recovery, isolation, command evidence, and marker-packet handoff. Includes cmux inspection commands, fallback receipt…

    Team practiceimpsroutingisolation
  • Product vision and earned automation

    Keep product direction durable without freezing implementation, and promote recurring reviews only when their signal earns it.

    Team practicevisionautomationgates
  • Product vision and earned automation — discussion and evidence

    Detailed companion accounts of concepts, questions, demonstrations, exercises, and unresolved observations.

    Team practicevision-and-automationdiscussionevidence
  • Prompt Builder composition and handoff: team walkthrough

    Prompt composition and launch inspection through prompt text, shell commands, and JSON; named app-server threads; final-argv handoff; interactive composer controls; zsh helper bridges; and installation, binary-selection, and quoting diagnostics.

    Team practiceprompt-builderpromptspreflight
  • Questions, answers, and unresolved decisions

    The complete anonymized question reference, preserving answered, partial, deferred, unlinked, and unanswered status.

    Team practicequestionscaveatsdecisions
  • Reliable non-interactive shell environments: team walkthrough

    Diagnosing agent tool visibility through non-interactive login-shell startup, agent-safe PATH configuration, executable precedence, clean-shell checks, and separation of interactive helpers from executable setup.

    Team practicezshenvironmentpath
  • Shell functions, aliases, and executable boundaries: team walkthrough

    Shell command classification, alias/function/executable tradeoffs, helper discovery and source lookup, interactive inspection versus login-shell handoff, workflow helper families, and executable fallbacks for scripts and CI.

    Team practicezshhelperscli
Browse 10 more references