Skip to content

umararshad4/honey-stack / skills/honey

Pick the honey-stack skill or flow for a situation, or switch response modes: direct, explain, balance, status, off, on, default.

honey

Router and mode switch for honey-stack.

  • Mode words (direct, explain, balance, status, default direct, …): apply them per the Modes section and reply with one status line.
  • update hooks: follow references/update-hooks.md for a one-time Honey release check and Codex hook review.
  • A situation ("I have a bug report and a half-written plan"): name the skill or flow that fits, say why in one line, then run it.
  • Nothing: show the main flow and the situation table below, trimmed to what fits the current repo.

Main flow: idea to shipped

grill ──> prototype? ──> plan ──> execute ──> verify ──> review ──> ship
  1. grill: pin down intent and the product calls the repo can't answer. Quick or small work skips straight to building.
  2. prototype, only when a question needs a runnable answer (behavior, timing, a layout you have to see). Bridge out and back with handoff if it needs its own session.
  3. plan: a session plan for work that fits one or two sessions, or a spec plus tracer-bullet tickets for a multi-session build.
  4. execute: drain the plan, tickets, or TODO.md without check-ins. For tickets, one fresh session per ticket.
  5. verify after each item, review on the finished diff, ship when the user asks to commit, push, or open a PR.

Bugs merge onto the flow at debug, which hands its fix to verify.

Situation to skill

SituationSkill
Vague idea, missing product decision, "grill me", "brainstorm"grill
Question only running code can settle; throwaway sketchprototype
Multi-file or multi-session work; plan, spec, PRD, ticketsplan
"continue", "next", "do the TODOs", "run the plan"execute
Broken, throwing, failing, flaky, slow; a fix that didn't workdebug
Writing a feature or fix test-first at an agreed seamtdd
About to say done, fixed, or passingverify
Diff or PR ready for a second look; self-reviewreview
Commit, push, PR, release, changelogship
Deploy to a cloud/PaaS, write Docker/K8s/IaC, fix a failing deploy or pipelinedeploy
Design the test matrix and hard edge cases for a feature before writing teststest-design
Set up a monorepo, micro-frontend, microservices, pre-commit hooks, lint/format/CItooling
Schema design, migrations, indexing, slow queries, N+1, transactionsdatabase
Profiling, hot paths, caching, load testing, backend perf with before/after numbersperf
Logging, metrics, tracing, error tracking, SLOs, alerting, instrument a serviceobservability
Design or version a REST/GraphQL/gRPC API, error contracts, pagination, idempotencyapi-design
Safely upgrade dependencies, patch a CVE, handle a breaking change or EOLupgrade
A production outage: triage, mitigate, roll back, communicate, postmortemincident
A skill misfired or a lesson should stick; improve honey-stack itselfrsi
UI, layout, styling, responsive, design-system workfrontend
Mocked product UI illustrations or animated cursor demosstageshow
Application animation, motion audit or dropped framesfrontend (motion references); review or perf for their respective checks
Drive the real app to find bugs before users doqa
Auth, sessions, secrets, payments, user data, webhookssecurity
Behavior, setup, commands, or APIs changed; docs driftdocs
Text reads like AI wrote it; tighten a message, post, prompt or docunslop
Thread is long or branching; carry state to a fresh sessionhandoff
Codebase hard to change or test; deepen modules, find seamsarchitecture
Name the domain terms, keep CONTEXT.md and ADRsdomain
Learn a concept over several sessionsteach
Write or edit a skillwrite-skill
A design call needs a named principle (root cause, idempotency, boundaries)principles
Need a library's real source or docs for a declared dependencyopensrc
Research a technical/product question against primary sourcesresearch
Create or maintain this project's launch/drive/evidence harnessproject-verify
Qualify issues, deduplicate reports or prepare an actionable agent brieftriage
Model a queue, retry or workflow invariant and its counterexamplesstatechart
Show honey's measured benchmark gainsgain
Understand a shipped app, binary, APK or site you don't have source for (authorized)reverse-engineer

When two rows fit, take the earlier one in the main flow: settle intent before planning, plan before executing.

Overlaps — which one wins

  • debug vs incident: local/non-urgent root-cause → debug; production is down or degraded right now → incident (mitigate first, then debug for the root cause).
  • perf vs database: a slow query, N+1, index, or migration → database; profiling, caching, load testing, or a non-DB hot path → perf. A slow endpoint caused by SQL is database; by CPU/serialization/IO is perf.
  • tdd vs test-design vs qa: what cases to test → test-design; writing them test-first → tdd; driving the real browser/UI → qa.
  • review vs verify: judging someone's diff/PR → review; proving your own change is actually done before you claim it → verify.
  • ship vs deploy: commit/push/PR → ship; getting it running on a server/cloud → deploy.
  • security vs upgrade: a design/code security concern or audit → security; patching a vulnerable dependency → upgrade.
  • docs vs unslop: writing/updating project docs → docs; tightening any prose of AI tells → unslop.
  • project-verify vs verify vs qa: author/maintain a project harness → project-verify; prove a particular change → verify; browser interaction → qa. Reuse the project's harness when it exists.
  • triage vs debug: qualify a report and prepare a brief → triage; investigate a confirmed failure → debug. A proposed fix is not verification.
  • research vs opensrc: broad primary-source investigation → research; installed dependency API context → opensrc.
  • frontend vs stageshow: application motion and UI quality → frontend; mocked product illustrations and cursor demos → stageshow. qa owns stress/mobile evidence.

Modes

One response style at a time. All modes keep the same task sizing, verification, and safety rules.

WordEffect
directStraight to the point, concise responses.
explainComprehensive explanations with useful context, reasoning, and examples.
balanceModerate detail: answer plus key reasoning, neither comprehensive nor too brief.
statusPrint the active response mode and whether Honey is paused.
off / onPause the whole layer (bootstrap, hooks, routing) / resume it.
default <mode>Save the mode for new sessions, e.g. honey default direct.

The default is direct. Session switches last until changed or the session ends. The indicator includes the active choice, for example 🍯 HONEY · balance. Explicit requests for more or less detail take priority over the selected style.

The hook does the switching. Send honey explain or /honey balance (Codex: $honey balance) as the whole message and the prompt hook applies it before the model runs. If this skill receives mode words instead, the hook didn't fire: honor the mode in conversation for the rest of the session and say in one line that nothing was saved.

Existing saved terse settings read as direct, and normal as balance. Old scope/process choices no longer change the workflow. Saving a new default writes mode in the global config and removes the old modes field.

Explain active rules

When asked what Honey applied, identify the relevant bootstrap, skill or learned preference and the evidence of its use. honey doctor --agent codex --json (or --agent claude) reports observed hook delivery; honey task status --json reports task evidence. Instruction loading alone does not prove enforcement. A response-mode change only changes presentation; preserve learned preferences unless the user explicitly asks to change or forget them.

Context hygiene

  • One unbroken thread for grill → plan, so the plan argues from the same thinking. Compact or clear after the plan is written, not during grilling.
  • /clear (Codex: /new) between unrelated tasks. Leftover context from task A steers task B.
  • handoff forks; /compact continues. Use handoff when you want a fresh session but need this one's state (a prototype detour, a thread nearing its smart zone, the next ticket). Use /compact at a phase boundary inside one task when losing verbatim history is fine; never mid-debug or mid-grill, where the details are the work.
  • Fresh session per ticket. Start each with execute, the spec, and that one ticket.
  • Reasoning degrades well before the window is full. When a long thread starts repeating itself or losing decisions, write a handoff and continue fresh rather than pushing on.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 467kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 319kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 319kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 319kUpdated Claude CodeCodexVerifiedInstall