fwd

Plugin fwd in baswenneker/fwd-skills. Commands read from the repo's manifest — 3 days ago.

Skills (20)

• codex-review-implementation

  Adversarial review of the DIFF after implementation, checked against a resolved plan — a /fwd:plan contract, a /fwd:mission-plan mission, or a /fwd:steps-plan steps-plan — delegated to Codex through the codex plugin's rescue runtime. Determines the diff scope automatically (a resolved mission/steps

• codex-review-plan

  Adversarial review of a plan BEFORE any code is written, delegated to Codex through the codex plugin's rescue runtime. Resolves the plan itself — a /fwd:plan contract, a /fwd:mission-plan mission, or a /fwd:steps-plan steps-plan (also accepts a path or pasted plan text) — then has Codex attack it fo

• mission-plan

  Plan a multi-agent "mission" — scope a software goal through conversation, write a PRD plus a validation contract (what "done" means, before any code), decompose into features and milestones, then create the mission branch and persist the plan on it. The interactive half of the fwd:mission-* orchest

• mission-run

  Execute a planned mission — the resident orchestrator of the fwd:mission-* layer (a Claude Code take on Factory.ai Missions). Reads the mission's state.json, drives features one at a time by spawning a fresh coder subagent each, runs adversarial validators (Scrutiny + User-Testing) at milestone boun

• plan

  Plan een feature, refactor of wijziging met DoD, 1-3 plannen en een verdict. Use when user invokes /fwd:plan of een implementatie wil plannen

• skill-eval

  Black-box self-evaluation for any Claude Code skill. Reads the target SKILL.md, extracts its surface (triggers, CLI flags, input/output formats, documented exit codes, examples), generates ~10 experiments covering happy paths, flag interactions, error paths, and domain invariants, runs each in an is

• steps-plan

  Plan een klus als een reeks kleine, toetsbare stappen voor uitvoering met /fwd:steps-run — de lichte tegenhanger van fwd:mission-plan. Scope het doel kort, pin een Definition of Done mét concreet eindbeeld (input→output-voorbeeld of ASCII-mockup), spreek de testplekken (seams) af, en lever een genum

• steps-run

  Voer een stappenplan van /fwd:steps-plan uit — attended (precies één stap per beurt) of autonoom (alle stappen achter elkaar, commit per stap), zoals in het plan afgesproken als `run_mode` en per sessie te overrulen met een tweede argument (`auto` / `attended`). Per stap; falende test eerst (rood),

• explain

  Break down anything heavy — a plan, code file, diff, doc, stack trace, PR, URL, or concept — into a layered walkthrough. Builds a mental model first (problem framed + best-fit form: diagram, analogy, before/after, or causal narrative — plus structure map), then one chunk at a time on demand. Use whe

• premortem

  Stress-test a plan by imagining it has already failed, then list concrete failure modes, grade each on Likelihood × Impact, and ICE-rank candidate mitigations for the meaningful ones. Use when user wants to pre-mortem a plan, asks "what could go wrong", wants to harden a design before commitment, or

• unsure

  Noem de 3 zaken waar je het minst zeker van bent — in een plan, ontwerp, diff, aanpak of in je eigen zojuist gegeven antwoord: wat wankelt, waarom, en wat het zou beslechten. Gebruik deze skill zodra iemand twijfel opvraagt of naar een zwakke plek zoekt: "waar ben je het minst zeker van", "wat is je

• changelog

  Automatically generate and update CHANGELOG.md based on recent changes. Writes directly without asking for confirmation.

• git-commit

  Stage and commit with conventional message — pre-flight scan blocks risky files (.env, logs, keys, secrets, >1MB)

• rules-audit

  Interactief de `.claude/rules/` directory bootstrappen voor een repo. De skill scant de codebase, stelt regelbestanden voor — elk voorzien van minimaal één golden example (een pad naar een echt, exemplarisch bestand) — en schrijft pas weg na expliciete goedkeuring van de gebruiker. Gebruik bij "rule

• setup-precommit

  Sets a repo up with pre-commit hooks. Runs unattended — zero prompts, project-local. Writes a .pre-commit-config.yaml with file checks and whitespace fixers (pre-commit-hooks), gitleaks, a Conventional Commits check on the message, autofixing formatters for the languages it finds (ruff for Python, s

• setup

  Setup wizard for HeadingFWD's optional Claude Code conventions. Runs unattended — zero prompts: installs every convention in one batch. Project-local: smartlint Stop-hook, lessons memory file, gitignore entries for fwd runtime artefacts, clear-context prompt on plan accept, no-attribution (disables

• caveman

  Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /fwd:caveman.

• explainer

  Builds a visual HTML explainer of anything heavy. It publishes it as an artifact with hand-drawn diagrams and, where the subject has them, real screenshots, maps and terminal output, all verified by actually rendering them. Invoke when someone says "create an html explainer", "create an explainer",

• jip-janneke

  Rewrites a referenced text into plain, readable language — "jip-en-janneketaal". One pass, chat output only; output is always Dutch unless another language is explicitly requested. Invoke when someone says "maak dit leesbaarder", "schrijf dit in jip-en-janneketaal", "leg uit in jip janneke", "leg di

• next-steps

  Answers "en nu?" with a short status block in Dutch -- one fact about where we stand, then one numbered list of next steps in the order they happen, with the user's own steps marked JIJ -- and ends with an offer to start, here or through the autocoder. Looks at the current session only and changes n