wickedagilewicked-garden

the toolkit · open-source · MIT

The tools your coding agentcan’t build alone.

Your harness already plans, swarms, and ships. wicked-garden refuses to wrestle it and fills only the gaps a planner-executor can’t fill alone — starting with the one that matters most: done is re-derived from evidence, never asserted.

load out garden and its peers — one command

interactive · picks your products across CLIs · direct install below

  • 94 skills
  • 12 domains
  • 10 work-shapes
  • MIT · local-first
agent · buildarmed
all acceptance tests pass
the agent asserted this. the gate doesn’t trust the stamp.
re-deriving from evidence…
auto-playing · hover to hold · tap a dot to pin

01 / the toolbox

Six gaps your agent can’t close alone.

Your harness plans, swarms, and ships. These are the six things a planner-executor genuinely can’t do on its own — and they’re a sample: the full kit runs to 94 skills across 12 domains. It plays itself; click any tool to pin it.

auto-playing the demos — click any tool to pin it and take control
“all tests pass”
REJECTED
the verifier never ran
proveevidence gate

Re-runs the proof behind the claim. A false pass is REJECTED; a missing backend FAILS CLOSED. Never a vacuous green.

garden skill

02 / the gate

Play the lying agent. Watch the gate refuse.

Garden’s one non-negotiable, made drivable. It plays itself — breaking the evidence and re-stamping the verdict. Flip a switch or pull the lever to take control: the gate re-derives the claim instead of taking your word for it.

evidence conditionsgate: armed
pull the lever — the gate stamps a verdict
auto-playing the gate — flip a switch or pull the lever to take control
claim card · archetype: build
build: all acceptance tests pass

The agent stamped this “done.” The gate re-runs the verifier, re-hashes the recording, and checks the vault is even there. Break a condition and prove it can’t be fooled.

03 / the whole toolkit

Six tools were the sample. Here’s the rest.

The toolbox shows the signature gap-fillers. Underneath sits the full surface — 94 skills across 12 domains, 34 of them fork/worker skills that run in isolated subagent contexts — all reading the same evidence-first discipline. Everything below is real and in the repo today.

product & UX25 skills

Vague ask → SMART criteria, UX & a11y review, mockups, visual direction, user-signal synthesis.

requirements-analysisacceptance-criteriaux-reviewaccessibilitymockupstrategy
platform & ops16 skills

The rubric on demand — security, compliance, incident, infra, distributed traces, CI.

auditcomplianceincidentinfraobservabilitygithub-actions
engineering14 skills

Graph-driven change — rename & patch across files, debug from a trace, architecture, docs.

architecturedebuggingpatchsystem-designintegrationlarge-scale-migration
agentic review9 skills

Review the agentic codebase itself — topology, framework detection, trust & safety.

agentic-patternscontext-engineeringframeworksreview-methodologytrust-and-safety
orchestration9 skills

Orchestration workers — implement, research, review; swarm, worktrees, workflow runners.

crew-implementercrew-researchercrew-reviewerswarmworktreesworkflow
context7 skills

Pull-model context — briefing, intent, propose-skills, classify a request, ground it in the repo.

discoveryintentpropose-skillsclassifyground
multi-model4 skills

A second opinion that isn’t self-grading — an independent external-model panel and facilitator.

councilbrainstormmulti-model
evidence2 skills

Evidence, re-derived — prove re-runs the proof; a semantic reviewer checks intent, not just diffs.

proveqe-semantic-reviewer
data & ML2 skills

ETL, data-quality, ontology, and ML workflows under the same evidence discipline.

datadata-engineer
personas2 skills

Run any task under a named behavioral profile — a reusable review cast on demand.

personapersona-agent
code intelligence2 skills

Impact & lineage over the real graph — the injected edges grep and a static call-graph can’t see.

blast-radiuslineagecodebase-narrator
work-shapes2 skills

Ten shapes read off each prompt — a typo to a cutover; deliberate challenges the ask first.

triagebuildmigratereviewdeliberate

One install bundles the family. Every peer is an opt-in layer you adopt when you want it — the kit works without any of them. The evidence backend the gate re-derives against rides inside wicked-testing, not a separate install.

wicked-testingopt-in layerwicked-brainopt-in layerwicked-busopt-in layerwicked-interactiveopt-in layer

04 / the bench

One command. The whole loadout.

The family installer is the fastest way in — one interactive command that picks your products across every CLI and installs the shared wicked CLI. Prefer just this plugin? The direct path is right below.

the family installer · recommended

interactive · picks your products across CLIs · ships the wicked CLI

or install just wicked-garden directly

add from marketplace
install the plugin

MIT · open-source · v12.27.0 · local-first — nothing leaves your machine.