Are you the author? Sign in to claim
Claude Code plugin marketplace — agentic-engineering (spec-driven shape→decide→execute→measure→eval with adversarial rev
A spec-driven workflow for building with coding agents. Never go prompt → code: shape → decide → execute → measure → eval.
Install · Quickstart · What you get · Plugin reference · Claude Code docs
shape decide execute verify diagnose
┌─────────┐ ┌─────────┐ ┌──────────┐ ┌───────────┐ ┌──────────┐
│ /pitch │──▶│ /adr │──▶ │ /ship │──▶ │ /measure │──▶ │ /eval │
│ the spec│ │ the why │ │ the cycle│ │ the data │ │ the modes│
└─────────┘ └─────────┘ └──────────┘ └───────────┘ └────┬─────┘
▲ │ │
│ ▼ │
│ ┌─────────┐ │
│ │ /graph │ fan breadth work out across a fleet, │
│ │ fan-out │ verify each finding, converge │
│ └─────────┘ │
└─────────────── flip-criteria · real failures ◀────────────┘
readers fan out · one writer at a time · review is a gate · data decides
Coding agents make it cheap to go from a prompt straight to a diff — and that's exactly the trap. Unshaped work balloons in scope, decisions get lost, and a green build gets mistaken for a correct one.
This plugin encodes a different discipline, distilled from a real, opinionated agentic-engineering practice: shape the work into a written spec first, record the hard decisions, delegate execution to a single serialized writer with an adversarial reviewer as a gate, fan breadth work out across a fleet instead of chaining it one task at a time, and let real data — not a passing test — decide what ships. Six skills, five subagent roles, and verification hooks make that discipline portable to any repo — see the graph model for the underlying lens.
[!NOTE] These are early, opinionated tools — structurally validated and dogfooded on this repo, not yet battle-tested across many. Feedback and issues are welcome. Distributed as a Claude Code marketplace named
giusto-agentic; one marketplace can host many plugins.
In Claude Code:
/plugin marketplace add GiustoPiedimonte/agentic-engineering-marketplace
/plugin install agentic-engineering@giusto-agentic
claude plugin marketplace add GiustoPiedimonte/agentic-engineering-marketplace
claude plugin install agentic-engineering@giusto-agentic
The six commands and five agents become available. New components load on your next Claude Code session.
Third-party marketplaces don't auto-update by default (a deliberate safety choice — installed plugins shouldn't change under you silently). Two ways to stay current with new releases:
/plugin → Marketplaces → giusto-agentic → toggle auto-update on. Claude
Code then refreshes it on startup and, when a new version ships, notifies you
to run /reload-plugins — no manual checking./plugin marketplace update giusto-agentic
/plugin update agentic-engineering@giusto-agentic # and/or github-keeper@…
/reload-plugins (or restart). The CLI equivalents are claude plugin ….Releases are versioned — see the releases and the CHANGELOG.
A typical end-to-end cycle, from idea to merged code:
/pitch "add Google OAuth to login" — an interview produces
docs/pitches/oauth.md, naming the graph the work touches and its gated edges.
Approve the shape before any code is written./clear, then /adr if a consequential choice was made (e.g.
session strategy). Behavior-altering work records a Flip-criteria./clear, then /graph for audits, reviews,
or research that spans many independent pieces — fan out across a fleet of
subagents, verify each finding, converge./clear, then /ship oauth — the executor implements and opens
a PR; the reviewer checks the diff against the pitch in a fresh context; you
fix the real gaps and merge./measure
against the recorded criterion flips them on — on real data, not a green build.[!TIP] Run
/clearbetween stages. Separating exploration, decision, and execution into clean contexts is the single biggest lever on output quality.
| Command | What it does |
|---|---|
/pitch | Shape a feature into a Shape Up pitch (the spec / source of truth) via interview, before any code. Names the graph the work touches and its gated edges. |
/adr | Record a consequential decision in an append-only docs/DECISIONS.md, with optional dark-launch Gate/Flip-criteria. |
/graph | Turn a straight-line task into an execution graph: fan breadth work (audits, reviews, research) out across a fleet of subagents, verify findings, converge. Built on dynamic workflows — coordination costs zero model tokens. |
/ship | Execute an approved pitch as a closed-scope cycle: pre-spawn filter, doc-bundle, standard PR format, adversarial review, dark-launch flip. |
/measure | Unblock a decision with a read-only, data-backed flip/keep/cut verdict — never guesses, never writes. |
/eval | Make eval the unit of progress: build the harness from real failures, localize where a pipeline breaks (transition-failure matrix), feed flip-criteria. |
The organizing law is parallelize readers, serialize writers: research and review fan out across many agents; only one writer ever touches the code.
| Agent | Role |
|---|---|
executor | The serialized writer: implements one closed scope, keeps build/tests green, opens a PR, never merges. |
researcher | Fan-out, read-only research with cited, verified findings; prefers current docs over memory. |
reviewer | Adversarial pre-merge gate over a whole PR diff; 8-check rubric; returns MERGE / ADJUST / REJECT. |
verifier | General single-claim adversarial node: given one finding, tries to kill it and returns real/not-real. Fan-out safe — run several in parallel as a gate on a graph edge. |
measurer | Read-only data verdicts to unblock measure-gated decisions. |
eslint/ruff are present).[!NOTE] The Stop hook is a reminder, not a gate — it surfaces "you have uncommitted changes; run this project's checks and show the output" and then gets out of the way. The real verification discipline lives in the
/shipandexecutorprompts; the hook just keeps it front-of-mind without ever blocking the turn.
jq on your machine, for the format hook.researcher / /measure can pull live library docs:
claude mcp add context7 -- npx -y @upstash/context7-mcp.The skills reference docs/pitches/ and docs/DECISIONS.md by convention. Adapt
the doc-bundle tiers in
EXECUTION_PLAYBOOK.md
and the invariants in the review checklist to your project, and change the paths
if your repo differs. See the plugin reference
for the full component breakdown.
Releasing an update: bump version in both
plugin.json and
marketplace.json, commit, tag, and push.
Users pick it up with /plugin marketplace update giusto-agentic.
Validate before pushing:
claude plugin validate .
claude plugin validate ./plugins/agentic-engineering
agentic-engineering-marketplace/
├── .claude-plugin/
│ └── marketplace.json # lists the plugin(s), schema-validated
├── assets/
│ └── banner.svg
├── docs/
│ ├── DECISIONS.md # append-only ADR log
│ └── pitches/ # shaped specs, one per feature
├── plugins/
│ ├── agentic-engineering/ # the spec-driven / graph-engineering plugin
│ │ ├── .claude-plugin/plugin.json
│ │ └── skills/ agents/ hooks/ README.md
│ └── github-keeper/ # README + open-source maintenance plugin
│ ├── .claude-plugin/plugin.json
│ └── skills/ README.md
├── LICENSE
└── README.md
github-keeper — make a public repo
well-made and honest. /readme's fidelity gate derives the hero archetype,
palette, voice, badges, and sections from the target project's own identity and
proposes-and-confirms before generating, instead of imposing a house style;
/opensource adds the community-health files, an honest CI gate, and the right
repo settings. Install it with /plugin install github-keeper@giusto-agentic.
Issues and PRs are welcome — bug reports, a sharper skill prompt, or a new
role/skill that fits the shape → decide → execute → measure → eval spine.
Open an issue
to discuss anything non-trivial first. Run claude plugin validate . before
opening a PR.
MIT © Giusto Piedimonte
1000+ skills curated from Anthropic, Vercel, Stripe, and other engineering teams
Design enforcement with memory — keeps your UI consistent across a project
Detects 37 AI writing patterns and rewrites text with human rhythm across 5 voice profiles
WCAG accessibility audit — automated scanning, manual review, remediation