delivery-method

v0.2.2

Méthode de livraison en trois phases pour Claude Code : spécification, implémentation story par story en sessions jetables, recette. Moteur deliveryctl, rôles, commandes, gabarits.

Claude Code9 Skills

By peugeneLicense: MIT0 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes: Claude Code
Parsed components: 9 skill or MCP entries
Source updated: Oct 2, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install delivery-method for Claude Code

Installs for the current user

claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install delivery-method@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/peugene/delivery-method

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

delivery-method/

├── .claude-plugin/plugin.json
├── skills/acceptance-by-role/SKILL.md
├── skills/adversarial-review/SKILL.md
├── skills/anchoring/SKILL.md
├── skills/brainstorm/SKILL.md
├── skills/framing-discussion/SKILL.md
├── skills/qualification-doctrine/SKILL.md
├── skills/spec-writing/SKILL.md
├── skills/testing-doctrine/SKILL.md
└── skills/work-orders/SKILL.md

Included Skills9

acceptance-by-roleskills/acceptance-by-role/SKILL.md

How to write the shared Playwright acceptance suite from the spec - tags per criterion, locators by role and label key, data only through the UI and the harness, a new client state per test, red against the empty app. Used by the product-analyst after the GO close and by spec reviewers.

adversarial-reviewskills/adversarial-review/SKILL.md

Mechanics of an adversarial review in any phase - independent angles with evidence, a refuter per finding, verdict before reading the author's, three attacks on a flawless result, read versus probe, no number without measurement. Used by spec-reviewer, refuter, story-reviewer and the leads that synthesise a review.

anchoringskills/anchoring/SKILL.md

How to establish a fact before passing it on or acting on it - code over documentation, a guard read from its real input, searches that can fail, state checked after a change, level 2 probes, and the read / measured / inferred label. Used by the technical-lead, the story-implementer and the story-reviewer.

brainstormskills/brainstorm/SKILL.md

Explore an idea with the decision owner without committing to anything - no memory, no note, no file - then close on the owner's word - forget, archive or frame. Invoked by the owner only, in a human session, on any topic and at any phase.

framing-discussionskills/framing-discussion/SKILL.md

How a lead frames with the decision owner under the discuss regime - read the existing, give an opinion, ask numbered questions with recommendations, record decisions verbatim, decide nothing in silence. Used by the product-analyst and by the technical-lead in framing.

qualification-doctrineskills/qualification-doctrine/SKILL.md

Doctrine of the qualification phase (observe and record) - surface drawn from the code, negatives by default, material versus product failures, replay rather than date, installation and removal as tests, evidence as a verdict plus one line. Load it to plan, run or synthesize a qualification.

spec-writingskills/spec-writing/SKILL.md

How to write technology-neutral spec stories - behaviour in the present tense, numbered business rules, flows, Given/When/Then criteria, UI contract, outcomes - and when a story is ready. Used by the product-analyst and by spec reviewers.

testing-doctrineskills/testing-doctrine/SKILL.md

What to test in a story, at which layer, which checks run when (targeted tests, check, the story's UI tests, the nightly full suite), how a check guards its own preconditions, and how to investigate a red build. Used by the story-implementer and the story-reviewer.

work-ordersskills/work-orders/SKILL.md

How the technical-lead writes a work order (docs/stories/<id>/order.md) that a mid-range agent carries out without a question, and how it reads the report that comes back. Used before every `deliveryctl story open` and after every story stop.

Plugin manifests1

.claude-plugin/plugin.json

{
  "name": "delivery-method",
  "version": "0.2.2",
  "description": "Méthode de livraison en trois phases pour Claude Code : spécification, implémentation story par story en sessions jetables, recette. Moteur deliveryctl, rôles, commandes, gabarits.",
  "author": {
    "name": "peugene",
    "url": "https://github.com/peugene"
  },
  "homepage": "https://github.com/peugene/delivery-method",
  "repository": "https://github.com/peugene/delivery-method",
  "license": "MIT",
  "keywords": [
    "delivery",
    "method",
    "stories",
    "specification",
    "qualification",
    "worktree",
    "review"
  ]
}

Browse the “delivery” tag →

agent-harness-skills

by Agent Harness Skills contributors

Reusable skills for building agent-ready repository harnesses.

Codex5 Skills

1.1kUpdated last week

review-suite

by Lev Nikolaevich

Independent plan and delivery reviews with evidence-based verdicts.

CodexAgent Plugins2 Skills

557Updated last month

source-control

by Melodic Software

Git and GitHub delivery workflow: /commit (Conventional Commits + Co-authored-by trailer via safe heredoc mechanics), /pull-request (prep, create, CI monitoring, review-comment triage, merge, CI-log fetch), /babysit-prs (self-pacing fleet loop, safe by default; opt-in worker/autopilot tiers add gate-checked merge and thread resolution behind a deterministic Python engine), /babysit-loop (the loop-lane merge lane: a standing or drain loop that invokes babysit-prs per cycle, configured through repo-scoped babysit_loop_* keys on the layered source-control.md seam, with merge authority human-only until the target repo's tracked config adopts the lane, a gate-proven C2-mechanical baseline once adopted, and standing merge-rung raises binding from the team-tracked layer only, with one named exception, where an invocation line explicitly typing both the autopilot tier keyword and the dedicated raise argument --merge c3-this-run widens that single invocation's merge authority up to C3 behind a fresh independent frontier-tier resolver, while C4-structural and C5-untrusted-provenance stay unconditionally human-merge), /worktree (create, status, cleanup, audit for parallel-session isolation), /setup (check the effective commit-subject / PR-title convention merged across its config layers and the babysit-prs config, or apply, which interviews the repo and writes the convention config to a chosen layer), and /resolve-conflicts (intent-first merge/rebase conflict resolution with a semantic-conflict sweep, never --abort). The commit-subject / PR-title convention is configurable via a source-control.md config written by a re-runnable setup skill, layered across a ~/.claude user-global file, the tracked team file, and a gitignored .claude/source-control.local.md personal overlay merged per key; Conventional Commits is the default when no convention is declared.

Claude Code7 Skills

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[delivery-method on Agent Plugins Marketplace](https://pluginsmp.com/plugins/delivery-method)