Skip to content
Back to search

shipgate

MarketplaceWorks with Claude CodeGitHub

Gated multi-agent delivery pipeline for Claude Code: test-first, locked tests, cross-model review, single testing queue. Jira or GitHub Issues.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/iremir0--shipgate/badge.svg)](/listings/iremir0--shipgate)

HTML

<a href="/listings/iremir0--shipgate"><img src="/api/listings/iremir0--shipgate/badge.svg" alt="findsafeskills safety rating" /></a>

Install

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 21 lines
  1. {
  2. "name": "shipgate",
  3. "owner": { "name": "Emir Tüfekci", "url": "https://github.com/Iremir0" },
  4. "metadata": { "description": "Gated multi-agent delivery pipeline for Claude Code" },
  5. "plugins": [
  6. {
  7. "name": "shipgate",
  8. "source": "./plugins/shipgate",
  9. "description": "Ticket-to-release pipeline: test-first, locked tests, cross-model review, single testing queue. Jira or GitHub Issues.",
  10. "version": "0.1.0",
  11. "category": "development"
  12. },
  13. {
  14. "name": "shipgate-hooks",
  15. "source": "./plugins/shipgate-hooks",
  16. "description": "Optional Stop hook that runs your quick checks on changed files before Claude ends a turn.",
  17. "version": "0.1.0",
  18. "category": "development"
  19. }
  20. ]
  21. }
README.md · README · 139 lines
  1. <p align="center">
  2. <img src="assets/banner.svg" alt="shipgate: To Do → In Progress → Code Review → Testing → Ready for Release" width="100%">
  3. </p>
  4. <p align="center">
  5. <a href="LICENSE"><img alt="MIT" src="https://img.shields.io/badge/license-MIT-d97757"></a>
  6. <img alt="version" src="https://img.shields.io/badge/version-0.1.0-2a1d16">
  7. <img alt="Claude Code plugin" src="https://img.shields.io/badge/Claude%20Code-plugin-d97757">
  8. <img alt="trackers" src="https://img.shields.io/badge/trackers-GitHub%20Issues%20%7C%20Jira-2a1d16">
  9. <a href="https://github.com/Iremir0/shipgate/actions/workflows/ci.yml"><img alt="CI" src="https://github.com/Iremir0/shipgate/actions/workflows/ci.yml/badge.svg"></a>
  10. </p>
  11. <p align="center"><b>A gated, multi-agent delivery pipeline for <a href="https://docs.claude.com/en/docs/claude-code">Claude Code</a>.</b><br>
  12. You write tickets and release. Agents write tests, code and reviews. Gates decide what ships.</p>
  13. <p align="center"><a href="README.tr.md">Türkçe</a> · <a href="docs/how-it-works.md">How it works</a> · <a href="https://github.com/Iremir0/shipgate-demo">Demo repo</a> · <a href="docs/case-study.md">Case study</a></p>
  14. ---
  15. ## Why
  16. Letting one AI session "just build the feature" works until it doesn't: it edits the test to make it pass, reviews
  17. its own blind spots, and calls something done that was never run against the real services.
  18. This plugin is the process I use on a production e-commerce codebase instead. The main Claude Code session becomes a
  19. **manager that is not allowed to write code**. It moves each ticket across a kanban board and hands the work to
  20. specialised agents, and a ticket only moves forward when a gate is passed with evidence.
  21. ## The pipeline
  22. ```mermaid
  23. flowchart LR
  24. A[To Do] --> B["In Progress<br/><sub>test-author → dev</sub>"]
  25. B --> C["Code Review<br/><sub>other model + security</sub>"]
  26. C -- reject --> B
  27. C --> D["Testing<br/><sub>single queue, merged with main</sub>"]
  28. D -- fail --> B
  29. D --> E[Ready for Release]
  30. E -- you --> F[Done]
  31. ```
  32. | Gate | Rule | Why |
  33. |---|---|---|
  34. | 🔒 **Locked tests** | Failing tests are written first, in their own commit. The dev agent may not touch them; the reviewer diffs them and auto-rejects any change. | The agent can't "fix" the test instead of the code. |
  35. | 🔀 **Cross-model review** | Sonnet's code is reviewed by Opus and vice versa. A forced same-model review is stamped ⚠️ on the PR. | A model approves its own mistakes. |
  36. | 🛡️ **Risk routing** | Money, payments, auth, migrations → stronger dev, mandatory test-first, security review (Critical/High = reject). | Spend the expensive checks where mistakes are expensive. |
  37. | 🧪 **Single testing queue** | One ticket at a time, merged with the latest `main`, every relevant suite incl. e2e against real services. | Shared DBs and ports; two green branches can be red together. |
  38. | ⛔ **BLOCKED ≠ PASS** | A suite that couldn't run never counts as passed. | No "tests skipped, looks good". |
  39. | 🔁 **Loop limit** | 3 rejects + fails → `blocked`, human looks. | Stops agents from grinding on a bad ticket. |
  40. | 🙋 **Humans release** | The pipeline stops at *Ready for Release* with a release note and a pipeline log. | You stay accountable for what ships. |
  41. More detail and the reasoning behind each rule: **[docs/how-it-works.md](docs/how-it-works.md)**.
  42. ## Try it in 5 minutes
  43. The **[demo repo](https://github.com/Iremir0/shipgate-demo)** is a tiny cart calculator with three seeded
  44. issues: a copy change, a risky money feature and a planted bug.
  45. ```bash
  46. gh repo create my-pipeline-demo --template Iremir0/shipgate-demo --private --clone
  47. cd my-pipeline-demo && npm ci && npm run seed
  48. claude # trust the folder, accept the plugin install
  49. > /pipeline
  50. ```
  51. Watch the issues move across `status:*` labels, with plans, review decisions and release notes as comments and one
  52. merged PR per issue. The first real run (3 issues, 3 merged PRs, and the 8 plugin problems it surfaced) is
  53. written up in **[docs/example-run.md](docs/example-run.md)**.
  54. ## Use it in your repo
  55. ```text
  56. /plugin marketplace add Iremir0/shipgate
  57. /plugin install shipgate@shipgate
  58. /plugin install shipgate-hooks@shipgate # optional Stop hook
  59. /pipeline-init # detects your stack, writes .claude/pipeline.json, sets up the tracker
  60. /new-ticket add refund requests
  61. /pipeline # work the whole board
  62. /pipeline #12 # or one ticket
  63. ```
  64. | Command / agent | What it does |
  65. |---|---|
  66. | `/pipeline [key]` | The manager. Board mode or a single ticket. |
  67. | `/new-ticket <idea>` | Drafts a ticket with testable Given/When/Then criteria, test plan, out-of-scope and security notes; creates it after you approve. |
  68. | `/pipeline-init` | One-time setup per repo. |
  69. | `test-author`, `dev-standard`, `dev-critical`, `code-reviewer`, `security-reviewer`, `test-runner` | The agents ([agents/](agents)). |
  70. | `shipgate-hooks` (optional plugin) | A Stop hook that runs your quick checks on changed files before Claude may end a turn. |
  71. Configuration reference: **[docs/configuration.md](docs/configuration.md)** · Trackers: **[docs/trackers.md](docs/trackers.md)**
  72. ## In production
  73. I run this pipeline on a production e-commerce monorepo (Medusa 2 + Next.js 16 + Expo, Jira kanban) where prices follow
  74. the live gold price, so most work touches money, stock or payments. First three weeks:
  75. | 30 | 76 % | 81.5 % | 3 |
  76. |:---:|:---:|:---:|:---:|
  77. | tickets delivered | approved on first cross-model review | passed first test run against `main` + real services | test runs reported **BLOCKED** instead of a fake pass |
  78. One ticket in four was sent back by the reviewer and one in five failed integration before any human saw it.
  79. The full story, including what went wrong and what changed because of it: **[docs/case-study.md](docs/case-study.md)**.
  80. ## What shipgate runs and fetches
  81. shipgate has no server, no telemetry and no dependencies. Everything happens on your machine, through tools you
  82. already authorised:
  83. - **Stop hook**, only if you install the optional `shipgate-hooks` plugin
  84. (`plugins/shipgate-hooks/hooks/verify-on-stop.mjs`, plain Node): runs `git status` and the commands *you* list under
  85. `verifyOnStop` in `.claude/pipeline.json`; writes a fingerprint cache to `.claude/.cache/`.
  86. - **`/pipeline` and the agents** run `git` (worktrees, branches, push of ticket branches), your project's commands from
  87. `.claude/pipeline.json`, and your tracker:
  88. - GitHub Issues: the `gh` CLI with your own login (issues, labels, PRs).
  89. - Jira: the Atlassian MCP server you connect yourself.
  90. - **`/pipeline-init`** reads your project files to propose a config and creates GitHub labels with `gh`.
  91. - Nothing is downloaded at runtime. The JSON schema URL in `pipeline.json` is only used by your editor for autocomplete.
  92. ## FAQ
  93. **Isn't this expensive?** Cheap work stays cheap: copy and small changes go to Sonnet and may skip test-first. Opus is
  94. spent on risky code and on reviewing Sonnet. The pipeline log on every ticket tells you where the tokens went.
  95. **Can it merge to my main branch by itself?** By default yes, after review *and* testing pass; it never pushes to
  96. `main` directly. Set `"autoMerge": false` to stop at an approved, tested PR.
  97. **What does it ask me?** Only real decisions: a new module or data model, where data lives, a new dependency, a
  98. customer-visible rule with several reasonable answers. Everything else it decides and records on the ticket.
  99. **Does it work without Docker / integration tests?** Yes. `commands.suites` is optional; the demo has none.
  100. ## Roadmap
  101. - Linear and GitHub Projects (v2) status fields as trackers
  102. - Cost per ticket in the pipeline log
  103. - A `/pipeline-report` command that charts reject/fail rates per model over time
  104. ## License
  105. MIT © Emir Tüfekci

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.