Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/anshss/shiploopWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/anshss/shiploop/shiploop)<a href="https://agentmods.dev/plugins/anshss/shiploop/shiploop"><img src="https://agentmods.dev/badge/plugins/anshss/shiploop/shiploop/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/anshss/shiploop/shiploop"><img src="https://agentmods.dev/badge/plugins/anshss/shiploop/shiploop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
shiploop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "shiploop",
"displayName": "shiploop",
"version": "1.20.2",
"description": "Self-improving multi-agent harness that dispatches the tickets you name across every repo in your product: guarded auto-merge on green CI, and every resolved ticket writes a lesson into your git-tracked CLAUDE.md. Every ticket dispatches at a fixed floor tier and escalates once, on measured failure, rather than a tier predicted per ticket up front; deterministic fixes skip the model entirely; and the lessons file evicts old entries rather than growing without bound.",
"author": {
"name": "anshss",
"url": "https://github.com/anshss"
},
"homepage": "https://github.com/anshss/shiploop",
"repository": "https://github.com/anshss/shiploop",
"license": "Apache-2.0",
"keywords": [
"self-improving",
"multi-agent",
"orchestration",
"model-routing",
"backlog",
"monorepo",
"multi-repo",
"worktrees",
"autonomous-agent",
"ticket-queue",
"governor",
"worker-subagent"
]
}
What it installs
The manifest is a name and a version. 2 skills, 7 commands, 3 agents travel with it, and installing the plugin installs all of them — 235 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill deep-research-tiered A 0 tokens
- Skill shiploop A 0 tokens
- Command setup A 24 tokens
- Command update A 0 tokens
- Command compress A 28 tokens
- Command flows A 0 tokens
- Command push A 0 tokens
- Command validated A 25 tokens
- Command statusline A 27 tokens
- Agent worker A 25 tokens
- Agent investigator A 56 tokens
- Agent lookup A 50 tokens
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago Changed 54b0e4673c78
- 13d ago Changed 584de88e7fd8
- 18d ago Changed 9e1679f23364
- 27d ago Changed ce50808cabdc
- 1mo ago Changed 1f96d7e58c11
- 1mo ago Changed e8ca6852a9e7
- 1mo ago Changed c81fdee7738c
- 1mo ago Changed 98608d3fcace
- 1mo ago Changed d33a9e7ddd9a
- 1mo ago First seen · 29 lines scan A d6ca7dfb580b
shiploop is a plugin published in the GitHub repository anshss/shiploop (9 stars, last pushed 12d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other plugins, from other repositories
before-you-build
Pre-build product risk review for founders, product teams, and AI-assisted builders before implementation starts.
obw
Obsidian Workspace — project-scoped vault productivity (capture / notes / PM). Skills own folder layout and templates; /obw:pm splits a spec into blocking tickets; /issue is a Claude Mod pane that lists a view of the project's dashboard, draws Mermaid as text diagrams, and can open a card in the browser through viz.…
feature-to-pr-factory
Turn one feature into dependency-ordered GitHub or GitLab issues, then build each ticket into its own reviewed, tested PR or MR with agents.
mission-control
SDLC management for Operations, Asgard, and CAMPPS: prepared issue drafts, live schema sync, board schemas, labels, project fields, metrics, and card validation.
feishu-calendar
Manage Feishu (Lark) calendar events — create, read, update, delete events and manage attendees via the Feishu Open Platform Calendar API v4.
gse
GSE-One — AI engineering companion for structured SDLC management. 24 commands, adaptive risk analysis, unified backlog, knowledge transfer, worktree isolation.