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/3awny/qshipWrote 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/3awny/qship/qship)<a href="https://agentmods.dev/plugins/3awny/qship/qship"><img src="https://agentmods.dev/badge/plugins/3awny/qship/qship/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/3awny/qship/qship"><img src="https://agentmods.dev/badge/plugins/3awny/qship/qship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
qship 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 1mo 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
{
"name": "qship",
"description": "Bootstrapper for the qship pipeline. Installs a single configurator skill that walks you through ~25 questions about your codebase, then renders the 21-skill qship pipeline (plan/implement/review/test/ship) into your ~/.claude/skills/ tree. Hook-enforced, resumable, parallel/epic-mode capable. Supports both Claude Code and Codex CLI.",
"version": "1.0.1",
"keywords": ["claude-code", "agent-skills", "codex-cli", "jira", "tdd", "code-review", "autonomous-agent", "developer-tools"],
"license": "MIT",
"author": {
"name": "Ahmed Awny",
"email": "[email protected]",
"url": "https://github.com/3awny"
},
"homepage": "https://github.com/3awny/qship",
"repository": {
"type": "git",
"url": "https://github.com/3awny/qship.git"
}
}
What it installs
The manifest is a name and a version. 22 skills, 1 agent, 1 hook travel with it, and installing the plugin installs all of them — 1,638 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill qe2etest A 36 tokens
- Skill qmanualt A 32 tokens
- Skill qmigrationdevcheck A 73 tokens
- Skill qbcheck A 73 tokens
- Skill qbug A 65 tokens
- Skill qcheck A 55 tokens
- Skill qlocalclonedb A 68 tokens
- Skill qshipcheck A 51 tokens
- Skill qspinuplocal A 43 tokens
- Skill qauthtrailingslash A 80 tokens
- Skill qplan A 57 tokens
- Skill qcheckf A 59 tokens
- Skill qcheckt A 62 tokens
- Skill qcomponent A 51 tokens
- Skill qdirectory A 58 tokens
- Skill qmemory A 64 tokens
- Skill qshipphasecheck A 62 tokens
- Skill qclean A 58 tokens
- Skill qreuse A 62 tokens
- Skill qship B 125 tokens
- Skill configure B 126 tokens
- Skill qshipmaster D 240 tokens
- Agent qship-worker A 38 tokens
- Hook SessionStart A not measured
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.
- 1mo ago First seen · 18 lines scan A 80bf01d96019
qship is a plugin published in the GitHub repository 3awny/qship (2 stars, last pushed 3mo ago), licensed MIT. 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
total-agent-memory
Persistent local memory for Claude Code — temporal knowledge graph, procedural memory, AST codebase ingest, cross-project analogy. Installs the MCP server, the memory-protocol skill and the capture hooks in one step.
voice-calibration-marketplace
Plugin marketplace listing 1 plugin: voice-calibration-plugin.
voice-calibration-plugin
Learns your personal writing and speaking style through interactive prompts, then generates a reusable voice profile so AI can write like you.
cladding
Reference implementation of the Ironclad standard — multi-agent dev harness for Claude Code.
superb
Personal skill collection for Claude Code and Codex, invoked as superb: . setup installs what the others need; craft turns a vague product idea into a decision-rich brief; pipeline v2 drives a settled idea through approved file-backed plans and durable execution state to a finished branch; pipeline-auto does the.
cladding
Reference implementation of the Ironclad standard — multi-agent dev harness for Gemini CLI. Exposes spec validation, drift detection, 15 Iron Law stages, and 5 agent personas as custom commands + an auto-launched MCP server.