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/lolay/nowlineWrote 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/lolay/nowline/gemini-extension)<a href="https://agentmods.dev/plugins/lolay/nowline/gemini-extension"><img src="https://agentmods.dev/badge/plugins/lolay/nowline/gemini-extension/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/lolay/nowline/gemini-extension"><img src="https://agentmods.dev/badge/plugins/lolay/nowline/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
nowline 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 2d 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": "nowline",
"version": "0.11.0",
"description": "Create and edit your roadmaps in a plain-text format.",
"mcpServers": {
"nowline": {
"command": "npx",
"args": ["-y", "@nowline/mcp@latest"]
}
}
}
What ships with it
55 files beside gemini-extension.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.
- examples/capacity.nowline 572 B
- examples/continuation.nowline 354 B
- examples/dependencies.nowline 744 B
- examples/inline-date-pins.nowline 2.0 KB
- examples/isolate-include.nowline 476 B
- examples/long.nowline 10 KB
- examples/minimal.fr.nowline 324 B
- examples/minimal.nowline 542 B
- examples/nested.nowline 1.8 KB
- examples/nested/android.nowline 1.2 KB
- examples/nested/data.nowline 1.3 KB
- examples/nested/ios.nowline 1.1 KB
- examples/nested/platform.nowline 1.4 KB
- examples/nested/web.nowline 1.3 KB
- examples/partner.nowline 271 B
- examples/platform-2026.nowline 2.0 KB
- examples/product.nowline 2.0 KB
- examples/showcase.nowline 771 B
- examples/sizing.nowline 609 B
- examples/teams.nowline 1.1 KB
- examples/waves-program.nowline 545 B
- examples/waves-program/api.nowline 411 B
- examples/waves-program/web.nowline 411 B
- examples/waves.nowline 1.4 KB
- examples/working-calendar.nowline 1.7 KB
- scripts/apply-branch-policies.sh 14 KB runs code
- scripts/build-deb.sh 4.2 KB runs code
- scripts/changelog.py 16 KB runs code
- scripts/compare-samples.html 8.5 KB
- scripts/gallery/assets/gallery.css 12 KB
- scripts/gallery/assets/gallery.js 29 KB runs code
- scripts/gallery/collect.mjs 9.2 KB runs code
- scripts/gallery/lib/diff.mjs 3.6 KB runs code
- scripts/gallery/lib/html.mjs 24 KB runs code
- scripts/gallery/lib/lines.mjs 7.9 KB runs code
- scripts/gallery/lib/model.mjs 5.8 KB runs code
- scripts/gallery/lib/source.mjs 1.3 KB runs code
- scripts/gallery/lib/validate.mjs 11 KB runs code
- scripts/gallery/publish.mjs 19 KB runs code
- scripts/gallery/serve.mjs 2.5 KB runs code
- scripts/gallery/test/lines.test.mjs 13 KB runs code
- scripts/gallery/test/model.test.mjs 5.3 KB runs code
- scripts/gallery/test/publish.test.mjs 47 KB runs code
- scripts/gallery/test/source.test.mjs 3.2 KB runs code
- scripts/homebrew-tap/Formula/nowline.rb 1.1 KB runs code
- scripts/homebrew-tap/README.md 1.5 KB
- scripts/lib/check-dist-fresh.mjs 3.9 KB runs code
- scripts/lib/render-manifest.mjs 8.5 KB runs code
- scripts/render-samples.mjs 2.8 KB runs code
- scripts/render-tests.mjs 2.8 KB runs code
- scripts/render.mjs 1.4 KB runs code
- scripts/smoke-binary.sh 5.9 KB runs code
- scripts/sync-mcp-metadata.mjs 3.1 KB runs code
- scripts/test/release-cut.test.mjs 5.3 KB runs code
- scripts/test/toolchain-floors.test.mjs 2.7 KB runs code
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.
- 2d ago Changed ea3ca529694c
- 3d ago Changed 0c9b316bf28a
- 5d ago Changed 768a4afc9774
- 1mo ago First seen · 12 lines scan A 5f33e78ab44a
nowline is a plugin published in the GitHub repository lolay/nowline (0 stars, last pushed yesterday), 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 2026-09-07.
Other plugins, from other repositories
arckit
The Enterprise Architecture Governance Harness - 68 commands across strategy, architecture, delivery, and assurance — including UK Government compliance.
software-engineering
Subagent orchestration, wave execution, persistent completion, autonomous delivery, and migration batching.
spec-driven-development
Requirements clarification, phase planning, workstreams, and wave-based execution for reviewable delivery.
spipe
SPipe guarded release planning, process guidance, and MCP tools.
turnale
Run recreational racket-sport tournaments from chat: fair draws, live standings, score entry, dropout handling. Bundles the Turnale MCP connector and a tournament-organiser skill.
gambit
Thirteen product management skills and four chained workflow agents for PM workflows.