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.
npx agentmods add skills/10xdev-startup/template-nodejs-express-next-supabase/gstacknpx skills add 10xdev-startup/template-nodejs-express-next-supabase --skill gstackgit clone --depth 1 https://github.com/10xdev-startup/template-nodejs-express-next-supabaseWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00244 | $0.06012 |
| Opus 5 | $0.00122 | $0.03006 |
| Sonnet 5 | $0.00049 | $0.01202 |
| Haiku 4.5 | $0.00024 | $0.00601 |
Grade C, and why
gstack scanned grade C with 2 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 yesterday.
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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. If `bun` is not installed: `curl -fsSL https://bun.sh/install | bash` The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files beside SKILL.md 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.
- .env.example 171 B
- .github/actionlint.yaml 82 B
- .github/docker/Dockerfile.ci 2.7 KB
- .github/workflows/actionlint.yml 176 B
- .github/workflows/ci-image.yml 1.0 KB
- .github/workflows/evals.yml 8.3 KB
- .github/workflows/skill-docs.yml 835 B
- .gitignore 192 B
- actionlint.yaml 56 B
- AGENTS.md 2.5 KB
- agents/openai.yaml 158 B
- ARCHITECTURE.md 21 KB
- autoplan/SKILL.md 43 KB
- autoplan/SKILL.md.tmpl 29 KB
- benchmark/SKILL.md 18 KB
- benchmark/SKILL.md.tmpl 9.0 KB
- bin/dev-setup 2.4 KB
- bin/dev-teardown 1.6 KB
- bin/gstack-analytics 6.3 KB
- bin/gstack-community-dashboard 4.7 KB
- bin/gstack-config 1.1 KB
- bin/gstack-diff-scope 2.4 KB
- bin/gstack-global-discover.ts 18 KB runs code
- bin/gstack-repo-mode 3.5 KB
- bin/gstack-review-log 411 B
- bin/gstack-review-read 528 B
- bin/gstack-slug 800 B
- bin/gstack-telemetry-log 6.7 KB
- bin/gstack-telemetry-sync 4.4 KB
- bin/gstack-update-check 7.8 KB
- browse/bin/find-browse 814 B
- browse/bin/remote-slug 572 B
- browse/scripts/build-node-server.sh 1.9 KB runs code
- browse/SKILL.md 19 KB
- browse/SKILL.md.tmpl 4.1 KB
- browse/src/browser-manager.ts 22 KB runs code
- browse/src/buffers.ts 4.2 KB runs code
- browse/src/bun-polyfill.cjs 2.9 KB runs code
- browse/src/cli.ts 17 KB runs code
- browse/src/commands.ts 8.0 KB runs code
- browse/src/config.ts 4.6 KB runs code
- browse/src/cookie-import-browser.ts 23 KB runs code
- browse/src/cookie-picker-routes.ts 8.1 KB runs code
- browse/src/cookie-picker-ui.ts 21 KB runs code
- browse/src/find-browse.ts 1.7 KB runs code
- browse/src/meta-commands.ts 9.7 KB runs code
- browse/src/platform.ts 634 B runs code
- browse/src/read-commands.ts 12 KB runs code
- browse/src/server.ts 14 KB runs code
- browse/src/snapshot.ts 15 KB runs code
- browse/src/url-validation.ts 3.5 KB runs code
- browse/src/write-commands.ts 13 KB runs code
- browse/test/bun-polyfill.test.ts 2.9 KB runs code
- browse/test/commands.test.ts 67 KB runs code
- browse/test/config.test.ts 13 KB runs code
- browse/test/cookie-import-browser.test.ts 21 KB runs code
- browse/test/cookie-picker-routes.test.ts 7.4 KB runs code
- browse/test/find-browse.test.ts 2.0 KB runs code
- browse/test/fixtures/basic.html 914 B
- browse/test/fixtures/cursor-interactive.html 883 B
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.
- yesterday First seen · 583 lines · 244 tokens per session scan C fd715dfcdfe6
gstack is a skill published in the GitHub repository 10xdev-startup/template-nodejs-express-next-supabase (2 stars, last pushed 13d ago), with no licence file. It adds 244 tokens to every session and 6,012 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
mintlify-preview
Run the public Mintlify product docs site locally for live preview. Use when previewing or iterating on docs under docs/ (.mdx/.md pages, docs.json nav), or when the user says "start the docs", "run mintlify", "preview the docs site".