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/nbiish/agentsstandard-dot-com/gstack-codernpx skills add nbiish/agentsstandard-dot-com --skill gstack-codergit clone --depth 1 https://github.com/nbiish/agentsstandard-dot-comWhat 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 | $0.00102 | $0.02315 |
| Opus 5 | $0.00051 | $0.01157 |
| Sonnet 5 | $0.00020 | $0.00463 |
| Haiku 4.5 | $0.00010 | $0.00231 |
Grade A, and why
gstack-coder 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GStack Coder — Multi-Tool Coding Orchestration
This skill combines gstack (Claude Code skill pack) with pi and mini to form a complete multi-tool coding workflow. Each tool has unique strengths and subscription quotas — this skill ensures all are utilized.
PRD Anchor: Always read llms.txt in the repository root first. It is the authoritative Product Requirements Document for this repo — it defines architecture, security policy (PQC mandates, secrets management), workflow rules (git worktrees, commit conventions), and the provider/MCP infrastructure. If llms.txt and any other doc conflict, llms.txt wins. Never skip reading it.
1. GStack Installation & Setup
gstack is a collection of Claude Code skills by garrytan. Install once:
git clone --single-branch --depth 1 https://github.com/garrytan/gstack.git ~/.claude/skills/gstack && cd ~/.claude/skills/gstack && ./setup
After installation, gstack provides these slash commands inside Claude Code:
| Command | Purpose |
|---|---|
/cso |
Security audit — full codebase security review |
/review |
Code review — detailed PR/code review |
/qa https://... |
QA test a URL — test a deployed endpoint |
/autoplan |
Auto-plan — generate implementation plan for a feature |
/ship |
Ship — build, test, and deploy pipeline |
/office-hours |
Office hours — architect/planning discussion before building |
2. Multi-Tool Coding Workflow
Tool Inventory
| Tool | CLI | Config Location | Best For |
|---|---|---|---|
| Claude Code (gstack) | claude |
~/.claude/ |
Security audits, code review, planning, shipping |
| pi | pi (wrapper) |
~/.pi/agent/ |
Fast non-interactive coding, extensions, themes, MCP servers |
| mini | mini (wrapper) |
~/.config/mini-swe-agent/.env |
Lightweight SWE agent, bash-based tasks |
Provider Hot-Swap (use all subscriptions)
The ainish-coder framework supports hot-swapping provider configs via CLI wrappers. Each tool can be pointed at different API providers to maximize quota usage:
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 · 242 lines · 102 tokens per session scan A a675a322e434
gstack-coder is a skill published in the GitHub repository nbiish/agentsstandard-dot-com (2 stars, last pushed 3mo ago), licensed MIT. It adds 102 tokens to every session and 2,315 once invoked, about $0.0005 per session on Opus 5. 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…