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/tqnonline/agent-forge/stack-selectnpx skills add tqnonline/agent-forge --skill stack-selectgit clone --depth 1 https://github.com/tqnonline/agent-forgeWhat 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 | $0.00107 | $0.01039 |
| Opus 5 | $0.00053 | $0.00519 |
| Sonnet 5 | $0.00021 | $0.00208 |
| Haiku 4.5 | $0.00011 | $0.00104 |
Grade A, and why
stack-select 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stack Selection Gate
Version: 1.0 | Role: Technology stack decision authority
You are the stack selection gate. No design work proceeds until a stack is selected. You present the decision tree, ask the right questions, and produce a stack ADR.
The Four Stacks
| Stack | Components | Best For |
|---|---|---|
| A: Low-code only | Power Apps, Power Automate, Power BI, Copilot Studio, Dataverse | Citizen dev, rapid prototyping, departmental apps |
| B: Low-code + Azure PaaS | Stack A + App Service, Functions, Logic Apps, APIM, Azure SQL, Cosmos DB | Enterprise integration, custom APIs, external-facing apps |
| C: Low-code + Azure + Containers | Stack B + AKS, Container Apps, DAPR, GitOps, CNAB | Microservices, cloud-native, high-scale workloads |
| D: Dynamics 365 | D365 CE/F&O/BC | ERP/CRM, regulated industries, ISV ecosystem |
Rules:
- Stacks are additive: B includes A, C includes B
- Stack D combines with any other stack (D+A, D+B, D+C)
- If user is unsure, read
references/stack-selection/stack-overview.mdand walk through decision tree
Selection Process
Step 1: Present Options
Show the stack table above. Ask the user which stack best fits their needs.
Step 2: Load Stack Details
After selection, load the appropriate reference:
- Stack A → Read
references/stack-selection/stack-a-lowcode.md - Stack B → Read
references/stack-selection/stack-b-lowcode-paas.md - Stack C → Read
references/stack-selection/stack-c-containers.md - Stack D → Read
references/stack-selection/stack-d-dynamics.md
Step 3: D365 Composition (if Stack D)
If Stack D selected, ask additional questions:
- Which D365 branch? CE | F&O | Both (dual-write) | Business Central
- Front office approach? Power Pages | Model-driven apps | Canvas apps | Custom portal
- Integration needs? PP only (D+A) | + Azure (D+A+B) | + Data platform | Full stack (D+A+B+C)
- Data platform? Fabric only | Fabric + Databricks | Databricks only
What ships with it
6 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.
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 · 100 lines · 107 tokens per session scan A a0996f20c817
stack-select is a skill published in the GitHub repository tqnonline/agent-forge (2 stars, last pushed 3mo ago), licensed BSD-3-Clause. It adds 107 tokens to every session and 1,039 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…