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 skills add mamahoos/dot-files --skill architecture-decision-makinggit clone --depth 1 https://github.com/mamahoos/dot-filesWrote 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/skills/mamahoos/dot-files/architecture-decision-making)<a href="https://agentmods.dev/skills/mamahoos/dot-files/architecture-decision-making"><img src="https://agentmods.dev/badge/skills/mamahoos/dot-files/architecture-decision-making.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00075 | $0.01190 |
| Opus 5 | $0.00037 | $0.00595 |
| Sonnet 5 | $0.00015 | $0.00238 |
| Haiku 4.5 | $0.00007 | $0.00119 |
Grade A, and why
architecture-decision-making 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Decision Making
This skill makes the decision. documentation-and-adrs records it. Do not fill an ADR template until this pipeline has a Decision.
Hand first
Inventory the cards we actually hold before naming options. See cards.md.
Do not play a card that is not in the hand unless you name it as a new card (learn + operate + ongoing cost).
Pipeline
Problem ↓ Constraints ↓ Requirements ↓ Options ↓ Trade-offs ↓ Failure modes ↓ Operational cost ↓ Decision
Don't optimize architecture for imaginary scale.
When to use
- Choosing storage, runtime, deploy shape, module boundary, or a major dependency
- A change that would be expensive to reverse (one-way door)
- The user asks for architecture, system design, or "what should we use"
- Before
documentation-and-adrson a significant decision
When not to:
- a two-line bugfix or a rename
- recording a decision already made (
documentation-and-adrs) - performance work without measured load (
performance-optimization)
Door type
| Door | Meaning | Path |
|---|---|---|
| Two-way | Cheap to reverse this month (you operate it) | Short: Hand → Problem → Options → Decision |
| One-way | Painful to undo (data, public contract, prod topology) | Full pipeline |
If unsure, treat as one-way. If the write-up would take longer than a reversible spike, take the short path and spike.
Workflow
Copy and track:
- [ ] Hand inventoried (cards.md); new cards named
- [ ] Evidence of scale stated (or "unknown → assume single-operator / small")
- [ ] Door type chosen
- [ ] Pipeline completed (short or full)
- [ ] Option 0 (status quo / do nothing) considered
- [ ] Decision packet written from templates/decision.md
- [ ] `python3 home/.cursor/skills/architecture-decision-making/scripts/check_decision.py PATH` passes
- [ ] User accepted the Decision (or overrode with eyes open)
- [ ] If significant: hand off to documentation-and-adrs
Scale evidence (mandatory). State what you know: users, RPS, data size, deploy frequency, boxes, operators. If you have no numbers, write unknown and design for the hand, not for a blog. Imaginary "when we have millions of users" is not a requirement.
What ships with it
7 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.
- 3d ago First seen · 128 lines · 75 tokens per session scan A 8f3889adb107
architecture-decision-making is a skill published in the GitHub repository mamahoos/dot-files (4 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 1,190 once invoked, about $0.0004 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 2026-09-04.
Other skills, from other repositories
git-commit
This skill should be used BEFORE running any git commit command. Triggers when about to run git commit. Ensures commit messages follow Conventional Commits specification and prompts for the Jira ticket number.
golang-style
Go conventions specific to this author. Use before writing or editing any Go (.go) file.
nvim-plugin
Conventions and tooling for authoring a Neovim plugin in Lua. Use when creating, modifying, or reviewing a plugin — plugin structure, ftplugin, health checks, setup(), vimdoc, LuaCATS, lazy loading — or when working in a directory that looks like one (plugin/, lua/, ftplugin/).
mbo-plan
Plan a new objective end-to-end in this repo's docs/mbo Management-By-Objective system — turn a GitHub issue or a gss draft-PR worktree into consistent design/spec/plan artifacts and track it in docs/mbo/index.md. Use this whenever the user wants to START planning or designing a new feature, skill, CLI, or service…
wispr-flow-debug
Debug and test the Wispr Flow AutoHotkey dictation triggers (Copilot key + extra keys) from WSL by deploying macos.ahk to the Windows Desktop, reloading AutoHotkey, and reading the debug log. Use when an activation/trigger key isn't starting/stopping dictation, when the overlay clicks land wrong, or when verifying a…
herdr
Use when the user mentions herdr or is working inside a herdr pane and wants to save/restore a pane layout, change herdr's theme, prefix or other preferences on this host only, start or check on an agent in another herdr pane, or asks why the herdr sidebar colors are unreadable. Requires HERDRENV=1.