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 oborchers/fractional-cto --skill architecture-decision-recordsgit clone --depth 1 https://github.com/oborchers/fractional-ctoWrote 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/oborchers/fractional-cto/architecture-decision-records)<a href="https://agentmods.dev/skills/oborchers/fractional-cto/architecture-decision-records"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/architecture-decision-records/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/skills/oborchers/fractional-cto/architecture-decision-records"><img src="https://agentmods.dev/badge/skills/oborchers/fractional-cto/architecture-decision-records.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 9 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 257 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00064 | $0.02805 |
| Opus 5 | $0.00032 | $0.01403 |
| Sonnet 5 | $0.00013 | $0.00561 |
| Haiku 4.5 | $0.00006 | $0.00281 |
Grade A, and why
architecture-decision-records 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 12d 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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Down Every Decision or Pay to Re-Make It
Every infrastructure team makes dozens of significant decisions in the first months of a project: which cloud provider, which account structure, which naming convention, which container orchestrator, which CI/CD pipeline design. When those decisions live only in Slack threads and the memories of people who were in the room, they get relitigated every time someone new joins, every time someone forgets, and every time a stakeholder asks "why did we do it this way?" An Architecture Decision Record (ADR) takes 15 minutes to write and saves weeks of repeated debates. The format is deliberately simple: context, decision, consequences. No templates longer than a page. No approval workflows. Just a numbered, immutable document stored alongside the code it governs.
This skill follows the lightweight ADR format introduced by Michael Nygard in "Documenting Architecture Decisions" (2011) and later adopted by Thoughtworks in the "Adopt" category of their Technology Radar.
The ADR Format
An ADR captures exactly four things: what number it is, what context motivated the decision, what was decided, and what the consequences are. Nothing more.
# ADR-0001: [Title of the Decision]
**Status:** Proposed | Accepted | Superseded by ADR-XXXX | Deprecated
**Date:** 2026-02-15
**Deciders:** Platform Team
## Context
[What situation, constraint, or question prompted this decision?
What alternatives were considered? What trade-offs exist?]
## Decision
[What was decided? Be specific and unambiguous.
State the choice, not the rationale -- that belongs in Context.]
## Consequences
[What are the positive and negative outcomes of this decision?
What follow-up actions are required?
What becomes easier? What becomes harder?]
That is the entire format. Three sections. One page. Fifteen minutes. The value compounds over every month the project exists.
Numbering and Immutability
ADRs are numbered sequentially: ADR-0001, ADR-0002, ADR-0003. Numbers are never reused, never reordered, and never deleted. An ADR is a historical record of a decision made at a point in time.
What ships with it
2 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.
- 12d ago First seen · 260 lines · 64 tokens per session scan A 9d729727b959
architecture-decision-records is a skill published in the GitHub repository oborchers/fractional-cto (30 stars, last pushed 1mo ago), licensed MIT. It adds 64 tokens to every session and 2,805 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…