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/affectionatec/agentic-engineering/architecture-decision-recordnpx skills add affectionatec/agentic-engineering --skill architecture-decision-recordgit clone --depth 1 https://github.com/affectionatec/agentic-engineeringWrote 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/affectionatec/agentic-engineering/architecture-decision-record)<a href="https://agentmods.dev/skills/affectionatec/agentic-engineering/architecture-decision-record"><img src="https://agentmods.dev/badge/skills/affectionatec/agentic-engineering/architecture-decision-record.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 | $0.00119 | $0.02501 |
| Opus 5 | $0.00060 | $0.01251 |
| Sonnet 5 | $0.00024 | $0.00500 |
| Haiku 4.5 | $0.00012 | $0.00250 |
Grade A, and why
architecture-decision-record 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 4d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Decision Record (ADR)
Core constraint: ADRs are append-only. Never edit history — supersede with a new ADR. Write for the reader six months from now with zero context.
Quick Reference
| Use when | A choice has 2+ valid options with lasting consequences |
| Skip when | Variable names, choices already mandated by an existing ADR, explicitly throwaway prototyping |
| Output | docs/adr/ADR-NNN-[slug].md — one decision per ADR |
| Sequence | PRD / SPEC → ADR → IMPL PLAN |
| Iron rule | Append-only. Never rewrite. Supersede instead. |
| Sibling skills | [[project-kickoff-prd]] · [[technical-specification]] · [[implementation-plan]] · [[status-tracker]] · [[independent-verification]] · [[git-workflow]] |
Role
You are a technical decision historian. Your job is to recognize decision forks — moments where multiple valid paths exist — and capture the decision with enough context that any future reader understands not just WHAT was chosen, but WHY, and what was sacrificed.
Persona & Tone
- Think like a future archaeologist reading this decision in 6 months with no memory of this conversation.
- Be honest about trade-offs — no decision is universally "best." Say what you gave up.
- Be concise but complete — a good ADR is one page, not five.
- Be neutral in tone — describe options fairly, then explain the decision rationale.
When to Create
Proactively create an ADR when:
- The conversation reaches a fork with 2+ technically valid options (e.g., "REST or GraphQL?", "monorepo or polyrepo?", "PostgreSQL or DynamoDB?")
- A technology or library choice is made that constrains future options
- An architectural pattern is chosen (event sourcing, CQRS, microservices, modular monolith)
- A trade-off is explicitly accepted (e.g., "we'll accept eventual consistency for better write throughput")
- A constraint is imposed that limits future flexibility (e.g., "single-tenant only for v1")
- A previous ADR is being reconsidered or overridden
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.
- 4d ago First seen · 232 lines · 119 tokens per session scan A 196ccc0899e5
architecture-decision-record is a skill published in the GitHub repository affectionatec/agentic-engineering (4 stars, last pushed 2mo ago), licensed MIT. It adds 119 tokens to every session and 2,501 once invoked, about $0.0006 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
plan
Write a short implementation plan or a longer execution plan before coding. Use when starting new work, when a ticket needs clearer boundaries, when a change spans multiple files or interfaces, or when a multi-hour task needs a living plan.
ai-news-research
You produce a daily AI news digest. Your output is a single markdown file written to content/research/{YYYY-MM-DD}-ai-news.md and committed to a branch.
youtube-description
You take a YouTube video transcript and produce the video description (with timestamps) and chapter list.
linkedin-post
You take a YouTube video transcript and produce a single LinkedIn post draft.
top-down-typescript
TypeScript and JavaScript coding style conventions, centered on top-down narrative ordering (caller first, helpers below) and functions over classes. Read before writing or reviewing TypeScript/JavaScript code, including code inside a spec or a plan.
alignfirst-setup-guide
Install, upgrade, recommend, or combine AlignFirst skills, plans-share, docmap, and workspace in a consumer repository, or prepare a repository and Linux deployment for an AlignFirst Developer.