Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/handarbeit/fabriknpx agentmods add skills/handarbeit/fabrik/architecture-foundationsWrote 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/handarbeit/fabrik/architecture-foundations)<a href="https://agentmods.dev/skills/handarbeit/fabrik/architecture-foundations"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/architecture-foundations/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/handarbeit/fabrik/architecture-foundations"><img src="https://agentmods.dev/badge/skills/handarbeit/fabrik/architecture-foundations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00148 | $0.05205 |
| Opus 5 | $0.00074 | $0.02603 |
| Sonnet 5 | $0.00030 | $0.01041 |
| Haiku 4.5 | $0.00015 | $0.00521 |
Grade A, and why
architecture-foundations 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 9d 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 — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Foundations
Establish what is already fixed, what the shared things are called, who owns each of them, and who is allowed to do what — so that specifications written weeks apart still describe one system.
Read ../../CONVENTIONS.md first. It carries the shared rules — stages, where work is
saved, the tree, markers, the decision register, interview rules, precedence, gates,
decision records and the baseline status footer. This skill does not repeat them.
This is stage 3 of 5, and it is the one stage that is a living document, not a one-off interview.
Run this early, and run it again
Specifications drift. Each new feature introduces concepts the earlier ones could not anticipate, and without something owning the shared entities the drift is silent: two specs model the same employee differently, three disagree about which state triggers what, and nobody notices until integration.
So: run this as soon as the first few specifications exist — you do not need all of them — and re-run it whenever a new specification introduces an entity, a state, or an authority. On a re-run, lead with what has changed since last time and what the new specs broke, rather than starting from the top.
The cost of running it early is that some of it will be wrong. The cost of running it late is that everything built in between was built against nothing.
What this is not
Not budgets, build order, fitness functions, or mechanisms chosen for a quality — performance, cost, scale, resilience. Those are stage 5, and they cannot be written until the experience baseline exists — they convert user-facing guarantees into system guarantees, and the guarantees do not exist yet.
The test for what belongs here: does it need to know how the product looks or feels? Which feature owns the employee record does not. How long an offline capture may survive does. The first is yours now; the second waits.
If the architect starts designing mechanisms — and they will — record it under Deferred to the baseline and move on.
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.
- 9d ago First seen · 429 lines · 148 tokens per session scan A 05793bd9421f
architecture-foundations is a skill published in the GitHub repository handarbeit/fabrik (22 stars, last pushed today), licensed Apache-2.0. It adds 148 tokens to every session and 5,205 once invoked, about $0.0007 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
flame-harness-evaluator
Phase 6 — skeptical QA. Run the game, watch it, then judge against the contract. Default = functional check; --strict adds quality and edge-case passes.
flame-harness-admob
Phase 7 — analyze the game, decide a rewarded-ad strategy, guide manual AdMob ad-unit creation, and inject googlemobileads + ATT/UMP consent code.
flame-harness-submit
Phase 10 — upload store text metadata + categories via fastlane, then pause with exact manual steps for the final iOS review submission and Android production promotion.
flame-harness-design
Phase 3 — define the Flutter designtokens.dart spec (palette, typography, spacing), the game's art/visual concept, and the asset/audio sourcing plan.
flame-harness-retro
Phase 11 — score the completed pipeline against Anthropic's 9 harness principles plus game quality, and write the retrospective.
flame-harness-screenshot
Phase 9 — capture store screenshots in the game's configured locales via integrationtest (ads hidden), fill ASO keywords, and upload via fastlane.