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 wedabro/bro-skills --skill speckit.architecturegit clone --depth 1 https://github.com/wedabro/bro-skillsWrote 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/wedabro/bro-skills/speckit.architecture)<a href="https://agentmods.dev/skills/wedabro/bro-skills/speckit.architecture"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.architecture/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/wedabro/bro-skills/speckit.architecture"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.architecture.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00031 | $0.00573 |
| Opus 5 | $0.00015 | $0.00287 |
| Sonnet 5 | $0.00006 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
speckit.architecture 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission
Turn product constraints into the simplest architecture that can meet them.
Use this skill for significant technical decisions; use speckit.plan for the
feature implementation plan, speckit.ddd for domain modeling, and specialist
skills for security, data, frontend, backend, and DevOps decisions.
Protocol
0. Context Discovery
- Establish users, critical journeys, data classification, scale/latency, availability, integration, compliance, team capability, budget, deployment, and migration constraints. Separate verified facts from assumptions.
- Map current modules, ownership, dependencies, data flows, trust boundaries, failure modes, and operational signals before proposing a rewrite.
1. Option and Boundary Design
- Start with the simplest viable option. Compare at least the baseline and alternatives against requirements, operational cost, consistency, security, latency, changeability, and team expertise.
- Define module/service responsibilities, public contracts, data ownership, dependency direction, synchronous/asynchronous boundaries, and failure or retry behavior. Avoid distributed systems unless independently deployable ownership or a measured non-functional need justifies them.
- Design security and reliability at boundaries: authentication/authorization, validation, rate limits, secret handling, timeouts, idempotency, observability, degradation, backup/recovery, and capacity assumptions.
2. Decision Records
- Write an ADR before material, difficult-to-reverse choices. Include status, context, drivers, considered options, decision, consequences, risks, rollback/reversal path, implementation owner, and links to evidence.
- Never rewrite an accepted ADR to hide a changed decision; create a superseding ADR and preserve the original rationale. Keep a searchable ADR index.
3. Validation and Handoff
- Turn the chosen architecture into measurable quality attributes, explicit contracts, migration slices, test/load/DR gates, and operational runbooks.
- Run a constitution check and threat/data/operability review. Record unknowns, rejected options, and decisions requiring user approval.
- Hand approved boundaries to
speckit.planand atomic tasks; update mapping artifacts after significant implementation changes.
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 · 64 lines · 31 tokens per session scan A 43262ca929f7
speckit.architecture is a skill published in the GitHub repository wedabro/bro-skills (2 stars, last pushed 16d ago), licensed MIT. It adds 31 tokens to every session and 573 once invoked, about $0.0002 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
math-modeling
A workflow for mathematical modelling, where real-world questions are represented with mathematics and solved with code or analysis.
math-modeling
A workflow for mathematical modelling, where real-world questions are represented with mathematics and solved with code or analysis.
科研可视化工具
A research-visualisation workflow for examining data and producing publication-ready charts for scientific papers.
LaTeX工具
A tool for creating, compiling, and checking mathematical modelling papers written in LaTeX, a document system often used for technical writing.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…
DOCX工具
A tool for creating, editing, checking, and converting Microsoft Word DOCX files. It also handles LaTeX research papers, mathematical formulas, tables, tracked changes, and comments.