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/softspark/ai-toolkit/architecture-decisionnpx skills add softspark/ai-toolkit --skill architecture-decisiongit clone --depth 1 https://github.com/softspark/ai-toolkitWrote 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/softspark/ai-toolkit/architecture-decision)<a href="https://agentmods.dev/skills/softspark/ai-toolkit/architecture-decision"><img src="https://agentmods.dev/badge/skills/softspark/ai-toolkit/architecture-decision.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 | $0.00044 | $0.00925 |
| Opus 5 | $0.00022 | $0.00463 |
| Sonnet 5 | $0.00009 | $0.00185 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
architecture-decision 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 6d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Decision Skill
Core Philosophy: "Everything is a Trade-off"
There are no "best solutions", only solutions with the right set of trade-offs for the specific context.
Decision Making Process (RFD / RFC)
- Context: What is the problem? Why now?
- Constraints: Budget, Time, Skillset, Legacy.
- Options: Propose at least 3 viable options.
- Trade-off Analysis: Compare constraints vs options.
- Recommendation: Choose one and justify.
Trade-off Analysis Matrix (Template)
| Feature | Option A (e.g. SQL) | Option B (e.g. NoSQL) | Option C (e.g. File) |
|---|---|---|---|
| Scalability | Medium (Vertical) | High (Horizontal) | Low |
| Consistency | Strong (ACID) | Eventual (BASE) | N/A |
| Complexity | Low (Known) | Medium (New tech) | Low |
| Cost | $$ | $$$ | $ |
Architecture Note
When a decision is made, document it.
# Architecture Note: Use PostgreSQL for Main Database
## Status
Accepted
## Context
We need a reliable, relational database for user data...
## Decision
We will use PostgreSQL 16.
## Consequences
- Positive: ACID compliance, rich ecosystem.
- Negative: Scaling writes requires sharding later.
Critical Factors to Evaluate
- Reliability (Availability, Fault tolerance)
- Scalability (Throughput, Latency)
- Maintainability (Simple vs Easy, Ecosystem)
- Security (AuthN/Z, Encryption)
- Cost (Infrastructure, License, Cognitive load)
Rules
- MUST present at least 3 viable options, including "status quo / do nothing" when relevant
- MUST state constraints (budget, time, team skillset, legacy) before enumerating options — options without constraints are arbitrary
- NEVER recommend an option without explicitly naming its failure mode and what would trigger revisiting the decision
- CRITICAL: the output is a document (ADR / RFC / RFD), not code changes. Code work belongs in
/planor/refactor-plan. - MANDATORY:
Consequencessection names both Positive and Negative effects. A decision with only upside is not honestly analysed.
What ships with it
1 file 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.
- 6d ago First seen · 80 lines · 44 tokens per session scan A dc29d15d78fa
architecture-decision is a skill published in the GitHub repository softspark/ai-toolkit (169 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 925 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 2026-08-30.
Other skills, from other repositories
cline-fix-volatile-msg
Ladder-aware Cline Anthropic caching — verify the rolling read/write ladder on the wire, then add the tools breakpoint and tune TTL. Updated for the 2026-08 AI-SDK monorepo.
continue-gemini-explicit
Continue's Gemini provider doesn't use the cachedContents API at all. Add explicit caching for sessions over the minimum token threshold.
roo-fix-volatile-msg
Ladder-aware Roo Code Anthropic caching — verify the rolling read/write ladder on the wire, then close the real gaps (Vertex 4-block budget, MiniMax path).
aider-1h-ttl
Aider uses 5min TTL by default and works around long pauses with keepalive pings. Wire up the 1h TTL beta instead.
cline-openai-cache-key
Cline OpenAI native provider sends no promptcachekey. Add a stable per-task key so cachedtokens stops being zero.
continue-enable-defaults
Continue's prompt caching is opt-in via config and off by default. Flip the default to systemAndTools.