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 nimadorostkar/Claude-Skills-collection --skill architecture-decisionsgit clone --depth 1 https://github.com/nimadorostkar/Claude-Skills-collectionWrote 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/nimadorostkar/claude-skills-collection/architecture-decisions)<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/architecture-decisions"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/architecture-decisions/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/nimadorostkar/claude-skills-collection/architecture-decisions"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/architecture-decisions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Data Exfiltration · line 3 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
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 | $0.00043 | $0.01062 |
| Opus 5 | $0.00022 | $0.00531 |
| Sonnet 5 | $0.00009 | $0.00212 |
| Haiku 4.5 | $0.00004 | $0.00106 |
Grade A, and why
architecture-decisions 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Decisions
Purpose
Record why a decision was made, not just what was decided. Code shows the what. The context, the alternatives, and the constraints that made the choice correct at the time are otherwise lost within months.
When to Use
- Choosing a database, framework, protocol, or vendor.
- Adopting or abandoning an architectural pattern.
- Making a decision that will be expensive to reverse.
- Revisiting a decision someone made and nobody can explain.
Capabilities
- ADR authoring in a consistent, greppable format.
- Options analysis with honest trade-offs.
- Superseding and amending existing decisions without rewriting history.
Inputs
- The decision to be made and the forces acting on it.
- The realistic options, including "do nothing".
- Constraints: team, time, budget, compliance, existing systems.
Outputs
A numbered ADR in docs/adr/NNNN-short-title.md with:
- Status: proposed, accepted, superseded by NNNN.
- Context: the situation and the forces, written so a new hire understands them.
- Decision: what was chosen, in the active voice.
- Consequences: what becomes easier, what becomes harder, what is now hard to reverse.
Workflow
- State the forces — What is pushing on this decision? Latency, cost, team familiarity, compliance, an existing commitment. If there are no forces, there is no decision to record.
- List real options — Including the status quo. An ADR with one option is a justification, not a decision.
- Evaluate against the forces — Each option, against each force. The trade-offs should be visible in the table.
- Decide and state it plainly — "We will use PostgreSQL." Not "PostgreSQL was considered favorably."
- Write the consequences honestly — Especially the negative ones. An ADR with only upsides is marketing.
- Never delete an ADR — Supersede it. The old reasoning is what explains the old code.
Best Practices
- One decision per record. If the title needs "and", split it.
- Write for someone who joins in two years and has none of your context.
- Include the numbers that drove the decision. "Cheaper" is not a reason; "$400/month vs $3,100/month at our volume" is.
- Record decisions you rejected loudly, especially the popular ones. The next person will ask "why not Kafka?" — answer it once, in writing.
- Keep them in the repository, in version control, next to the code they govern.
- Status changes are edits to the old ADR; the reasoning is never rewritten.
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 · 111 lines · 43 tokens per session scan A e7bfe3001fef
architecture-decisions is a skill published in the GitHub repository nimadorostkar/Claude-Skills-collection (26 stars, last pushed 24d ago), licensed MIT. It adds 43 tokens to every session and 1,062 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
offensive-crypto-attacks
Systematic methodology for identifying and exploiting cryptographic implementation weaknesses in real-world applications. Covers padding oracle attacks against CBC-mode ciphers with PKCS7 padding (Vaudenay's original attack through modern padbuster automation), ECB mode exploitation including block cut-and-paste and…
offensive-c2-frameworks
Command and Control framework deployment, configuration, and operational tradecraft for red team engagements. Covers Cobalt Strike (malleable C2 profiles, Beacon types HTTP/HTTPS/DNS/SMB, Beacon Object Files for in-memory execution, sleep and jitter tuning, named pipe pivoting), Sliver (implant generation across…
offensive-parameter-pollution
HTTP parameter pollution (HPP) checklist: duplicate parameter injection, backend vs frontend parsing differences, WAF bypass via HPP, server-side vs client-side HPP, and practical exploitation patterns. Use when testing web applications for parameter handling flaws.
offensive-wifi
Wireless / 802.11 attack methodology for red team engagements and wireless security assessments. Covers monitor-mode setup, WPA/WPA2-PSK handshake capture and PMKID attacks, WPA3 SAE downgrade and Dragonblood, WPA-Enterprise (EAP) attacks (MSCHAPv2 cracking, EAP-TLS cert theft, evil-twin RADIUS), Karma / Known Beacons…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
seo
Optimize for search engine visibility and ranking. Use when asked to "improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", or "search engine optimization".