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 cosmicstack-labs/mercury-agent-skills --skill architecture-decision-recordsgit clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-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/cosmicstack-labs/mercury-agent-skills/architecture-decision-records)<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/architecture-decision-records"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/architecture-decision-records/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/cosmicstack-labs/mercury-agent-skills/architecture-decision-records"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/architecture-decision-records.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 20 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.
- medium MCP Rug Pull · line 393 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00019 | $0.03716 |
| Opus 5 | $0.00010 | $0.01858 |
| Sonnet 5 | $0.00004 | $0.00743 |
| Haiku 4.5 | $0.00002 | $0.00372 |
Grade A, and why
architecture-decision-records 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 11d 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 — 496 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Decision Records
Capture architectural decisions systematically so your team understands not just what was decided, but why — and what alternatives were considered.
Core Principles
1. Decisions Are More Important Than Diagrams
A diagram shows the current architecture. An ADR explains why it is that way. When someone asks "why did we do it this way?" the ADR is the answer.
2. Capture Context, Not Just Conclusions
Every architectural decision exists in a web of constraints, tradeoffs, and alternatives. If you only record the conclusion, future engineers will wonder if you considered the obvious alternative — and they might reverse it without understanding why the original choice was made.
3. Lightweight Is Sustainable
An ADR doesn't need to be a 10-page document. A structured 1-page record is infinitely better than nothing. If the process is heavy, people won't follow it.
4. Accept and Track Superseded Decisions
Architecture evolves. An ADR that gets superseded is a success — it means the system adapted. Old ADRs remain valuable as historical records of the team's thinking.
ADR Maturity Model
| Level | Capture | Storage | Review | Enforcement |
|---|---|---|---|---|
| 1: Tribal | Decisions in Slack/meetings | Nobody remembers | None | None |
| 2: Documented | Some decisions written down | Shared drive or wiki | Sporadic | None |
| 3: Systematic | All significant decisions as ADRs | In repository alongside code | PR review requires ADR for arch changes | Basic: "needs ADR" check |
| 4: Integrated | ADRs linked to implementation | Searchable, indexed, cross-referenced | Mandatory ADR review for arch changes | Automated: lint checks for ADR format |
| 5: Governance | ADRs drive architecture reviews | Catalog with status dashboard | Regular architecture review board | Automated compliance checks |
Target: Level 3 for most teams. Level 4+ for regulated or long-lived systems.
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.
- 11d ago First seen · 496 lines · 19 tokens per session scan A 612665710e1b
architecture-decision-records is a skill published in the GitHub repository cosmicstack-labs/mercury-agent-skills (470 stars, last pushed 17d ago), licensed MIT. It adds 19 tokens to every session and 3,716 once invoked, about $0.0001 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
modern-saas-builder
Founder-minded senior product engineer and SaaS architect skill. Use when building, planning, architecting, validating, designing, testing, securing, deploying, or monetizing modern SaaS products, micro-SaaS, web apps, AI agents, Web3/Base applications, agent commerce, or Telegram bots/Mini Apps. Always active when…
claude-md-improver
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.