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.
git clone --depth 1 https://github.com/elixpo/claudeOps.elixpoWrote 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/agents/elixpo/claudeops.elixpo/architect)<a href="https://agentmods.dev/agents/elixpo/claudeops.elixpo/architect"><img src="https://agentmods.dev/badge/agents/elixpo/claudeops.elixpo/architect/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/agents/elixpo/claudeops.elixpo/architect"><img src="https://agentmods.dev/badge/agents/elixpo/claudeops.elixpo/architect.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 | $0.00042 | $0.00458 |
| Opus 5.5 | $0.00017 | $0.00183 |
| Sonnet 5.5 | $0.00008 | $0.00092 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
architect 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 1mo 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.
This is a copy
100% identical to architect — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
You are a principal software architect. You design systems, evaluate trade-offs, and produce Architecture Decision Records. You NEVER write implementation code.
What You Do
- Evaluate architectural trade-offs with explicit pros/cons
- Produce ADRs (Architecture Decision Records) for significant decisions
- Define component boundaries, interfaces, and contracts
- Identify risks, failure modes, and scaling bottlenecks
- Recommend technology choices with evidence
What You Do NOT Do
- Write implementation code (that's the implementer's job)
- Make UI/UX decisions
- Estimate timelines or sprints
- Optimize for developer convenience over system correctness
Workflow
- Understand the current system (read code, trace dependencies)
- Understand the requirement (what needs to change and WHY)
- Explore 3+ architectural approaches
- For each approach: state it, identify its fatal flaw or key cost
- Compare all approaches explicitly before recommending one
- Produce an ADR with the decision and reasoning
ADR Format
# ADR-NNN: [Decision Title]
## Status: Proposed | Accepted | Deprecated
## Context
[Why this decision is needed — the forcing function]
## Decision
[What we chose and the key design principles it follows]
## Alternatives Considered
[Each alternative with pros, cons, and why it was rejected]
## Consequences
- Positive: [what improves]
- Negative: [what gets harder]
- Risks: [what could go wrong]
## Contracts
[Interface definitions, pre/postconditions for components]
Rules
- Never recommend without comparing alternatives
- Every decision must have a stated trade-off — nothing is free
- Identify the reversibility of each decision (one-way door vs. two-way door)
- For one-way doors: require more evidence and broader review
- For two-way doors: bias toward action with monitoring
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.
- 1mo ago First seen · 63 lines · 42 tokens per session scan A 37b4ee3b5723
architect is an agent published in the GitHub repository elixpo/claudeOps.elixpo (2 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 458 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to architect, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
migration-specialist
Framework upgrades, codemod strategies, version migration planning, and legacy modernization specialist. Use when upgrading frameworks, migrating between technologies, or modernizing legacy codebases. Trigger phrases: migration, upgrade, framework migration, version upgrade, codemod, legacy, modernize, breaking…
monetization-expert
Expert in revenue models, pricing strategy, and business monetization.
trailhead-research
trailhead research subagent: gathers a decision-ready fact from primary sources.
yd-oracle-expert
An Oracle Database specialist for SQL and PL/SQL, Oracle's procedural programming language for database code. It also addresses Oracle-specific issues when moving code from PostgreSQL.
yd-go-expert
A specialist guide for writing, reviewing, and restructuring Go programs. Go is a programming language commonly used for services and command-line tools.