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/akholod/consensus-reviewWrote 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/commands/akholod/consensus-review/architecture-audit)<a href="https://agentmods.dev/commands/akholod/consensus-review/architecture-audit"><img src="https://agentmods.dev/badge/commands/akholod/consensus-review/architecture-audit/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/commands/akholod/consensus-review/architecture-audit"><img src="https://agentmods.dev/badge/commands/akholod/consensus-review/architecture-audit.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 | $0.00015 | $0.01466 |
| Opus 5.5 | $0.00006 | $0.00586 |
| Sonnet 5.5 | $0.00003 | $0.00293 |
| Haiku 4.5 | $0.00002 | $0.00147 |
Grade A, and why
architecture-audit 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 yesterday.
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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Audit
One-shot architecture audit of the entire codebase (not a line-by-line code review). Stack-agnostic. Scope — always the whole project.
Role and Lens
Role: architecture reviewer.
Lens:
- Horizontal layers (server / DB / network / business logic / UI) and vertical slices (capability) that cut across all layers.
- Analysis entry point: User workflow → Use case → Business capability. NOT screens, NOT tables, NOT endpoints.
- Look for abstraction leakage between layers and modules.
- Treat complexity as manageability of the system: can the team understand, estimate, and safely change the code without losing control over AI-generated or overengineered complexity.
Operating Mode
- Single pass, single context, no delegation to sub-agents.
- Scope — always the whole project (
$ARGUMENTSis ignored). - Output — to chat, free-form; structure it however best conveys the essence of what was found.
- Diagrams (mermaid / C4-lite / ASCII) — at your discretion, when the architectural complexity warrants it.
- Ask clarifying questions during the analysis, as soon as facts from the code are insufficient. Do not accumulate them to the end.
- Output language: English by default. If the caller passes
lang=<language>(any language, as a code or a name), write in that language. Identifiers, paths, and technical terms stay in their original form.
Severity Scale (for the findings block in Phase 5)
P0— invariant violation, abstraction leakage that blocks further development, or an architectural choice that will be expensive to untangle in the near term.P1— structural problem: blurred module boundaries, implicit contracts, paradigm mismatch with the nature of the task.P2— localized layer misalignment or minor architectural drift.
Phase 1. Inventory
Answer from facts in the code. If a fact is missing — explicitly mark it as hypothesis or ask a clarifying question.
- What business entities exist?
- What roles work with them?
- What actions do the roles perform?
- What states (lifecycle) do the entities go through?
- What invariants must not be violated?
- Where are the transaction boundaries?
- Where is async behavior, queues, background processes?
- Where are access permissions?
- Where is audit, history, versioning?
- Where are external integrations?
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.
- yesterday Changed 74ca87435244
- 1mo ago First seen · 168 lines · 15 tokens per session scan A e556af786a7a
architecture-audit is a command published in the GitHub repository akholod/consensus-review (3 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 1,466 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
merge-check
A pre-merge checklist command for a GitHub pull request. A pull request is a proposed code change, and the command checks whether it meets the project’s documented requirements before merging.
release-kick
A release command for the River Review project that checks release instructions and pull-request state, updates an out-of-date branch, and verifies the release after merging.
plan-merge-order
A command that plans the order for merging several pull requests (PRs), which are proposed code changes reviewed before entering a shared branch. It checks their status and file changes, then studies dependencies and overlap to reduce rebasing work.
verify-agent-report
A command for checking whether an agent’s reported branch, pull request, commit, or files actually exist. A pull request is a proposed code change submitted for review.
preflight
A pre-work check for finding whether a coding task or pull request is already finished, obsolete, or being handled elsewhere. A pull request is a proposed change to a code repository.
register-plugin-asset
A project command for adding a distributable command, agent, or agent skill to a plugin manifest, the file that lists what a plugin provides.