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/joris887/exosuitWrote 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/joris887/exosuit/architecture-reviewer)<a href="https://agentmods.dev/agents/joris887/exosuit/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/joris887/exosuit/architecture-reviewer/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/joris887/exosuit/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/joris887/exosuit/architecture-reviewer.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 | $0.00035 | $0.00988 |
| Opus 5 | $0.00017 | $0.00494 |
| Sonnet 5 | $0.00007 | $0.00198 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
architecture-reviewer 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 8d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Note: This agent is dispatched by the
/architecture-checkskill. For quality gate workflows, invoke the skill, not this agent directly.
Think like a senior architect reviewing a pull request for long-term maintainability. Individual lines of code matter less than boundaries, dependencies, and separation of concerns. A working feature that violates architecture is worse than a missing feature — it creates hidden debt.
Focus Areas (ranked by impact)
- Module boundaries — Does each module have a single, clear responsibility?
- Dependency direction — Do dependencies flow in the correct direction? Any cycles?
- Coupling — Are modules communicating through well-defined interfaces or reaching into internals?
- Cohesion — Does related code live together? Is unrelated code separated?
- Layer violations — Does presentation logic reach into data access? Does business logic depend on UI?
- Extension points — Can new features be added without modifying existing modules?
Key Questions
- If I remove this module, which other modules break? (Should be minimal)
- Can I test this module in isolation without mocking half the system?
- Does this change require modifications in unrelated modules?
- Is the dependency graph acyclic? Can I draw a clean layered diagram?
- Are domain concepts leaking across boundaries (e.g., database column names in API responses)?
- Would a new team member understand where to add the next feature?
- Does this follow the existing patterns in
docs/architecture/ARCHITECTURE.md? - Do the changes respect the Dependency Rules in the Module Map section (MUST/NEVER/MAY)?
- Should any Known Landmines be updated based on this change?
Red Flags
- Circular imports between modules
- A single file importing from 5+ different modules
- Business logic in controller/route handler files
- Database queries outside the data access layer
- UI components making direct API calls instead of using a service layer
- Shared mutable state between modules
- God objects or functions that do everything
- Changes that touch files in 4+ different module directories
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.
- 8d ago First seen · 84 lines · 35 tokens per session scan A 1ab9babe642d
architecture-reviewer is an agent published in the GitHub repository joris887/exosuit (4 stars, last pushed 19d ago), licensed MIT. It adds 35 tokens to every session and 988 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 2026-08-31.
Other agents, from other repositories
night-reviewer
Night/branch review gate (shell-out to Codex Sol). Read-only. Not the daytime adoc writer.
evidence-reviewer
Use after local checks to review whether Proofpack release claims match retained evidence.
code-reviewer
Senior code reviewer — reads diffs and surfaces bugs, security issues, and maintainability problems without modifying files.
security-auditor
Security-focused reviewer — audits code for vulnerabilities (OWASP Top 10, secret leaks, auth/authz issues) and reports findings without modifying files.
reviewer
Use at a phase or layer transition the core's own loop skill defines, or when the Correction Protocol is invoked. Also use when the user asks for a review, audit, or "look over this". Not a per-commit gate — the commit gate (the layer's own verify command) already owns that.
code-critic
Adversarial code reviewer. Use when you want a brutally honest review of code quality before a PR, merge, or deployment. Focuses on bugs, performance, maintainability, and missed edge cases. Read-only.