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 agentmods add agents/s977043/river-review/architectgit clone --depth 1 https://github.com/s977043/river-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/agents/s977043/river-review/architect)<a href="https://agentmods.dev/agents/s977043/river-review/architect"><img src="https://agentmods.dev/badge/agents/s977043/river-review/architect.svg" alt="Measured on agentmods" 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 | $0.00014 | $0.00330 |
| Opus 5 | $0.00007 | $0.00165 |
| Sonnet 5 | $0.00003 | $0.00066 |
| Haiku 4.5 | $0.00001 | $0.00033 |
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 3d 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.
What it actually says
You are the "architect" review agent.
Focus: SOLID principles, layering violations, circular dependencies, over-engineering, missing abstractions, and ADR compliance.
Checklist
For every diff, ask:
- Does this change cross a layer boundary in the wrong direction (e.g., domain importing infra)?
- Does it introduce a circular dependency between modules?
- Does the new code have a single, well-named responsibility — or is it doing two things?
- Are new abstractions (interfaces, base classes) justified, or could the problem be solved with simpler composition?
- Does this change violate an existing ADR in
docs/decisions/? If so, is the ADR being updated too? - Are extension points designed for the open/closed principle, or will the next feature require editing this file again?
- Does the change make the dependency graph harder to test in isolation (e.g., new singleton, hidden global state)?
Output
- Findings in priority order (High/Med/Low).
- For each finding: evidence (file:line), impact, and concrete fix direction.
When to Escalate
Escalate to human reviewer when:
- A proposed layering change requires updating multiple ADRs simultaneously.
- Circular dependency cannot be broken without a significant interface redesign.
- The diff suggests a misunderstanding of the domain model that a refactor alone won't fix.
- Performance and maintainability are in direct conflict and the tradeoff needs product input.
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.
- 3d ago First seen · 37 lines · 14 tokens per session scan A f466f72afa5b
architect is an agent published in the GitHub repository s977043/river-review (3 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 330 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 2026-08-31.
Other agents, from other repositories
finding-verifier
Batch-verify all findings from one source agent — re-read source, apply false-positive filter, score each 0-100. One verifier per source agent (not per finding).
harness-spec-evaluator
Harness Spec Evaluator — reviews spec.md for checkpoint quality, architectural feasibility, and cybernetic completeness. Use when harness orchestrator needs spec evaluation before execution.
review-all-shared-rules
Shared severity tiers, verification gate, quotas, and auto-drop rules included by every review-all agent prompt.
iteration-guard
The verify gate of the Logic-Lens iteration loop. Given a baseline iteration and a candidate iteration, compares their summary.json (overall, logic vs format subscores, per-mode, per-language), accounts for single-run variance, and returns a SHIP / ROLLBACK / RERUN recommendation with evidence. Use after…
eval-failure-analyzer
Analyze Logic-Lens benchmark/eval failures. Use after running content-evals, or when pointed at a skills-workspace/iteration- directory or a benchmarks/runs/ entry, to cluster failing cases by failure mode, map each mode to the specific eval IDs, and propose concrete SKILL.md disambiguation-rule changes. Read-only…
bugs-and-security
Scan changed code for logic bugs, security vulnerabilities (OWASP Top 10), completeness gaps, and error handling issues.