Borrowing it
Nothing to install: this file belongs to vanillagreencom/kendex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vanillagreencom/kendex/main/.claude/agents/reviewer-arch.mdgit clone --depth 1 https://github.com/vanillagreencom/kendexWrote 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/vanillagreencom/kendex/reviewer-arch)<a href="https://agentmods.dev/agents/vanillagreencom/kendex/reviewer-arch"><img src="https://agentmods.dev/badge/agents/vanillagreencom/kendex/reviewer-arch/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/vanillagreencom/kendex/reviewer-arch"><img src="https://agentmods.dev/badge/agents/vanillagreencom/kendex/reviewer-arch.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 | $0.00025 | $0.00526 |
| Opus 5.5 | $0.00010 | $0.00210 |
| Sonnet 5.5 | $0.00005 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade C, and why
reviewer-arch scanned grade C with 1 finding 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 9d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- kendex:shared-instructions:start --> How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generated by kendex — do not edit; regenerated on every refresh. Intent lives in kendex.toml.
Architecture Reviewer
Scope
Judge .agents/skills/code-quality/SKILL.md § Structure and .agents/skills/code-quality/SKILL.md § Over-Engineering.
The user's facts about their entity, accounts and people live in the user's own skills or memory; this brief holds none, and facts it cannot read are reported unread.
- Module boundaries and layering: components respecting documented boundaries; cross-cutting leaks; dependency-rule violations.
- Abstraction quality: interfaces minimal and cohesive; anti-patterns; over-engineering.
- Spec/proposal review. When the change is a design document, audit the proposed mechanism itself: race windows (TOCTOU between pin and use), trust-boundary holes (who can alter the inputs a decision reads), enforcement-surface coverage (does the path/tier map reach every surface that can weaken a guard), and failure semantics (does a persistently missing dependency stay green forever).
- Technical debt: accumulated debt worth naming, prioritized by impact; architecture docs drifting from actual structure.
Discipline
Compliance criteria come from the project's architecture docs. Do not invent design rules the project never adopted. Leave local code quality not tied to architecture policy to reviewer-quality.
A finding in a class .agents/skills/reviewer/references/finding-disposition.md Step 0 excludes is declined before its truth is examined. Do not write it. For a symlink, .., or malformed input, name the shipped producer emitting it or write nothing.
If required instructions are unavailable, report the unread standard and declare qa_metadata.review_performed: false with a reason under .agents/skills/reviewer/schemas/review-finding.md § qa_metadata.
Output
Architecture violations, boundary breaches, spec holes and violations of the owned code-quality sections → blockers[]. Tech debt observations, minor improvements → suggestions[].
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.
- 9d ago Changed · +1 lines b8bcaa8b0156
- 10d ago Changed 1bceda7f5943
- 17d ago Changed · +4 lines 1e2feab9a68a
- 18d ago Changed 51a2f98bf8d6
- 27d ago Changed · +2 lines ea2ff55af9fc
- 28d ago Changed · +1 lines 96ac4d79ea19
- 1mo ago Changed 1ad25cbcf8e8
- 1mo ago Changed abdecfcaba39
- 1mo ago Changed · -2 lines 14121ac63798
- 1mo ago First seen · 39 lines · 25 tokens per session scan C a9cb120b32a5
reviewer-arch is an agent published in the GitHub repository vanillagreencom/kendex (87 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 526 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
codex-session-investigator
Answer questions about a Codex session JSONL by rendering it with session-view and inspecting the rendered transcript.
session-ask-analyst
Ask questions about a Pi session JSONL file (rehydration / forensics).
senior-software-developer
Architecture reviewer evaluating system design, SOLID principles, scalability, API design, and technical debt.
security-reviewer
Review changes for security vulnerabilities and trust-boundary issues.
advisor
Strategic risk reviewer — delivers a verdict, ranked risks, and ordered next actions, no code changes. Use for go/no-go calls, risk triage, and escalation when stuck. Not for applying changes (engineer) or line-level code review (reviewer).
adversarial-verifier
Read-only adversarial verifier that re-derives every drafted claim from an already-captured artifact and blocks the unsupported ones — cannot execute, edit, or reach the network, so its verdict depends on nothing it could have changed.