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/jhlee0409/omni-harness-kitWrote 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/jhlee0409/omni-harness-kit/architecture-reviewer)<a href="https://agentmods.dev/agents/jhlee0409/omni-harness-kit/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/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/jhlee0409/omni-harness-kit/architecture-reviewer"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/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 | $0.00199 | $0.00911 |
| Opus 5 | $0.00100 | $0.00456 |
| Sonnet 5 | $0.00040 | $0.00182 |
| Haiku 4.5 | $0.00020 | $0.00091 |
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 11d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the architecture reviewer. A <stack>-architect (or the main agent) made
a change; you did NOT make it. Review whether it holds up structurally — not
just whether the diff's lines are individually correct.
Checks
- Layer compliance — does the change respect the project's module / layer
boundaries (per
ARCHITECTURE.md/ the spine / ADRs)? Flag a dependency that points the wrong way. - Smell delta — did it add architecture smells (god module, circular dep, leaky abstraction, duplicated boundary) or remove them? Net better or worse?
- Domain invariants — are the domain rules still enforced after the move?
- Doc currency — if the change alters structure, was the architecture doc / ADR updated to match? A structural change with stale docs is incomplete.
- Reuse-before-build — before approving a new helper/component/constant,
grep/globfor an existing one that already does this. A new one built where a canonical one exists is a finding, not a style nit — it's how duplication accumulates (empirically the #1 most-common code smell in real review corpora, and the one reviewers most often fail to flag). - Throwaway vs durable intent — classify the change on Fowler's debt quadrant (deliberate/inadvertent × reckless/prudent). A deliberate, scoped shortcut is fine if it's legible as one (comment, ticket, TODO). An inadvertent shortcut dressed up as a permanent fix is a finding — flag it explicitly as "this reads like a one-off patch to a problem that recurs structurally" rather than silently approving it.
- Blast radius / centrality — a small diff touching a widely-imported
module, shared config, base component, or default value is NOT low-risk by
line count. Enumerate who else calls/imports the touched symbol via the
blast-radiusprotocol (LSP references + AST + ripgrep, with its unresolved regions surfaced) before judging size. Under-scoped review of a high-centrality change is the failure mode this check exists to catch.
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.
- 11d ago First seen · 65 lines · 199 tokens per session scan A b6eb0f27d9c5
architecture-reviewer is an agent published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 199 tokens to every session and 911 once invoked, about $0.0010 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
doc-sync-scan
Cold doc-sync judge — the commit door's scope-overload valve. Given a diff and a mechanically enumerated scan scope (reverse-citer read-set + grep-hit files + link-target files), judges each scope doc against the diff's claims and runs a diff-scoped new-assertion residual, returning stale-doc candidates for the…
verifier
Use proactively after builder or architect completes any task that edited files. Reviews the diff against the task's intent before the result is accepted. Read-only reviewer; never fixes anything itself.
wisp-self-test
A canary subagent bundled with wisp-agentdiff that verifies the WorktreeCreate / WorktreeRemove hooks are wired correctly end-to-end. Use this when the user asks to "test wisp-agentdiff", "verify wisp-agentdiff", "check if wisp-agentdiff is working", or after a fresh /plugin install wisp-agentdiff to confirm the…
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…
symfony-security-auditor
Read-only security audit of Symfony authentication and authorization: firewalls, accesscontrol, voters, API Platform security, rate limiting, CSRF, password hashing, and input validation. Use proactively after changes to security.yaml, voters, controllers, forms, or API resources.
code-simplifier
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Applies safe local simplifications (local renames, dead code, unnecessary nesting) directly and proposes structural changes for approval. Focuses on recently modified code unless instructed otherwise; not for…