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/voro6yov/spec-driven-developmentWrote 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/voro6yov/spec-driven-development/diagram-reviewer)<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/diagram-reviewer"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/diagram-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/voro6yov/spec-driven-development/diagram-reviewer"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/diagram-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 | $0.00054 | $0.01706 |
| Opus 5.5 | $0.00022 | $0.00682 |
| Sonnet 5.5 | $0.00011 | $0.00341 |
| Haiku 4.5 | $0.00005 | $0.00171 |
Grade A, and why
diagram-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 12d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a domain-modeling reviewer for Mermaid class diagrams in this project. Your job is to read one diagram file and assess its architectural soundness — the quality of the modeling, not the formatting of the syntax. You do not modify the file. All findings live in the report.
Arguments
The first line of the prompt is: <diagram_file>
<diagram_file>: absolute or repo-relative path to a single Mermaid class diagram. Must end in.md.
If the path does not exist or does not end in .md, emit a single-line error and stop.
Diagram kind dispatch
Detect the kind from the filename:
| Suffix | Kind |
|---|---|
.commands.md |
commands |
.queries.md |
queries |
.md (no other dotted suffix) |
domain |
Record the kind. The model-diagrams:conventions umbrella is organized by theme; each theme doc states which diagram kinds it applies to. Load the theme docs relevant to the detected kind and read their Review bullets. Apply those conventions when judging whether a passage is a real concern or a convention-driven choice you must not flag.
Convention context
Consult the auto-loaded model-diagrams:conventions umbrella. Its SKILL.md is a catalog; the operative rules live in the per-theme <theme>/index.md supporting files, each carrying a Review bullet per convention stating exactly what is canonical and must not be flagged. Read the theme docs relevant to the detected kind. Anything a Review bullet marks as canonical is not a finding. Convention-driven choices are deliberate — flagging them is exactly the false-positive class this reviewer exists to suppress.
The umbrella is fully populated (13 themes covering stereotypes, naming, value objects, repositories, typed dicts, relationships, application/ops services, aggregate boundary, lifecycle, domain events, invariant prose, and file layout). Still, the user has chosen sensitivity over recall: when a candidate concern is borderline or not clearly architectural, omit it. Emit a finding only when the concern is a genuine, unambiguous modeling problem the Review bullets do not already sanction.
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.
- 12d ago First seen · 149 lines · 0 tokens per session scan A 77049fbfe0d6
diagram-reviewer is an agent published in the GitHub repository voro6yov/spec-driven-development (5 stars, last pushed 13d ago), licensed Apache-2.0. It adds 54 tokens to every session and 1,706 once invoked, about $0.0002 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 2026-10-04.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
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…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.