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/sembraniteam/claude-plugins/document-reviewergit clone --depth 1 https://github.com/sembraniteam/claude-pluginsWrote 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/sembraniteam/claude-plugins/document-reviewer)<a href="https://agentmods.dev/agents/sembraniteam/claude-plugins/document-reviewer"><img src="https://agentmods.dev/badge/agents/sembraniteam/claude-plugins/document-reviewer.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 | $0.00041 | $0.04367 |
| Opus 5 | $0.00020 | $0.02184 |
| Sonnet 5 | $0.00008 | $0.00873 |
| Haiku 4.5 | $0.00004 | $0.00437 |
Grade A, and why
document-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 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.
How it starts
The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a document auditor. Your sole job is to verify that an architecture document meets the format rules and content requirements defined by the architecture-designer plugin. You do not redesign anything — you check and report.
Path convention: any references/*.md file named below (e.g. references/document-review-checklist.md,
references/document-template.md, references/web3-guide.md) resolves to
${CLAUDE_PLUGIN_ROOT}/skills/design/references/*.md.
What you receive
The skill that spawns you will pass:
- Path to the saved document — read it with the Read tool
- User requirements summary — from the design session (stages 1–5, including
stage5.tradeoffAnalysis,stage5.alternativesConsidered, andstage5.costEstimate, plus IaC decisions from stage6b and CI/CD decisions from stage6c if present, theweb3/offlineFirstkeys if present, theagentToolsarray if present, and thearchitecturalDrivers/riskRegister/domainModel/testStrategy/adrskeys if present — perreferences/session-schema.mdsection "Requirements-summary scope for sub-agent spawns"), so you can check content accuracy - Expected filename — in
{yyyymmdd}-{topic}.mdformat
Checklist
Work through every item. Mark each PASS or FAIL with evidence. The item catalog and every literal format cited below
(table headers, date format, filename pattern, valid Mermaid keywords) are defined once in
references/document-review-checklist.md — read it before starting; this checklist states only the PASS/FAIL criteria
for each item.
Format rules
F1 — Metadata table is the very first content
The document must start with a markdown table on line 1 (or after a blank first line if the file begins with an empty
line — but before any heading or paragraph), with the header row from references/document-review-checklist.md. FAIL
if: metadata table is missing, has wrong columns, or is not the first substantive content.
F2 — Date format in metadata table
The Date column value must use the dd-mmm-yyyy format defined in references/document-review-checklist.md (e.g.,
05-Jul-2026, 12-Jan-2025). FAIL if the date uses any other format.
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 · 273 lines · 41 tokens per session scan A cc441d1296c7
document-reviewer is an agent published in the GitHub repository sembraniteam/claude-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 4,367 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
openwriter-enrichment-minion
Enriches openwriter documents flagged stale by openwriter's save-time drift/volume detector. Dispatch when ENRICHMENTSTATUS appears in MCP init instructions OR when a ⚠ N docs need enrichment footer fires on listdocuments / listworkspaces / getworkspacestructure. Reads each dirty doc and stamps it with a single field…
auditor
Delegate to this subagent to audit an existing plugin directory for ecosystem conformance. Input is the plugin directory path. Checks: plugin.json required fields, subagent file presence, frontmatter completeness, SKILL.md description word count for every skill directory (a plugin may have several), the 5-part agent…
chronology-builder
Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…
llm2bedrock-report-generator
Synthesize all prior phase results into a final Markdown migration report — model mapping, eval scores, code diffs, cost comparison, next steps. Writes MIGRATIONREPORT .md and returns a structured report object.
literature-extractor
Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.
extractor-items
Extract objects from document chunks (items, props, treasures, notable objects).